A source-linked comparison across the complete Podium ADE rubric. 6 criteria have sourced findings for both products; 6 were also cross-checked by a second agent for both. 28 rows have at least one sourced finding, including 28 with an agent-cross-checked finding. No score or winner is inferred.
Each finding carries its own verification status, scope and dates. Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.
Rubric
0.3 · 51 criteria
Last source check
2026-09-23
Next source check due
2026-10-07
Agent cross-checked for both
6 criteria
Podium source checks
2026-09-23
Proliferate source checks
2026-09-23
Access and agent choice
ACC-01
Client access
Judgment rule. List desktop OS and minimum versions, iOS, Android, browser, mobile browser, CLI and editor extensions separately. For each client, record start, steer, approve, review and resume actions, notifications and plan restrictions. Test moving the same task from desktop to phone; distinguish an installable mobile app from a mobile website and from status-only monitoring.
Podium
Agent cross-checkedpartial
macOS desktop and browser access are documented. Windows/Linux are previews; phone web access is described and native iPhone release is planned.
Scope
Surfaces: Desktop client, Browser client and self-hosted server, Podium CLI · Version: 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Public README describes these clients; release installation and cross-device behavior were not tested. Windows/Linux are explicitly previews, and native iPhone availability is planned.
9 atomic answers
Desktop os [supported] macOS; Windows and Linux preview builds. Sources: podium:readme.
Mobile apps [unknown] Mobile apps: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Editor extensions [unknown] Editor extensions: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Task actions [unknown] Task actions: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Notifications [unknown] Notifications: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Cross device continuity [unknown] Cross device continuity: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Judgment rule. List supported harnesses and model providers separately, including custom adapters. Record whether the product embeds a harness, controls its sessions through an API, or only launches its terminal command. Verify at least two different harnesses before describing mixed-harness operation as observed.
Podium
Agent cross-checkedpartial
Public documentation lists Claude Code, Codex, Grok, opencode and Cursor harnesses and cross-harness delegation. Mixed-harness behavior has not been tested.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
5 atomic answers
Harnesses [supported] Claude Code, Codex, Grok, opencode and Cursor. Sources: podium:readme.
Model providers [unknown] Model providers: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Custom adapters [unknown] Custom adapters: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Session integration [supported] Persistent terminal sessions are documented. Sources: podium:readme.
Mixed harness operation [unknown] Mixed harness operation: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
ACC-03
Subscriptions, API keys and vendor credits
Judgment rule. Record bring-your-own agent subscription, bring-your-own API account, vendor credits and local models as separate routes. List supported plans, models/modes, multiple-account switching and what works without a vendor account or token purchase. Existing subscription support cannot be inferred from API-key support. Record required extra payments and documented provider restrictions.
Podium
Agent cross-checkedpartial
Podium supports native coding-agent logins and managed provider credentials. Claude subscriptions and local ChatGPT/Codex login are explicitly supported paths, alongside Anthropic and OpenAI API keys.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Do not generalize subscription compatibility to every plan/harness. Provider limits and terms still apply. No reseller/pricing claim inferred.
7 atomic answers
Agent subscriptions [supported] Native Claude subscription and local ChatGPT/Codex login use provider plan capacity. Managed Claude setup-token is also offered. Sources: podium:v4-accounts, podium:v4-accounts-hub.
Api accounts [supported] Managed Anthropic API keys drive Claude Code and OpenAI API keys drive Codex. Sources: podium:v4-accounts.
Vendor credits [unknown] Vendor credits: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Local models [unknown] Local models: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Account switching [partial] Users choose native or supported managed accounts. Rotating several subscription logins across agents is explicitly Coming soon. Sources: podium:v4-accounts, podium:v4-accounts-hub.
Vendor account requirement [unknown] Vendor account requirement: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Provider restrictions [partial] Managed credentials have explicit harness pairings; OpenRouter is not offered as a managed coding account because the shipped coding CLIs do not consume that key. Sources: podium:v4-accounts.
Judgment rule. Measure fresh install to first successful task, with manual steps and failures. Test a local directory without Git, a local Git repo without a remote, and a GitHub-backed repo separately. Record whether account, project, host, credential and permission prerequisites are explained before accepting an unusable prompt. Evaluate managed-cloud setup and first-class BYO VPS installer/onboarding independently of hidden settings or a DIY shell recipe.
Podium
Agent cross-checkedpartial
Headless VPS setup and machine joining have documented installer commands. Setup effort, no-Git projects and automated environment repair are untested.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-23
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
7 atomic answers
First task setup [unknown] First task setup: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No git [unknown] No git: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Local git without remote [unknown] Local git without remote: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Hosted git [unknown] Hosted git: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Prerequisite guidance [unknown] Prerequisite guidance: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Managed cloud setup [unknown] Managed cloud setup: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
ACC-05
Programmable access
Judgment rule. Inventory actual CLI, API, SDK, MCP and webhook operations for create, inspect, steer, stop and review. Record authentication and API stability. Having an MCP client that uses external tools is different from exposing the product to other agents over MCP.
Podium
Agent cross-checkedpartial
CLI includes issue creation, reading, claim/update, dependencies and artifact access. This pass does not validate an externally stable API contract.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-23
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
ACC-06
External tools and extensions
Judgment rule. Record MCP client support, plugins, custom tools, skill/instruction import, integration authentication and permission scope. Name which component provides each connection and whether setup is product-managed or inherited from the underlying harness. Verify one external-tool call and its access boundary where available.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
ACC-07
Client implementation
Judgment rule. For each desktop/mobile client, record native platform UI, Electron, Tauri, React Native, web/PWA or unknown, plus hybrids. Require official technical docs or pinned source/build evidence. Tauri is not synonymous with fully native UI. Keep implementation choice separate from measured responsiveness and usability.
Podium
Agent cross-checkedpartial
Desktop source uses Tauri 2; mobile source uses Expo/React Native. Native mobile release availability is not established.
Scope
Surfaces: Desktop client, Mobile client source; native release not established · Version: 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Planning and context
PLAN-01
Intake and external tracker relationship
Judgment rule. Record local creation, prompt intake, issue import and chat/Git triggers. Identify the authoritative tracker, stable issue IDs, one-way or two-way sync, supported edits and operations requiring a trip back to Linear/GitHub/Jira. Importing or attaching a ticket is not native issue management. Answer PLAN-06 and PLAN-07 separately.
Podium
Agent cross-checkedpartial
Podium implements its own issue records and CLI creation/editing. External tracker sync has not been established.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-23
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
Sync [unknown] Sync: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Supported edits [supported] Title, description, brief, priority, assignee, stage and labels have command surfaces. Sources: podium:issue-cli, podium:issue-model.
External roundtrips [unknown] External roundtrips: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
PLAN-02
Durable task plans
Judgment rule. Record task plans and acceptance criteria, editors, revision history and links to implementation. Test amending a task while work is running, restarting and revisiting it later. A task-specific starting brief, reusable memory and a persistent product specification are different objects; product specs are judged in PLAN-08.
Podium
Agent cross-checkedpartial
Issue briefs, design, acceptance criteria and notes persist as issue fields. Filled design/acceptance/notes fields are editable in the human issue page; agents edit them through issue commands.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
No executed restart/revision-history scenario. Do not claim automatic plan maintenance or formal plan approval.
7 atomic answers
Plans [partial] Durable issue brief/design/notes can hold the plan; this is not proof of a dedicated revision-controlled plan object. Sources: podium:v4-issue-body, podium:v4-issue-registry.
Acceptance criteria [supported] Issues have a persistent acceptance field displayed and editable in the issue page when populated. Sources: podium:v4-issue-body.
Revisions [unknown] Revisions: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Implementation links [unknown] Implementation links: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Restart persistence [unknown] Restart persistence: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
PLAN-03
Hierarchy, dependencies and evolving scope
Judgment rule. Record epics, arbitrary parent/child depth, blockers, readiness, dependency enforcement and state propagation. Start with a simple interactive task, grow it into an epic and retain its identity, discussion, history and outputs. Verify blockers actually prevent dispatch. Record whether a rigid preselected workflow is required, and whether changing scope requires recreating work.
Podium
Agent cross-checkedpartial
Podium supports persistent parent/sub-issue relationships and dependency links, including reparenting an existing issue without replacing its identity. Dependency and containment cycles are refused.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Readiness propagation and end-to-end multi-day epic behavior remain separate questions.
Enforcement [partial] Self-dependencies and dependency/containment cycles are refused. This is not blanket evidence for all execution-readiness enforcement. Sources: podium:v4-issue-hierarchy.
State propagation [unknown] State propagation: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Identity retention [supported] Reparent updates the existing issue row, retaining its ID. Sources: podium:v4-issue-hierarchy.
Workflow constraints [unknown] Workflow constraints: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
PLAN-04
Shared context and memory
Judgment rule. List repository instructions, skills, project docs and cross-session/cross-harness memory. Record scope, provenance, citation, correction/deletion and stale-context controls. Test what survives a new session or colleague takeover. A notes page or shared file is not automatically a maintained spec or managed memory.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
PLAN-05
Architecture and API awareness
Judgment rule. Record code search, repository indexing, external knowledge and multimodal inputs, with source freshness and access scope. Ask an agent to use an existing API under a documented architecture rule, then propose a conflicting change. Check retrieval, citation, conflict detection and review-time enforcement separately. A large context window or an instruction file alone does not prove architectural consistency.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
PLAN-06
Native issue management and idea backlog
Judgment rule. Enumerate create, edit, discuss, prioritize, label, assign, search, filter, archive, reopen and project/epic views within the product. Save an idea without creating a running agent, refine it with another person, and explicitly mark it ready or dispatch it later. Record separate task/session entities, metadata depth, multiple sessions per task, durable state transitions and whether an external tracker remains necessary.
Podium
Agent cross-checkedpartial
Public source exposes native issue creation with an optional start flag, separate dispatch, editing and search. Issue records have their own identity. Released behavior and the idea-to-epic scenario remain untested.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
Reopen [unknown] Reopen: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Project epic views [unknown] Project epic views: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Durable states [unknown] Durable states: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
External tracker requirement [unknown] External tracker requirement: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
PLAN-07
Agent-native issue operations
Judgment rule. Verify an agent can read/create/update the same durable issue IDs and fields humans use, claim/assign work, change state, create dependencies/children and report blockers/results through documented CLI/API/MCP. Check that human views reflect actual writes with attribution, permissions and conflict handling. Distinguish shared authoritative records, synchronized external records, agent-private metadata and prompt-only conventions.
Podium
Agent cross-checkedpartial
Public CLI source calls the issue service for canonical issue IDs: create/update/claim, parent relationships, dependencies and artifacts. Authorization, concurrent edits and released behavior remain untested.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
PLAN-08
Living product specifications
Judgment rule. Record persistent requirements across tasks/releases, editable by humans and agents with attributable revisions and approval rules. Verify requirement-to-task/implementation links, retrieval during later tasks, drift detection and consideration during review/quality control. Amend a requirement after one task ships, then implement another. A one-time spec-to-plan workflow, per-task brief, memory store or unreferenced document does not establish a living product spec.
Podium
Agent cross-checkedpartial
Persistent living specs are available through the spec CLI and service. The Specs UI and spec-aware injected guidance are experimental edge features, off by default; this UI flag does not disable the direct CLI command.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Label experimental UI availability. Do not claim automatic drift detection, guaranteed compliance or automatic spec-based shipping veto.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Coordination and automation
COORD-01
Parallel work
Judgment rule. Record independently running sessions and tasks, documented quotas and observed concurrency. Describe how a user sees running, waiting, failed and finished work. Several chat tabs are not proof that runs execute concurrently.
Podium
Agent cross-checkedpartial
Documentation describes parallel sessions across worktrees and paired machines. Limits and achieved concurrency are unmeasured.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Public README documents these capabilities at the pinned revision; shipped release parity, concurrency limits and hands-on behavior remain unverified.
Concurrent tasks [supported] Worktree-based parallel feature work described. Sources: podium:readme.
Quotas [unknown] Quotas: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Observed concurrency [unknown] Observed concurrency: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Status visibility [unknown] Status visibility: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Judgment rule. Record assignment to humans or agents, claims, queues, routing and duplicate-work prevention. Test two workers attempting the same task. Distinguish a display label, an advisory lock and enforced exclusive ownership.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
COORD-03
Inspectable delegation and communication
Judgment rule. Record parent/child roles, model/harness/effort choice, messages, result return and cross-harness teams. Distinguish product orchestration, provider-native subagents, installed orchestration skills and scripts. Record activation, auth and experimental flags. Verify actual child identity, live progress, retained results and ability to reopen or follow up after completion. A final sentence claiming two reviewers ran is not proof. Test the documented invocation as well as the shared natural-language request.
Podium
Agent cross-checkedpartial
Cross-harness delegation and session mail are documented. This pass has not validated retained child results or follow-up across a complete delegated task.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Public README documents delegation and session/issue mail at the pinned revision; a complete delegated task, retained child results and shipped release parity remain unverified.
12 atomic answers
Roles [unknown] Roles: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Model harness effort [unknown] Model harness effort: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Messages [supported] Session and issue mail documented. Sources: podium:readme.
Results return [unknown] Results return: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Judgment rule. Record schedules, event triggers, recurring tasks and completion conditions. Name where the scheduler runs, overlap handling, retries and whether closing the client stops it. A desktop cron recipe is a manual integration unless the product owns it.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
COORD-05
Intervention and attention
Judgment rule. Record pause, stop, resume, steering, notifications, pending decisions and escalation. Test an in-run amendment and a harmless approval prompt in both chat and terminal modes. Record silent waits, hidden CLI-only questions and whether stop terminates execution while preserving history. Require discoverable errors rather than inferring success from silence.
Podium
Agent cross-checkedpartial
Podium lets a session switch between Chat and its native CLI surface. The terminal remains mounted across later switches; bidirectional draft synchronization is a separate experimental edge toggle.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Basic view switching is not the same as the separately gated draft-sync feature.
10 atomic answers
Pause [unknown] Pause: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Stop [unknown] Stop: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Resume [unknown] Resume: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Steer [unknown] Steer: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Notifications [unknown] Notifications: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Pending decisions [unknown] Pending decisions: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Escalation [unknown] Escalation: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Visible errors [unknown] Visible errors: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Chat terminal parity [partial] Chat/CLI buttons select views of the same session and keep the terminal mounted. This does not guarantee every harness prompt is interpreted equally in chat. Sources: podium:v4-agent-panel, podium:v4-flags.
Retained history [unknown] Retained history: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
COORD-06
Fleet and epic management UI
Judgment rule. Use a disclosed fixture of 12 task/agent states across several epics, including blocked, failed, awaiting input, reviewing and completed work. Locate parent/child relationships, dependencies, attention needs, history and workload without reading every transcript. Record navigation steps and errors. Boards, graphs, waterfalls, timelines or another interface can qualify; no required visual form. State whether the fixture was simulated or used live agents.
Podium
Agent cross-checkedpartial
Source includes a fleet waterfall with task/session relationships and attention states. The shared 12-task UX scenario has not been run.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
8 atomic answers
Fleet fixture [unknown] Fleet fixture: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Parent child [supported] Issue rows and attached session data are rendered. Sources: podium:fleet-ui.
Dependencies [unknown] Dependencies: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Attention [supported] Issue/session attention and blocked states render. Sources: podium:fleet-ui.
History [supported] Timeline activity data is rendered. Sources: podium:fleet-ui.
Workload [unknown] Workload: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Navigation errors [unknown] Navigation errors: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Fixture mode [unknown] Fixture mode: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
COORD-07
Workflow flexibility and orchestration visibility
Judgment rule. Compare a quick interactive change with a growing epic. Record mandatory workflow/preset selection, natural-language configuration, per-agent model/effort control, changes during execution and whether the UI exposes what actually ran. Test a coordinator with two reviewer children; capture roles, relationships and results during work and after completion. Document discoverability and auth friction without judging an unsupported magic prompt as proof of missing capability.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
Agent cross-checkedpartial
Saved workflows support agent and approval steps.
Scope
Surfaces: desktop, self-hosted, roadmap · Version: Official sources retrieved 2026-09-16 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-23
Other atomic questions remain unverified; no shared hands-on scenario was run.
10 atomic answers
Quick task [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Growing epic [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Presets [supported] Linear reusable steps. Sources: proliferate:flows.
Natural language [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Agent configuration [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
In run changes [supported] Pause, chat or redo steps. Sources: proliferate:flows.
Live roles [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Retained relationships [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Discoverability [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Auth friction [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Judgment rule. List local, user-owned VPS/remote host, self-hosted service, vendor cloud and hybrid modes. Record provisioning, payer, compute resources, region, idle/max lifetime and disconnection rules. Close/disconnect the originating client and continue from another device. A hosted UI or keep-awake setting is not evidence of remote execution. Record managed-cloud convenience separately from BYO setup effort in ACC-04.
Podium
Agent cross-checkedpartial
Local execution and self-hosted VPS execution are documented, with browser/desktop/phone access. Managed Podium cloud availability is not established.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: local, self-hosted · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Public README documents local and user-owned VPS routes; client disconnect and overnight runtime behavior were not tested. Managed cloud availability is unknown.
12 atomic answers
Local [supported] Local desktop execution documented. Sources: podium:readme.
Managed cloud [unknown] Managed cloud: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Hybrid [unknown] Hybrid: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Provisioning [supported] Installer plus browser configuration. Sources: podium:readme.
Payer [unknown] Payer: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Resources [unknown] Resources: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Region [unknown] Region: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Expiry [unknown] Expiry: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Client disconnect [supported] Documentation states terminal sessions survive closing a browser tab; not tested. Sources: podium:readme.
Other device continuation [unknown] Other device continuation: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Judgment rule. Record shared checkout, branch, worktree, container, VM and OS sandbox separately. Name filesystem, process, network and secret boundaries. Validate code separation with two changes; do not claim hostile-code containment without separate security evidence.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
Agent cross-checkedpartial
Delegated sessions share their parent checkout.
Scope
Surfaces: desktop, self-hosted, roadmap · Version: Official sources retrieved 2026-09-16 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-23
Do not assume child filesystem isolation.
12 atomic answers
Checkout [partial] Same workspace; use ordinary workspace for separate checkout. Sources: proliferate:children.
Branch [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Worktree [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Container [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Vm [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Os sandbox [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Filesystem [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Process [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Network [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Secrets [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Code separation [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Security boundary [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Judgment rule. Test client disconnect, worker crash, service restart and documented sandbox expiry safely. Separate transcript reload, process reconnection, task resumption and state reconstruction. Record lost context, duplicated actions, manual repair and ability to continue a multi-day epic after compute replacement. Short sandbox lifetimes are reported with their continuity behavior, not automatically treated as failure.
Podium
Agent cross-checkedpartial
Closing a browser tab does not stop the agent process on a running Podium host. Idle sessions may hibernate under configurable policies. The ordinary hibernateSession path refuses working or compacting agents; a separate age-backstop can park stale sessions without that guard.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
No fresh worker-crash/server-restart or multi-day soak executed. Host uptime and provider limits remain requirements. Avoid claiming unlimited runtime.
12 atomic answers
Client disconnect [supported] Persistent PTY continues when the browser tab closes; README describes reconnecting from other clients. Sources: podium:v4-readme.
Worker crash [unknown] Worker crash: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Service restart [unknown] Service restart: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Expiry [partial] Idle/resource policies and a separate age-backstop can park sessions. Ordinary hibernateSession protects working/compacting agents, but that guard does not apply to every park path. This is not a no-timeout guarantee. Sources: podium:v4-hibernation, podium:v4-session-teardown.
Transcript reload [unknown] Transcript reload: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Process reconnect [unknown] Process reconnect: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Task resume [partial] Hibernation retains session identity and resume reference where a cold resume is possible. Sources: podium:v4-session-teardown.
State reconstruction [unknown] State reconstruction: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Context loss [unknown] Context loss: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Duplicate actions [unknown] Duplicate actions: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Manual repair [unknown] Manual repair: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Multi day continuity [unknown] Multi day continuity: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
RUN-04
Development environment reliability
Judgment rule. Record dependency setup, node_modules/cache handling, snapshots, services, port allocation and secret injection. Start two workspaces with the same service requirements; note installation duplication, port collisions and repair steps. Repeat on a clean remote host. Record which problems the product handles automatically and which the user must diagnose.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
RUN-05
Limits and failure handling
Judgment rule. Record time, turn, token and spend limits; timeout, retry and provider-failure behavior. Test one controlled failure and a small safe budget. Record whether limits are warnings, enforced stops, or external billing controls.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
RUN-06
Truthful status and operational statistics
Judgment rule. Record logs, traces, failure reasons, usage exports and statistics by task, agent, project and time. Induce a worker failure and an approval wait: check agent, task and board state agree and remain correct after reconnect. Distinguish working, blocked, failed, idle, ready for review and delivered. For speed/success claims disclose fixture, model, hardware, attempts and failures. UI responsiveness needs observed interaction timings; never infer a framework from lag.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
RUN-07
Per-task API and compute cost
Judgment rule. Record visible model/API spend per task, session, child and epic, including aggregation across harness changes. Distinguish billed charges, estimates, tokens, subscription allowance and unavailable amounts; never render unknown subscription marginal cost as zero. Reconcile totals with provider evidence where available. Record compute fees separately, refresh delay, budget alerts, export and drill-down from summary statistics.
Podium
Agent cross-checkedpartial
Podium displays per-task token cost estimates with session detail. These use public model list prices and recorded tokens, not actual subscription invoices.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Do not call this money actually spent or claim infrastructure cost included.
14 atomic answers
Task cost [supported] Task cost records in source. Sources: podium:cost-model.
Session cost [unknown] Session cost: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Child cost [supported] Descendant split and rollups. Sources: podium:cost-model.
Epic cost [supported] Source includes recursive descendant traversal and own-versus-rollup token schemas; runtime accounting was not tested. Sources: podium:cost-model.
Harness aggregation [unknown] Harness aggregation: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Billed vs estimated [supported] Usage-derived pricing, not a provider billing receipt. Sources: podium:cost-model.
Tokens [supported] Input/output and cache token fields. Sources: podium:cost-model.
Subscription allowance [unsupported] Task dollar estimate does not apply subscription included capacity or plan pricing. Sources: podium:v4-cost-ui.
Provider reconciliation [unsupported] UI explicitly states estimates ignore subscriptions, negotiated pricing and free tiers; they are not provider bills. Sources: podium:v4-cost-ui.
Compute cost [unknown] Compute cost: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Refresh delay [unknown] Refresh delay: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Alerts [unknown] Alerts: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Export [unknown] Export: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Drilldown [supported] Task cost section includes the sessions that ran for the task, including completed sessions. Sources: podium:v4-cost-ui.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
RUN-08
Compute-aware scheduling and verification
Judgment rule. Record concurrency limits, queues, CPU/RAM limits, backpressure, per-host resource awareness and reuse/deduplication of checks. Queue multiple browser end-to-end tests under a declared safe capacity; verify excess work queues or throttles rather than overloading the host. Inspect cancellation, fairness, recovery and whether overlapping epics share limits. Do not run an uncontrolled load test.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Human collaboration and control
TEAM-01
Live human collaboration
Judgment rule. Record shared visibility, issue discussion, comments, presence and simultaneous co-prompting as independent capabilities. Use two named accounts to steer the same agent and record input ordering/conflict handling, attribution and permission controls. Read-only links and shared issues do not establish co-steering. Record team/free-tier restrictions and whether the original owner must stay online.
Podium
Agent cross-checkedpartial
The issue UI displays owner and visibility read-only and deliberately omits sharing controls. Backend share/unshare handlers exist; they do not establish a finished human collaboration workflow.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Scope is the reachable issue UI and backend handlers at the pinned revision. Do not infer shared-session collaboration or co-prompting from the presence of permission commands.
11 atomic answers
Visibility [partial] Owner and visibility metadata are displayed read-only. No issue-sharing control is offered in the issue UI. Sources: podium:v4-sharing-ui, podium:v4-sharing-test.
Discussion [unknown] Discussion: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Comments [unknown] Comments: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Presence [unknown] Presence: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Coprompting [unknown] Coprompting: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Ordering [unknown] Ordering: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Conflicts [unknown] Conflicts: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Attribution [unknown] Attribution: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Permissions [partial] Backend share/unshare commands write permission grants; these do not establish a released human collaboration workflow. Sources: podium:v4-issue-registry, podium:v4-sharing-ui.
Plan restrictions [unknown] Plan restrictions: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Owner online [unknown] Owner online: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
TEAM-02
Roles and access boundaries
Judgment rule. Record organization/project/task roles, membership lifecycle, SSO and provisioning where offered. Test unauthorized access and revocation with consenting test accounts. Describe documented versus observed enforcement, including which plan provides it.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
TEAM-03
Approvals and temporary access
Judgment rule. Record command, tool, network, secret and delivery approvals, approver identity and scope lifetime. Demonstrate allow, deny and revocation, including temporary tunnels or shared access after its thread/session ends. Separate default full access, available safer modes and product-enforced policy from instructions the model is expected to follow.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
TEAM-04
Decision and activity history
Judgment rule. Record attributed actions, approvals, edits, discussion and decision links. Check whether history persists across users and sessions, can be exported, and can be altered. Use the word audit only with a defined retention and integrity model.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
TEAM-05
Review experience and guidance
Judgment rule. Evaluate locating pending reviews, understanding a change, navigating evidence, commenting, requesting changes and finding the next shipping action. Measure steps/time and missed evidence on a shared fixture. Record keyboard/narrow-screen usability, context switching, clarity of agent roles and preservation of review context. Generic diff/PR access and a guided review workflow are different capabilities. Link high-volume review findings to SHIP-06.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
TEAM-06
Colleague takeover and continuity
Judgment rule. Have a second authorized person take over ongoing work with the same task, session history, decisions, artifacts, permissions and runtime context. Test after the first person disconnects. Record ownership transfer, attribution and lost context. Separately record transferring to another model/harness; a forked transcript or shared link alone is not full human takeover.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Verification and delivery
SHIP-01
Retained artifacts and outputs
Judgment rule. Record diffs, documents, screenshots, recordings, previews and test/reviewer outputs. Check for a searchable/browsable artifact gallery or equivalent retrieval, linked to task and exact revision, usable after sessions end. Reopen a completed child reviewer and retrieve its full findings. Check whether internal prompts or tool metadata unintentionally appear in the produced application or other user-facing output. In-chat attachments, persistent review evidence and a cross-task gallery get distinct answers.
Podium
Agent cross-checkedpartial
Artifact commands store and retrieve issue-linked files, including images, HTML and documents. Gallery usability and revision linking remain untested.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
13 atomic answers
Diffs [unknown] Diffs: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
SHIP-02
Verification and spec gates
Judgment rule. Record tests, lint, types, CI, independent review and persistent-spec conformance checks as required versus optional. Cause a failed test and a conflict with an existing product requirement. Verify review catches the conflict and delivery blocks where claimed. An agent saying checks passed is not a passing gate; record configured and enforced policy separately.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
SHIP-03
Git and pull request workflow
Judgment rule. Record branches/worktrees, commits, PR creation, review comments, CI response, rebase and conflict handling. Complete one fixture change through a draft PR. Distinguish an integrated workflow from the agent running Git commands without product state.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
SHIP-04
Merge and deployment authority
Judgment rule. Record who can approve, merge, release and deploy, plus checks against the exact revision. Verify the documented authority boundary without publishing real changes. PR creation, merge and production deployment are separate capabilities.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
SHIP-05
Completion evidence and rollback
Judgment rule. Record task-to-commit/PR/build/deployment links, delivery status, retained evidence and rollback or revert support. Change the candidate revision after review and examine whether approval/evidence is invalidated. Agent exit alone does not prove delivery.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
SHIP-06
Batch review and high-volume shipping
Judgment rule. Return to a queue of at least six completed fixture tasks and review a subset. Record summaries, grouping, risk/size filters, retained reviewer findings, artifact navigation, request-changes flow, approval of exact revisions, dependency-aware merge/release queues and clear next actions. Check stale approvals invalidate after edits and duplicate checks respect RUN-08. Distinguish basic diff/PR actions from a coordinated review-and-delivery queue; do not require Podium terminology.
Podium
Agent cross-checkedpartial
The shipping service records revision-specific approval, configured validation and delivery receipts. Shipping and Queues UI panels are experimental edge toggles, off by default.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public 89574f1c86a138a1242753397cb0635f385ed0f3; inspected current checkout 692d8c8e8f5465112dadeff50df0f0be817e9e51 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
source-only
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection of shipping controls does not establish batch-review usability. Queue locks and cached validation apply to shipping; they are not global resource controls for arbitrary agent tests. No claim is made here about automatic repair.
12 atomic answers
Review queue [unknown] Review queue: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Summaries [unknown] Summaries: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Grouping [unknown] Grouping: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Risk size filters [unknown] Risk size filters: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Findings [unknown] Findings: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Artifacts [unknown] Artifacts: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Request changes [unknown] Request changes: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Exact revision approval [supported] Shipping admission freezes exact approval facts and rejects stale facts before delivery. Sources: podium:v4-shipping-service.
Next actions [unknown] Next actions: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Stale approval invalidation [supported] Live revision/policy rechecks can hold stale shipping approvals. Sources: podium:v4-shipping-service.
Check deduplication [partial] Validation caching is scoped to queue prefix and matching validation configuration; not arbitrary tests run by agents. Sources: podium:v4-shipping-queue.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Ownership, privacy and economics
OWN-01
Source and license
Judgment rule. Record license and revision per component, including client, server and hosted extensions. Distinguish open source, source-available and closed components. Repository visibility is not a license classification or proof of hosted parity.
Podium
Agent cross-checkedpartial
Public repository is licensed Apache 2.0. Hosted extensions and release parity are not established.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-12-22
Root repository LICENSE establishes Apache 2.0 at the pinned revision; third-party notices and hosted-service terms are separate. Released and hosted parity remain unknown.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
OWN-02
Hosting and exit
Judgment rule. Record self-hosting scope, required vendor services, data export/import, standard formats and account cancellation behavior. Verify what remains usable without the vendor account. Exported code alone does not mean tasks, context and history are portable.
Podium
Agent cross-checkedpartial
Documentation supports running on a user-controlled VPS. Export/import completeness and vendor-independent identity have not been tested.
Scope
Surfaces: Browser client and self-hosted server, Podium CLI · Version: public main 89574f1c86a138a1242753397cb0635f385ed0f3 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Source inspection establishes implementation at the pinned revision; shipped release parity and hands-on behavior remain unverified.
8 atomic answers
Self hosting [supported] Self-hosted headless server documented. Sources: podium:readme.
Vendor dependencies [unknown] Vendor dependencies: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Export [unknown] Export: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Import [unknown] Import: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Formats [unknown] Formats: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Cancellation [unknown] Cancellation: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Account independence [unknown] Account independence: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
History portability [unknown] History portability: Not established by this public documentation and pinned-source pass. No hands-on scenario has been run.
Judgment rule. Record where code, prompts, credentials, logs and artifacts go, retention/deletion, training use, residency and subprocessors. Separately record telemetry disclosure, collection defaults, opt-in/opt-out controls and observed first-run prompts. No consent dialog is an observation, not proof of no telemetry, secret telemetry or unlawful processing. Separate orchestration-vendor and model-provider policies.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
Agent cross-checkedpartial
Self-host telemetry has opt-out controls.
Scope
Surfaces: desktop, self-hosted, roadmap · Version: Official sources retrieved 2026-09-16 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-23
Other atomic questions remain unverified; no shared hands-on scenario was run.
15 atomic answers
Code data [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Prompts [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Credentials [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Logs [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Artifacts [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Retention [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Deletion [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Training [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Residency [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Subprocessors [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Judgment rule. Record currency, billing interval, seats/seat minimums, workspace charges, included usage, credits, trial conditions, overages, taxes treatment and separate model/compute costs. Map billing routes to ACC-03. Cite public prices or dated quotes. Per-seat versus pooled billing is a fact, not a universal quality judgment.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
OWN-05
Scenario cost and controls
Judgment rule. Price stated workloads for one, two and five developers, with fixed tasks, concurrency, tokens and compute-hours. The two-person scenario models Till and Michael collaborating. Include subscription, platform, model and compute charges; separate fixed, variable, included and unknown costs. No invented average task cost. Link cost visibility and reconciliation to RUN-07.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
OWN-06
Availability and support
Judgment rule. Record GA/beta/access restrictions, support channels, documented response commitments, release activity, status history and deprecation/export options. Funding, stars and popularity can be context but are not reliability scores. An archived repository does not prove the hosted service is discontinued.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
OWN-07
Enterprise assurance
Judgment rule. Record each claimed assurance separately: ISO standard/certificate scope, issuer and validity; SOC 2 report type, covered service and audit period; report/certificate access and verification date. Distinguish public documentation, vendor assertion, independently accessible evidence and unavailable evidence. A logo, enterprise pricing tier, SSO or a provider certification does not prove this product is certified or audited. Report controls in TEAM-02 separately; no legal-compliance verdict.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
OWN-08
Useful free tier and evaluation access
Judgment rule. Distinguish an ongoing free tier, time-limited trial, credits-only trial, open-source self-hosting costs, paid-only access and gated early access. Map which shared scenarios work for free, especially two-person collaboration, BYO subscriptions, remote compute, mobile, issue management and review. Record card requirement, usage caps and whether meaningful evaluation needs payment or sales approval.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
Agent cross-checkedpartial
Team access is private beta; current official pages do not establish whether the Mac desktop app is free.
Scope
Surfaces: desktop · Version: Official sources retrieved 2026-09-16 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-09-23
Agent cross-check
2026-09-23
Check again by
2026-10-07
Other atomic questions remain unverified; no shared hands-on scenario was run.
Current homepage no longer states that the desktop app is free.
10 atomic answers
Ongoing free [unknown] Current official homepage and docs show a Mac download but no ongoing-free price statement.
Trial [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Credits trial [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Self host cost [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Paid only [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Early access [supported] Team private beta. Sources: proliferate:site.
Free scenarios [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Card required [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Usage caps [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Paid evaluation [unknown] Initial official-source pass did not establish this question; no hands-on scenario was run.
Judgment rule. Record publicly stated units, included limits, overage rates, compute/model pass-through or markup, minimum commitment, cancellation and sales-only unknowns. Use transparent, partially specified, quote-only or unknown, with named missing fields. A quote-only enterprise price is a disclosed procurement constraint, not proof of dishonesty.
Podium
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Proliferate
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Documentation lists macOS, preview Windows/Linux, browser and phone web access, separate planned native iPhone release, cross-harness delegation, agent issue tracking and a self-hosted VPS installer.
Inspected pinned public implementation: 175–203 managed accounts; 327–354 native subscription and API billing explanations. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
175–203 managed accounts; 327–354 native subscription and API billing explanations
Inspected pinned public implementation: 362–406 native and managed accounts; rotating several subscriptions Coming soon. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
362–406 native and managed accounts; rotating several subscriptions Coming soon
CLI commands call the issue service to create/edit/claim tasks, manage parent and dependency relationships, share access and retain artifacts. create accepts start as a separate optional flag.
Inspected pinned public implementation: 495–587 create, 835–847 sharing backend, ship handler, reparent. Availability is scoped in the linked criterion record.
Inspected pinned public implementation: 123–141 brief; 214 onward design/acceptance/notes and inline editing. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
123–141 brief; 214 onward design/acceptance/notes and inline editing
Inspected pinned public implementation: addDep / setParentForUpdate / reparent: durable links and cycle guards. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
addDep / setParentForUpdate / reparent: durable links and cycle guards
Inspected pinned public implementation: format, human decisions, superseded status, CLI command reference. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
format, human decisions, superseded status, CLI command reference
Inspected pinned public implementation: 53–62 inputs; service methods and repo-root validation; no feature flag gate. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
53–62 inputs; service methods and repo-root validation; no feature flag gate
Inspected pinned public implementation: help lists spec only when Specs is enabled at 1024–1026; command dispatch handles spec unconditionally at 2120–2125. Availability is scoped in the linked criterion record.
Inspected pinned public implementation: 1046–1070 Chat/CLI buttons; 1306–1340 same-session warm switch. Availability is scoped in the linked criterion record.
Inspected pinned public implementation: 15–30 and 81–170: idle pressure, configurable idle-session target. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
15–30 and 81–170: idle pressure, configurable idle-session target
Ordinary hibernation guards working and compacting agents; a separate age-backstop park path lacks that phase guard. This is not an unlimited active-session guarantee.
Product
podium
Kind
source-inspected
Locator
hibernateSession working/compacting guard; separate age-backstop park path; cold-resume references
Inspected pinned public implementation: Features and always-on VPS; desktop release/native iPhone planned. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
Features and always-on VPS; desktop release/native iPhone planned
Task cost model separates own and descendant usage, known costs from pending/missing data, and marks provisional/partial accounting. Supported transcript kinds include Claude Code, Codex and Grok. Pricing-derived usage is not a provider invoice.
Inspected pinned public implementation: 58–68: token list-price estimates, excludes subscription/negotiated/free pricing. Availability is scoped in the linked criterion record.
Inspected pinned public implementation: 19–32: sharing UX deliberately deferred; fields read-only. Availability is scoped in the linked criterion record.
Inspected pinned public implementation: CompatibilityShippingPolicyResolver: local ff-only, configured validation and resource lock. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
CompatibilityShippingPolicyResolver: local ff-only, configured validation and resource lock
Inspected pinned public implementation: admit/run: frozen approval, validation locks, stale-policy checks and durable receipts. Availability is scoped in the linked criterion record.
Product
podium
Kind
source-inspected
Locator
admit/run: frozen approval, validation locks, stale-policy checks and durable receipts
Inspected pinned public implementation: queue grouping, validation cache scope, dependency components. Availability is scoped in the linked criterion record.
