A source-linked comparison across the complete Podium ADE rubric. 5 criteria have sourced findings for both products; 5 were also cross-checked by a second agent for both. 19 rows have at least one sourced finding, including 19 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
5 criteria
OpenAI Codex source checks
2026-09-23
Superset 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.
OpenAI Codex
Agent cross-checkedpartial
Codex documents terminal, IDE, desktop and cloud web surfaces.
Scope
Surfaces: Codex CLI, Codex IDE extension, Codex in ChatGPT desktop, Codex cloud · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
9 atomic answers
Desktop os [unknown] Desktop os: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Mobile apps [unknown] Mobile apps: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Mobile browser [unknown] Mobile browser: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Task actions [unknown] Task actions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Notifications [unknown] Notifications: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Cross device continuity [unknown] Cross device continuity: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
ACC-02
Agent and model choice
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Multiple coding agents supported.
Scope
Surfaces: Superset desktop · Version: Not specified · 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
Remaining atomic questions and observed behavior are unverified.
5 atomic answers
Harnesses [supported] Claude Code, Codex and OpenCode listed. Sources: superset:home.
Model providers [unknown] Model providers: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Custom adapters [unknown] Custom adapters: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Session integration [unknown] Session integration: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Mixed harness operation [unknown] Mixed harness operation: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
Agent cross-checkedpartial
Local clients accept subscriptions or API keys; cloud requires ChatGPT sign-in.
Scope
Surfaces: Codex CLI, Codex IDE extension, Codex in ChatGPT desktop, Codex cloud · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
Api accounts [supported] API-key local access. Sources: codex:auth.
Vendor credits [unknown] Vendor credits: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Local models [unknown] Local models: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Account switching [unknown] Account switching: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Vendor account requirement [unknown] Vendor account requirement: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Surfaces: Superset desktop · Version: Not specified · 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
Remaining atomic questions and observed behavior are unverified.
Api accounts [supported] Existing keys accepted. Sources: superset:home.
Vendor credits [unknown] Vendor credits: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Local models [unknown] Local models: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Account switching [unknown] Account switching: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Vendor account requirement [unknown] Vendor account requirement: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Provider restrictions [unknown] Provider restrictions: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
Agent cross-checkedpartial
CLI supports non-interactive automation.
Scope
Surfaces: Codex CLI · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
8 atomic answers
Cli [supported] codex exec for scripts and pipelines. Sources: codex:cli.
Api [unknown] Api: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Sdk [unknown] Sdk: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Mcp server [unknown] Mcp server: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Webhooks [unknown] Webhooks: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Operations [unknown] Operations: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Authentication [unknown] Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Stability [unknown] Stability: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
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.
OpenAI Codex
Agent cross-checkedpartial
CLI supports MCP and packaged extensions.
Scope
Surfaces: Codex CLI · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
Plugins [supported] Plugins and skills. Sources: codex:cli.
Custom tools [unknown] Custom tools: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Instructions import [unknown] Instructions import: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Authentication [unknown] Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Permission scope [unknown] Permission scope: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Integration owner [unknown] Integration owner: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Electron desktop implementation at pinned commit.
Scope
Surfaces: Pinned default-branch source · Version: fefc0b69e0e23d39115e029d14b7082a6ec11de7 · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Mobile implementation [unknown] Mobile implementation: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Hybrids [unknown] Hybrids: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Native tasks support editable metadata and explicit dispatch.
Scope
Surfaces: Superset desktop · Version: Not specified · 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
No full idea-to-epic test; dependencies, archive and advanced lifecycle need checking.
Discuss [unknown] Discuss: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Label [unknown] Label: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Archive [unknown] Archive: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Reopen [unknown] Reopen: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Idea parking [unknown] Idea parking: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Task session separation [unknown] Task session separation: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Metadata [unknown] Metadata: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Durable states [unknown] Durable states: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
External tracker requirement [unknown] External tracker requirement: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
Agent cross-checkedpartial
Cloud supports parallel tasks in separate environments.
Scope
Surfaces: Codex cloud · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
5 atomic answers
Concurrent sessions [unknown] Concurrent sessions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Quotas [unknown] Quotas: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Observed concurrency [unknown] Observed concurrency: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Status visibility [unknown] Status visibility: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Surfaces: Superset desktop · Version: Not specified · 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
Remaining atomic questions and observed behavior are unverified.
5 atomic answers
Concurrent sessions [unknown] Concurrent sessions: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Concurrent tasks [supported] Separate worktrees per task. Sources: superset:docs.
Quotas [unknown] Quotas: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Observed concurrency [unknown] Observed concurrency: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Status visibility [unknown] Status visibility: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
Agent cross-checkedpartial
CLI can delegate focused work to subagents.
Scope
Surfaces: Codex CLI · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
12 atomic answers
Roles [unknown] Roles: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Model harness effort [unknown] Model harness effort: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Messages [unknown] Messages: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Results return [supported] Findings return to main session. Sources: codex:cli.
Cross harness [unknown] Cross harness: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Activation [unknown] Activation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Authentication [unknown] Authentication: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Live progress [unknown] Live progress: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Retained results [unknown] Retained results: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Followup [unknown] Followup: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Invocation [unknown] Invocation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Surfaces: Superset desktop, User-provided remote host via relay · Version: Not specified · 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
Natural-language invocation and retained relationship UI untested.
12 atomic answers
Roles [unknown] Roles: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Model harness effort [unknown] Model harness effort: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Cross harness [unknown] Cross harness: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Authentication [unknown] Authentication: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Live progress [unknown] Live progress: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Retained results [unknown] Retained results: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Followup [unknown] Followup: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Invocation [unknown] Invocation: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Execution and reliability
RUN-01
Laptop-independent execution
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.
OpenAI Codex
Agent cross-checkedpartial
Local CLI and managed cloud execution are separate modes.
Scope
Surfaces: Codex CLI, Codex cloud · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
12 atomic answers
Local [supported] CLI uses host repository/tools. Sources: codex:cli, codex:cloud.
Byo remote [unknown] Byo remote: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Self hosted [unknown] Self hosted: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Hybrid [unknown] Hybrid: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Provisioning [unknown] Provisioning: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Payer [unknown] Payer: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Resources [unknown] Resources: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Region [unknown] Region: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Expiry [unknown] Expiry: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Client disconnect [unknown] Client disconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Other device continuation [unknown] Other device continuation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
User-provisioned remote hosts are documented. Managed cloud sandboxes are only listed as an exploratory roadmap item.
Scope
Surfaces: User-provided remote host via relay · Version: Not specified · 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
Not a verified managed-compute service.
12 atomic answers
Local [unknown] Local: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Self hosted [unknown] Self hosted: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Managed cloud [unknown] The public roadmap lists cloud sandboxes under Exploring; current availability is not established.
Hybrid [unknown] Hybrid: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Payer [unknown] Payer: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Resources [unknown] Resources: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Region [unknown] Region: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Expiry [unknown] Expiry: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Client disconnect [unknown] Client disconnect: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Other device continuation [unknown] Other device continuation: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Git worktrees provide code separation.
Scope
Surfaces: Superset desktop · Version: Not specified · 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
Worktree isolation is not a security boundary.
12 atomic answers
Checkout [unknown] Checkout: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Branch [unknown] Branch: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Container [unknown] Container: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Vm [unknown] Vm: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Os sandbox [unknown] Os sandbox: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Filesystem [unknown] Filesystem: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Process [unknown] Process: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Network [unknown] Network: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Secrets [unknown] Secrets: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Code separation [supported] Separate branches. Sources: superset:docs.
Security boundary [unknown] Security boundary: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
Agent cross-checkedpartial
CLI documents saved chat resumption.
Scope
Surfaces: Codex CLI · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
12 atomic answers
Client disconnect [unknown] Client disconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Worker crash [unknown] Worker crash: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Service restart [unknown] Service restart: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Expiry [unknown] Expiry: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Process reconnect [unknown] Process reconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Task resume [unknown] Task resume: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
State reconstruction [unknown] State reconstruction: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Context loss [unknown] Context loss: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Duplicate actions [unknown] Duplicate actions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Manual repair [unknown] Manual repair: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Multi day continuity [unknown] Multi day continuity: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was 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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Remote hosts have explicit member grants.
Scope
Surfaces: User-provided remote host via relay · Version: Not specified · 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
No unauthorized-access test.
9 atomic answers
Organization roles [unknown] Organization roles: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Project roles [unknown] Project roles: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Task roles [unknown] Task roles: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Membership [supported] Owner adds organization members to host. Sources: superset:remote.
Sso [unknown] Sso: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Provisioning [unknown] Provisioning: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Unauthorized access [unknown] Unauthorized access: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Revocation [supported] Owner can remove members. Sources: superset:remote.
Plan scope [unknown] Plan scope: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Teammates can access authorized remote workspaces.
Scope
Surfaces: User-provided remote host via relay · Version: Not specified · 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
Co-prompting, full takeover and ordering unverified.
12 atomic answers
Ongoing takeover [unknown] Ongoing takeover: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Same task [unknown] Same task: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Session history [unknown] Session history: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Decisions [unknown] Decisions: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Artifacts [unknown] Artifacts: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Permissions [unknown] Permissions: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Runtime context [partial] Terminals, runs and diff via relay. Sources: superset:remote.
Owner disconnect [unknown] Owner disconnect: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Ownership [unknown] Ownership: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Attribution [unknown] Attribution: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Context loss [unknown] Context loss: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Harness transfer [unknown] Harness transfer: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
Agent cross-checkedpartial
Cloud review can lead to a pull request.
Scope
Surfaces: Codex cloud · Version: Public documentation checked 2026-09-23 · 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
This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run.
9 atomic answers
Branches [unknown] Branches: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Worktrees [unknown] Worktrees: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Commits [unknown] Commits: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Pull requests [supported] Review result and open PR. Sources: codex:cloud.
Ci response [unknown] Ci response: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Rebase [unknown] Rebase: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Conflicts [unknown] Conflicts: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Product state [unknown] Product state: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run.
Built-in diff workflow stages, commits, pushes and creates PRs.
Scope
Surfaces: Superset desktop · Version: Not specified · 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
Remaining atomic questions and observed behavior are unverified.
9 atomic answers
Branches [unknown] Branches: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Worktrees [unknown] Worktrees: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Commits [supported] Stage and commit. Sources: superset:docs.
Pull requests [supported] Open PR. Sources: superset:docs.
Comments [unknown] Comments: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Ci response [unknown] Ci response: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Rebase [unknown] Rebase: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Conflicts [unknown] Conflicts: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Product state [unknown] Product state: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Repository uses ELv2.
Scope
Surfaces: Pinned default-branch source · Version: Not specified · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Server license [unknown] Server license: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Hosted extensions [unknown] Hosted extensions: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Source visibility [supported] Public repository. Sources: superset:license.
Hosted parity [unknown] Hosted parity: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
OWN-03
Data handling and telemetry
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
OWN-04
Price and included usage
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Pro $20/user/month or $180/user/year.
Scope
Surfaces: Superset desktop, User-provided remote host via relay · Version: Not specified · 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
Agent and host costs separate; taxes/cancellation unverified.
Seat minimum [unknown] Seat minimum: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Workspace fees [unknown] Workspace fees: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Included usage [unknown] Included usage: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Credits [unknown] Credits: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Trial [unknown] Trial: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Overages [unknown] Overages: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Taxes [unknown] Taxes: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Model cost [unknown] Model cost: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Compute cost [unknown] Compute cost: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Enterprise lists SOC 2 Type II report.
Scope
Surfaces: User-provided remote host via relay · Version: Not specified · 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
Report scope, auditor and period unknown.
9 atomic answers
Iso scope [unknown] Iso scope: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Iso issuer [unknown] Iso issuer: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Iso validity [unknown] Iso validity: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Soc2 type [supported] Vendor-listed Type II. Sources: superset:pricing.
Soc2 scope [unknown] Soc2 scope: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Soc2 period [unknown] Soc2 period: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Report access [unknown] Report access: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Verification date [unknown] Verification date: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Evidence status [partial] Report not inspected. Sources: superset:pricing.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
Agent cross-checkedpartial
Ongoing free tier supports one local user.
Scope
Surfaces: Superset desktop · Version: Not specified · 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
Remote/team scenario needs paid tier.
10 atomic answers
Ongoing free [supported] Local desktop/CLI and GitHub. Sources: superset:pricing.
Trial [unknown] Trial: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Credits trial [unknown] Credits trial: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Self host cost [unknown] Self host cost: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Paid only [unknown] Paid only: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Early access [unknown] Early access: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Free scenarios [unknown] Free scenarios: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Card required [supported] No card required. Sources: superset:pricing.
Usage caps [unknown] Usage caps: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
Paid evaluation [unknown] Paid evaluation: Initial official-source pass did not resolve this question. No installed-client or authenticated scenario was run; source-only findings do not establish release parity.
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.
OpenAI Codex
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Superset
No sourced public findingnot-published
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Existing agent subscriptions and keys are advertised. The homepage now advertises mobile access; it does not establish managed cloud sandbox availability.
Product
superset
Kind
vendor-claimed
Locator
Agent Independence; Source Available; Your Agents, Your Accounts
Native create operation writes organization-scoped task title, description, status, priority and assignee. Docs link this operation to desktop New task.
Cloud sandboxes are listed as Exploring, not as available. The roadmap also places ticket launch and an SDK/public API in Exploring, while current documentation describes Tasks and a TypeScript SDK; reconcile the scopes before citing those claims.
Product
superset
Kind
vendor-claimed
Locator
Exploring: Cloud sandboxes; SDK & public API; Work from tickets
Free plan covers one local user; Pro lists $20 monthly or $15/user/month on annual billing. Mobile is listed in Pro, and Enterprise lists report access.
