Skip to content
Flows

What Flows just did

Based on your request to build Release Gates for Agent-Generated Code, Flows created 4 implementation stages and 12 checks.

You asked for: Define and enforce a release gate for agent-generated changes: automated review + tests + security scans, plus human sign-off scaled to change risk.. Flows generated 4 stages because the application requires A merge gate that agent-generated changes must pass before landing; Automated layers: rule-file review, full tests, security/dependency scans, secret scan; Risk classification of changes to set the required human-review depth. Each stage tells your AI builder what to do, tests whether it actually worked, and gives a repair instruction when it fails. These checks are designed to catch: Auto-merging agent PRs on green CI with no human ever looking at risky ones; Applying weaker checks to agent code than to human code; No risk tiering, so a typo fix and a payment change get identical review.

Example failure

The form reported success, but no database record was created.

What Flows does

Flows detects the failure, generates a repair instruction, reruns the test, and stores the passing evidence.

Stages — Plan → Build → Test → Fix → Prove → Ship

4 stages · 12 checks · progressive disclosure — open a stage for details

Copy to external builder

Copies a prompt for Claude/Cursor/etc. Records prompt_copied only — not execution, commits, or checks.

Execute through Oort

Requires Sign in with Oort + a provider connection (BYOK). Keys stay on Oort. A model name in the dropdown is not the same as a live connection.

Next

Check off: Rules, tests, security, deps, and secrets all ga…

Add a proof note on each check — a checkbox alone is weak proof.

Probes & advanced tools are under “More verification tools”. Experience level: Settings.

Release Gates for Agent-Generated Code
Agent QA & Security60-90 minutes

Project (saved with proof)

Project binding: Unbound — complete project binding before trusting this run · missing repositoryUrl, repositoryStartCommit, environment, stack

More verification tools (probes, timeline, adapters)Show

App persistence (create → read → assert token)

Body template: {"probe":"{{token}}","title":"flows-probe-{{token}}"}. Needs CORS-readable public create/list endpoints (or inconclusive). Badge only when create→read→refresh finds the token (detects false success).

Two-account authorization (User B cannot see/change User A)

Authorization evidence source: Cross-account ownership test (trust level 5/6). These are not equivalent. Unauthenticated probe alone is weaker (source: unauthenticated API probe). Tokens stay in this browser session only — not uploaded to Flows servers.

Generated edge-case tests (review / approve)

  • api_probe Logged-out users cannot open protected pages
  • api_probe Protected API rejects requests without credentials
  • api_probe Expired session cannot mutate data
  • browser_automation Logout in one tab invalidates mutations from another
  • cross_account_probe User B cannot see or change User A’s data
  • cross_account_probe Participant cannot call coach/admin endpoints
  • cross_account_probe URL/body ID tampering cannot cross tenant boundary
  • api_probe Create then refresh still shows the record
  • api_probe Edit then refresh keeps the edit
  • api_probe Delete then refresh removes the record
  • api_probe Nonexistent record ID fails cleanly
  • cross_account_probe Cross-user record identifier is rejected

Generated from this route’s signals — you approve; you do not invent security tests.

Content probe (GET body contains text)

In-product content probe reads response text when CORS allows — not full DOM/click automation. Playwright script is optional and external.

Proof strength

thin · 0/100

Heuristic from notes + probes + gates — not a production certification.

Verification adapters

  • Deploy URL probe · idle
  • API path probe · idle
  • Authz probe (unauth → 401/403) · idle
  • Browser persistence · idle
  • App persistence (create→read) · idle
  • Content / body text probe · idle
  • In-product Playwright DOM · not embedded (download external script)

Filled circles = available here. Empty = not shipped. Probes are not a production audit. Adapter docs

0/4 steps0%
Recording plan identity…

Step 1 of 4

Not started

Assemble the automated gate

Stack the deterministic and test-based checks first.

Flows keeps plan, checks, failures, and next steps connected

Your AI tool writes or changes the code

Repository grounds the plan only after inspect

Checks always carry a validation tier

Not checkedChecks not locked

How this plan was created

Plan from project details

Flows creates steps using the goal, requirements, stack, platform, and details you provide.

  • Project description
  • Selected template / route
  • User-entered stack
  • Constraints and notes
  • Release Gates for Agent-Generated Code

No repository inspection implied. Connect and inspect a codebase to ground steps in real files.

Codebase access

Checking GitHub…

Or paste a repository URL manually
Plan instructions

Use these instructions in Claude, ChatGPT, Cursor, Emergent, or another builder.

Build the automated portion of the gate for agent-generated changes. Compose the layers already available (or build the missing ones): the rule-file review gate (deterministic policy checks on the diff), the full test suite plus the verification evidence the agent produced, security scans (the injection/red-team suite where the change touches agent behavior; SAST where applicable), dependency/supply-chain checks for any new deps, and a secret scan on the diff. Wire these as required status checks on the change (PR or equivalent). Any failure blocks. Ensure these run on agent changes at parity with or above human-change checks. Test by pushing an agent change with a planted rule violation and a failing test and confirming both block the merge.

The AI tool writes code — Flows only organizes the plan · Complete implementation prompt with explicit requirements

Project context

Copies the project goal, technical details, current step, previous progress, and checks so your AI tool understands what it is working on.

Expected after this step

A stacked automated gate blocking on any failed check.

Should not happen

  • Auto-merging agent PRs on green CI with no human ever looking at risky ones
  • Applying weaker checks to agent code than to human code
  • No risk tiering, so a typo fix and a payment change get identical review
  • Unlabeled agent changes, so reviewers do not know to look harder

Verify gate — prove this step works before continuing

Do not move on until every check is true. Add proof notes — a checked box alone is weak proof. Checks are manual by default; deploy/API probes live under “More verification tools” and do not auto-check boxes.

Do not continue if…

  • !Auto-merging agent PRs on green CI with no human ever looking at risky ones
  • !Applying weaker checks to agent code than to human code
  • !No risk tiering, so a typo fix and a payment change get identical review
  • !Unlabeled agent changes, so reviewers do not know to look harder

Repair path — if this step fails

Use the Repair Prompt when a verify gate fails. Loop: Detected → Diagnosed → Repair issued → Changed → Retested → Resolved

Show repair prompt textShow

An agent change merged on partial checks. Make every layer a required status check (not advisory) and confirm the merge is technically blocked until all are green - advisory checks get ignored under deadline.

Your notes for this step

Definition of Done

Final route-level requirements. Manual checks — separate from per-step verify gates. Completing step gates does not auto-check these. Route completion is not a production-ready claim.

0/4 · manual