What Flows just did
Based on your request to build Add Usage‑Based Metered Billing, Flows created 6 implementation stages and 18 checks.
You asked for: Add a robust, usage‑based (metered) billing system that records real usage, calculates monthly invoices, integrates with Stripe's metered billing, and provides admin visibility.. Flows generated 6 stages because the application requires Persist usage events and invoices in PostgreSQL.; Support tiered rate plans.; Integrate with Stripe test mode using metered usage pricing.. 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: AI returns placeholder SQL or ORM definitions without executing migrations.; Usage middleware logs to console instead of inserting rows.; Billing service uses hard‑coded totals or skips DB transactions..
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
6 stages · 18 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: Can you query `SELECT column_name FROM informati…
Add a proof note on each check — a checkbox alone is weak proof.
Probes & advanced tools are under “More verification tools”. Experience level: Settings.
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 Submitting the form empty is rejected with a clear error
- api_probe Each required field can be omitted and fails validation
- api_probe Malformed email is rejected
- api_probe Malformed phone is rejected when phone is collected
- api_probe Duplicate submission does not create two records
- api_probe Double-click submit creates only one record
- false_success_probe Failed request does not show success
- browser_automation Refresh during submission does not leave corrupt state
- api_probe Oversized input is rejected
- api_probe Unsafe strings do not execute or break storage
- 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
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
Step 1 of 6
Not startedDefine billing and usage data model
Create persistent tables to store usage events, rates, and invoices.
The app uses a PostgreSQL database accessed via an ORM (e.g., Prisma or Sequelize). Existing user table is `users(id, ...)`.
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
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
- Add Usage‑Based Metered Billing
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
Use these instructions in Claude, ChatGPT, Cursor, Emergent, or another builder.
Write a database migration that adds three new tables: 1. `usage_events` with columns: `id PK`, `user_id FK -> users.id`, `event_type VARCHAR`, `quantity INT`, `recorded_at TIMESTAMP`. 2. `rate_plans` with columns: `id PK`, `name VARCHAR`, `unit_price_cents INT`, `tier_start INT`, `tier_end INT` (allow null for unlimited). 3. `invoices` with columns: `id PK`, `user_id FK`, `period_start DATE`, `period_end DATE`, `total_cents INT`, `status VARCHAR` (pending/paid), `created_at TIMESTAMP`. Make the migration idempotent, add foreign key constraints, and generate the corresponding ORM models. Finally, run the migration against a local dev DB and verify tables exist.
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
Three new tables exist in the local DB with correct columns, foreign keys, and ORM models are generated.
Should not happen
- ✕AI returns placeholder SQL or ORM definitions without executing migrations.
- ✕Usage middleware logs to console instead of inserting rows.
- ✕Billing service uses hard‑coded totals or skips DB transactions.
- ✕Stripe integration uses mock objects or omits webhook verification.
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…
- !AI returns placeholder SQL or ORM definitions without executing migrations.
- !Usage middleware logs to console instead of inserting rows.
- !Billing service uses hard‑coded totals or skips DB transactions.
- !Stripe integration uses mock objects or omits webhook verification.
- !Admin endpoints return static JSON instead of querying the DB.
- !E2E test relies on mocked Stripe SDK or fake DB fixtures.
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
The migration did not create real tables or used placeholders. Re‑run the migration with concrete SQL/ORM code that actually creates `usage_events`, `rate_plans`, and `invoices` with the specified columns and foreign keys, and verify by querying the DB.
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.