What Flows just did
Based on your request to build Add Activity Feed Feature, Flows created 6 implementation stages and 18 checks.
You asked for: Provide a live activity feed that records key user actions, stores them in the database, serves them via an API, and displays them in the UI.. Flows generated 6 stages because the application requires Activity data must be persisted in PostgreSQL.; API must be authenticated and support pagination.; Frontend component must fetch real data and display timestamps.. 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 a model definition but omits the foreign key or migration steps.; API code contains placeholder comments instead of real Express routes.; Activity creation is only logged to console, not persisted..
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: Does prisma/schema.prisma contain a model named …
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
- 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
Step 1 of 6
Not startedDefine Activity data model
Create a durable schema for storing activity events
App uses Node.js/Express backend with Prisma ORM and PostgreSQL. Existing Prisma schema already has a User model.
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 Activity Feed Feature
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.
In the project's prisma/schema.prisma file, add a new model named Activity with the following exact fields and attributes: 1. id Int @id @default(autoincrement()) 2. userId Int // foreign key to User.id 3. type String // short descriptor of the action (e.g., "post_created") 4. payload Json // any additional data needed for the UI 5. createdAt DateTime @default(now()) After defining the model, add a relation to the existing User model: `user User @relation(fields: [userId], references: [id], onDelete: Cascade)`. Run `npx prisma migrate dev --name add-activity-model` to generate and apply the migration. Finally, run `npx prisma generate` to refresh the client. Verify the migration SQL creates a table named "Activity" with the specified columns and foreign key.
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
prisma/schema.prisma contains a complete Activity model, a migration file exists, `prisma migrate dev` runs without error, and the PostgreSQL database has an Activity table.
Should not happen
- ✕AI returns a model definition but omits the foreign key or migration steps.
- ✕API code contains placeholder comments instead of real Express routes.
- ✕Activity creation is only logged to console, not persisted.
- ✕React component uses static mock data rather than calling the real endpoint.
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 a model definition but omits the foreign key or migration steps.
- !API code contains placeholder comments instead of real Express routes.
- !Activity creation is only logged to console, not persisted.
- !React component uses static mock data rather than calling the real endpoint.
- !Integration tests mock the database instead of exercising the real API.
- !Self‑audit sections are missing or contain generic statements.
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 Activity model was not added or the migration failed. Re‑create the Activity model exactly as specified, ensure the foreign key to User is present, run `prisma migrate dev` with a proper name, and verify the table exists in PostgreSQL.
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.