Skip to content
Flows

What Flows just did

Based on your request to build Add Persistent Full‑Text Search to Existing App, Flows created 5 implementation stages and 26 checks.

You asked for: Add a persistent full‑text search feature that indexes selected tables, exposes a secure API, and provides a responsive UI component.. Flows generated 5 stages because the application requires Search must be real, not mock data.; Indexes must persist in PostgreSQL and stay in sync with data changes.; API endpoint must be protected against injection and return ranked results.. 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 only UI mockups or placeholder components.; Migration missing trigger or backfill logic.; Backend endpoint uses string interpolation instead of parameterized queries..

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

5 stages · 26 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: JSON lists all tables that need search

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

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

Add Persistent Full‑Text Search to Existing App
App Builder1-2 hoursGenerated Draft

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

0/5 steps0%
Recording plan identity…

Step 1 of 5

Not started

Determine searchable entities and choose engine

Identify which tables/fields need full‑text search and select a compatible indexing solution.

💡

The app uses PostgreSQL. Prefer built‑in tsvector or a lightweight external like SQLite FTS5 if the stack allows. No external SaaS.

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
  • Add Persistent Full‑Text Search to Existing App

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.

1. Examine the existing PostgreSQL schema (list of tables and column types). 2. Identify which tables and specific text columns should be searchable (e.g., articles.title, articles.body, users.bio). 3. Choose between PostgreSQL native full‑text search (using tsvector columns and GIN indexes) or a lightweight embedded engine like SQLite FTS5 if the project already uses SQLite for some components. 4. Justify the choice in one sentence referencing performance, ease of migration, and existing stack. 5. Output the final decision in JSON: {"engine":"postgres","tables":[{"name":"articles","columns":["title","body"]},{"name":"users","columns":["bio"]}]}

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 JSON block specifying engine = "postgres" and a list of tables with columns to index.

Should not happen

  • AI returns only UI mockups or placeholder components.
  • Migration missing trigger or backfill logic.
  • Backend endpoint uses string interpolation instead of parameterized queries.
  • Frontend omits debounce or uses hard‑coded sample data.

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 only UI mockups or placeholder components.
  • !Migration missing trigger or backfill logic.
  • !Backend endpoint uses string interpolation instead of parameterized queries.
  • !Frontend omits debounce or uses hard‑coded sample data.
  • !Self‑audit sections are omitted or contain fabricated PASS.

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 AI omitted the required JSON or did not include the justification. Reply with: "Provide the complete JSON decision object for the search engine, including all tables and columns, a one‑sentence justification, and a PASS/FAIL self‑audit as specified."

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.

0/5 · manual