What Flows just did
Based on your request to build Add Real-Time Presence Indicators to a Chat App with WebSockets, Flows created 10 implementation stages and 50 checks.
You asked for: Implement real working presence indicators in the chat app using WebSockets, with backend-tracked online state, frontend subscription and rendering, typing indicators, disconnect handling, and testable real-time behavior across multiple clients.. Flows generated 10 stages because the application requires Use WebSockets for real-time presence updates instead of polling; Track whether a user is online based on active socket connections; Broadcast presence changes to relevant chat participants. 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 adds a green dot UI but never connects it to real WebSocket events; AI marks users offline on any disconnect without checking for other active connections; AI implements typing indicators that never clear or clear globally across all chats.
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
10 stages · 50 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: Identified the backend entry point for socket co…
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 10
Not startedInspect the existing chat architecture and choose presence data flow
Establish where WebSocket connections, user identity, and chat participants already exist so presence can be added without breaking the app.
Presence works best when the builder first maps the current auth, chat, and socket layers instead of generating a parallel system.
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 Real-Time Presence Indicators to a Chat App with WebSockets
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.
Inspect the current codebase and summarize the existing architecture for auth, chat conversations, messages, frontend state, and any real-time transport. Identify where the authenticated user ID becomes available, where chat participants are loaded, whether WebSockets or Socket.IO already exist, and where presence state should live on both backend and frontend. Produce a concrete implementation plan with files to edit, server events to add, client listeners to add, and how presence should be scoped to relevant conversations or participants.
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 clear integration plan that maps current auth, sockets, conversations, and UI components to the new presence system.
Should not happen
- ✕AI adds a green dot UI but never connects it to real WebSocket events
- ✕AI marks users offline on any disconnect without checking for other active connections
- ✕AI implements typing indicators that never clear or clear globally across all chats
- ✕AI only updates local client state and does not broadcast to other participants
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 adds a green dot UI but never connects it to real WebSocket events
- !AI marks users offline on any disconnect without checking for other active connections
- !AI implements typing indicators that never clear or clear globally across all chats
- !AI only updates local client state and does not broadcast to other participants
- !AI uses polling or fake timers instead of actual socket presence tracking
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
You gave a generic plan. Re-read the existing project structure and produce a project-specific presence integration map: socket server file, auth source, chat participant source, frontend chat header component, conversation state store, and exact new events and state fields to add.
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.