What Flows just did
Based on your request to build Build a Playable 2D Browser Game, Flows created 9 implementation stages and 46 checks.
You asked for: Create a real 2D game that can be played in the browser from start to finish, with working mechanics instead of a static mockup.. Flows generated 9 stages because the application requires Use a browser-friendly 2D rendering approach such as HTML5 Canvas or a lightweight game loop in the app; Implement a controllable player character or object with keyboard input; Render enemies, obstacles, collectibles, or targets as real interactive objects. 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: Building a nice-looking screen with no actual game loop or controls; Showing score and health labels that never update from real gameplay; Rendering objects visually but not wiring up collision behavior.
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
9 stages · 46 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: The game objective is stated in one sentence
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 9
Not startedDefine the game concept and core loop
Lock in a small game concept that is achievable and fully playable.
Keep the concept narrow. One player, one objective, one lose condition is enough.
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
- Build a Playable 2D Browser Game
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.
Create a concise implementation plan for a small 2D browser game that can be built quickly but is fully playable. Choose one simple concept such as dodge enemies, collect items, survive timer, or reach target. Specify: player controls, game objective, core loop, score system, lose condition, win condition, required game objects, and UI states for start, playing, and game over. Keep the plan scoped to a single screen and simple visual shapes.
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 specific and scoped game design with concrete mechanics and state transitions.
Should not happen
- ✕Building a nice-looking screen with no actual game loop or controls
- ✕Showing score and health labels that never update from real gameplay
- ✕Rendering objects visually but not wiring up collision behavior
- ✕Adding a restart button that only changes text instead of resetting state
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…
- !Building a nice-looking screen with no actual game loop or controls
- !Showing score and health labels that never update from real gameplay
- !Rendering objects visually but not wiring up collision behavior
- !Adding a restart button that only changes text instead of resetting state
- !Creating code with overlapping timers or loops that break after restart
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
Your concept is still too vague or too large. Reduce it to one playable loop on one screen. Define exact controls, objective, score logic, win condition, lose condition, and restart behavior. Do not add extra modes, levels, inventory, story, or multiplayer.
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.