What Flows just did
Based on your request to build Build a Scary First-Person Horror Game, Flows created 10 implementation stages and 50 checks.
You asked for: Build a genuinely functional scary first-person game prototype that can be played from start to finish, with working controls, interactions, game logic, enemy behavior, audio/visual horror cues, win state, and lose state.. Flows generated 10 stages because the application requires Implement first-person movement with mouse look and collision; Create at least one explorable indoor horror environment with lighting and navigable layout; Add interactive objects such as doors, keys, notes, switches, or pickups. 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 builds a level that looks scary but has no real gameplay loop; Interactions appear in UI but objects do not actually change state; Enemy is decorative, scripted once, or does not truly chase the player.
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: The plan includes a start, midgame escalation, a…
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 Logged-out users cannot open protected pages
- api_probe Protected API rejects requests without credentials
- api_probe Expired session cannot mutate data
- browser_automation Logout in one tab invalidates mutations from another
- cross_account_probe User B cannot see or change User A’s data
- cross_account_probe Participant cannot call coach/admin endpoints
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 startedDefine the game loop and systems before building
Force the builder to design a complete horror gameplay loop with concrete systems, not just a spooky scene.
Keep the scope to one short but complete level with a beginning, escalation, and ending.
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 Scary First-Person Horror 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.
Plan a playable first-person horror prototype with one short level. Specify: player movement, camera, interaction system, inventory or key items, door/lock logic, objective chain, threat or enemy behavior, audio scare triggers, lighting/event triggers, UI prompts, death/capture state, and end condition. Return a build plan with concrete systems, scene objects, scripts/components needed, and the order to implement them so the game is playable end to end.
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 concrete game specification describing the level flow, mechanics, and required systems.
Should not happen
- ✕AI builds a level that looks scary but has no real gameplay loop
- ✕Interactions appear in UI but objects do not actually change state
- ✕Enemy is decorative, scripted once, or does not truly chase the player
- ✕Objectives are described in text but are not connected to progression logic
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 builds a level that looks scary but has no real gameplay loop
- !Interactions appear in UI but objects do not actually change state
- !Enemy is decorative, scripted once, or does not truly chase the player
- !Objectives are described in text but are not connected to progression logic
- !Doors, keys, and triggers exist visually but are not wired together
- !Game has no real win state, lose state, or restart flow
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 plan is too vague and cinematic. Rewrite it as a build specification with exact systems, object interactions, state changes, and a full playable loop from spawn to victory or death.
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.