What Flows just did
Based on your request to build Design a Memory Index Loaded Every Session, Flows created 3 implementation stages and 9 checks.
You asked for: Split memory into an always-loaded index and on-demand detail files, with the agent trained to follow index pointers.. Flows generated 3 stages because the application requires A compact index file (hard token cap) always loaded at session start; Detail files per topic, referenced from the index with one-line descriptions; A memory_read tool for loading detail files on demand. 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: An 'index' that grew into the very memory dump it was meant to replace; Detail files the agent never loads because index descriptions are too vague; Orphaned detail files invisible to the index.
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
3 stages · 9 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: Index within its token cap
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 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
- cross_account_probe URL/body ID tampering cannot cross tenant boundary
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 3
Not startedStructure the index and details
The index is a map; the details are the territory.
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
- Design a Memory Index Loaded Every Session
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.
Design the two-layer memory structure. INDEX (memory/INDEX.md, hard cap ~400 tokens): a header stating its role, then one line per topic: `- topic-name: one-line description of what the detail file contains and when to load it -> memory/topics/topic-name.md`. DETAIL FILES (memory/topics/*.md): focused documents per topic (auth-system.md, deployment.md, user-preferences.md...), each starting with a 2-line abstract matching its index description. Migrate my existing memory content into this structure now, writing index descriptions that state WHEN to load ('load when working on login, sessions, or permissions'). Deliver the populated index and at least three real detail files.
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 populated index within cap plus topic detail files.
Should not happen
- ✕An 'index' that grew into the very memory dump it was meant to replace
- ✕Detail files the agent never loads because index descriptions are too vague
- ✕Orphaned detail files invisible to the index
- ✕Loading every detail file every time, defeating the entire design
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…
- !An 'index' that grew into the very memory dump it was meant to replace
- !Detail files the agent never loads because index descriptions are too vague
- !Orphaned detail files invisible to the index
- !Loading every detail file every time, defeating the entire design
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
Descriptions are labels, not signals ('auth stuff'). Rewrite each as a load-trigger: the task keywords and situations that should prompt opening the file.
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.