What Flows just did
Based on your request to build Hackathon Judge Report, Flows created 5 implementation stages and 15 checks.
You asked for: Produce a rigorous judge report: criteria-based scores with evidence, functionality verification, and actionable feedback.. Flows generated 5 stages because the application requires Scoring against the stated criteria with weights; Hands-on functionality verification, not demo-trust; Evidence noted per score. 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: Scoring from the demo video alone; Halo effects from polished pitches masking dead apps; Vague feedback ('great job, needs polish').
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 · 15 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: Each criterion has anchored scale points
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 Logged-out users cannot open protected pages
- api_probe Protected API rejects requests without credentials
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 5
Not startedSet up the rubric
Fix the criteria and standards before seeing any project.
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
- Hackathon Judge Report
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.
Set up my judging rubric. I will paste the competition's criteria below. Produce: each criterion with its weight and a 1-10 scale anchored with concrete descriptions (what a 3, 6, and 9 look like - observable behaviors, not adjectives); the functionality-verification checklist applied to every project (core action works, data persists, no dead buttons on the main path); and the report template (scores, evidence, strengths, issues, potential). Lock it before judging starts. CRITERIA: [paste here]
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
An anchored, weighted rubric plus a universal verification checklist and template.
Should not happen
- ✕Scoring from the demo video alone
- ✕Halo effects from polished pitches masking dead apps
- ✕Vague feedback ('great job, needs polish')
- ✕Inconsistent standards between the first and last project judged
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…
- !Scoring from the demo video alone
- !Halo effects from polished pitches masking dead apps
- !Vague feedback ('great job, needs polish')
- !Inconsistent standards between the first and last project judged
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 scale points are adjectives ('good', 'excellent'). Rewrite anchors as observable behaviors so two judges would score alike.
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.