Skip to content
Flows

What Flows just did

Based on your request to build Hackathon Submission, Flows created 5 implementation stages and 15 checks.

You asked for: Produce a winning submission package: story, demo script, written submission, and a judge-experience test.. Flows generated 5 stages because the application requires A problem-solution narrative judges grasp in 30 seconds; A 2-3 minute demo plan that cannot die on stage; Submission copy tuned to the judging criteria. 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: Demoing features instead of the story; Live-demo death with no recorded backup; Ignoring stated judging criteria.

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: The story lands in 30 seconds read aloud

Add a proof note on each check — a checkbox alone is weak proof.

Probes & advanced tools are under “More verification tools”. Experience level: Settings.

Hackathon Submission
Launch2-3 hours

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

0/5 steps0%
Recording plan identity…

Step 1 of 5

Not started

Build the judge narrative

Judges score dozens of projects - clarity in 30 seconds wins.

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

Not checkedChecks not locked

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 Submission

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
Plan instructions

Use these instructions in Claude, ChatGPT, Cursor, Emergent, or another builder.

Build my hackathon narrative. I will paste the project description and the judging criteria below. Produce: the 30-second story (problem someone has, what we built, the impressive part, why it matters) in plain words; the one-sentence version for the submission title/tagline; explicit mapping of the project to EACH judging criterion (what we say and show per criterion); and the anticipated judge questions with honest answers (including 'what would you do next'). PROJECT AND CRITERIA: [paste here]

The AI tool writes code — Flows only organizes the plan · Complete implementation prompt with explicit requirements

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 30-second story, tagline, criterion-by-criterion mapping, and Q&A prep.

Should not happen

  • Demoing features instead of the story
  • Live-demo death with no recorded backup
  • Ignoring stated judging criteria
  • Judges finding broken buttons in 30 seconds of clicking

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…

  • !Demoing features instead of the story
  • !Live-demo death with no recorded backup
  • !Ignoring stated judging criteria
  • !Judges finding broken buttons in 30 seconds of clicking

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 narrative ignores the judging criteria. Rewrite the mapping so every criterion the rules mention has an explicit claim and a demo beat behind it.

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.

0/4 · manual