What Flows just did
Based on your request to build Build an AI Affiliate Marketing Agent That Finds, Publishes, and Tracks Revenue Opportunities, Flows created 11 implementation stages and 53 checks.
You asked for: Launch a real working affiliate marketing agent with operational workflows for offer intake, content generation, link tracking, performance reporting, and optimization based on measurable revenue signals.. Flows generated 11 stages because the application requires Create a database schema for affiliate programs, offers, campaigns, content assets, clicks, conversions, and earnings; Provide a way to add affiliate programs manually including payout terms, landing URLs, tracking links, and disclosure requirements; Build an AI workflow that turns offer details into content briefs and multiple content variations for at least 3 channels. 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 pretty dashboard with hardcoded sample metrics instead of computing from stored click and revenue data; AI generates content but does not attach it to campaigns, offers, or persistent records; AI adds affiliate links directly without implementing tracked redirect or click logging.
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
11 stages · 53 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: There are persistent models/tables for offers, c…
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 11
Not startedDefine the affiliate agent scope and data model
Set the exact product scope, entities, relationships, and success metrics before building screens or AI features.
Keep version 1 narrow: one operator, manual affiliate offer entry, tracked clicks, recorded earnings, and AI content generation.
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 an AI Affiliate Marketing Agent That Finds, Publishes, and Tracks Revenue Opportunities
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 the initial architecture for an AI affiliate marketing agent application. Include a concrete data model for affiliate programs, offers, campaigns, content assets, tracked links, click events, conversions, earnings entries, and compliance rules. Also define the main user flows: add an offer, create a campaign, generate content, use tracked links, record conversions or earnings, and view reporting. Generate the actual schema and wire it into the app foundation so later steps can build on real persisted data.
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 working project scaffold with persistent data structures and clear app sections for offers, campaigns, content, link tracking, and analytics.
Should not happen
- ✕AI builds a pretty dashboard with hardcoded sample metrics instead of computing from stored click and revenue data
- ✕AI generates content but does not attach it to campaigns, offers, or persistent records
- ✕AI adds affiliate links directly without implementing tracked redirect or click logging
- ✕AI claims conversion tracking exists but only stores a placeholder field with no input path or import flow
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 pretty dashboard with hardcoded sample metrics instead of computing from stored click and revenue data
- !AI generates content but does not attach it to campaigns, offers, or persistent records
- !AI adds affiliate links directly without implementing tracked redirect or click logging
- !AI claims conversion tracking exists but only stores a placeholder field with no input path or import flow
- !AI ignores disclosure requirements and creates risky promotional copy
- !AI builds campaign cards and statuses visually but does not persist status changes in the database
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 current build is too shallow. Replace any placeholder data structures with real persistent models for offers, campaigns, content assets, tracked links, click events, conversions, and earnings. Update the app so all future pages read from and write to these real records instead of mock data.
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.