Skip to content
Flows

What Flows just did

Based on your request to build Cost Control: Model Routing and Effort Tiers, Flows created 4 implementation stages and 12 checks.

You asked for: Implement model routing and effort tiers in the harness: task classification, per-class model/effort assignment, budget tracking, and quality-guarded rollout.. Flows generated 4 stages because the application requires A task/subtask classification the router can act on (main reasoning, summarization, classification, repair, sub-agent research); Per-class routing config: model + effort/reasoning tier + token limits; Escalation paths: failed cheap attempts retry on stronger settings. 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: Premium models summarizing tool output at 20x the needed cost; Cheap models silently degrading main-task quality with no eval to notice; Routing logic duplicated across call sites, drifting independently.

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

4 stages · 12 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: Every call site tagged with a class

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

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

Cost Control: Model Routing and Effort Tiers
Harness Engineering90-120 minutes

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

0/4 steps0%
Recording plan identity…

Step 1 of 4

Not started

Profile spend by call class

Find where the money actually goes before moving anything.

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
  • Cost Control: Model Routing and Effort Tiers

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.

Profile my agent's model spend. Instrument every model call with: call class (main-loop reasoning, compaction summary, memory extraction, classification/routing, repair, sub-agent, embedding), model, tokens in/out, and computed cost. Run a representative day of tasks (or replay recent transcripts through the accounting). Produce the spend breakdown: cost share per class, average call size per class, and the top-3 cost concentrations. Typical finding worth checking: auxiliary calls (summaries, classifications) making up a large cost share while needing far less capability than they get.

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 spend breakdown by call class with concentrations identified.

Should not happen

  • Premium models summarizing tool output at 20x the needed cost
  • Cheap models silently degrading main-task quality with no eval to notice
  • Routing logic duplicated across call sites, drifting independently
  • No escalation, so cheap-tier failures just become task failures

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…

  • !Premium models summarizing tool output at 20x the needed cost
  • !Cheap models silently degrading main-task quality with no eval to notice
  • !Routing logic duplicated across call sites, drifting independently
  • !No escalation, so cheap-tier failures just become task failures

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

Call sites are untagged and unmeasurable. Add the class tag to the single model-client wrapper (create one if calls are scattered - that wrapper is also where routing will live).

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