What Flows just did
Based on your request to build Choose the Right Dispatch: Spawn, Fork, or Direct, Flows created 4 implementation stages and 12 checks.
You asked for: Implement spawn and fork dispatch paths with correct context handling, and encode a decision policy for when each strategy (including direct) applies.. Flows generated 4 stages because the application requires A spawn path: named agent definitions with fresh context, own tool pool, own permission mode and model; A fork path: child inherits the parent conversation and system prompt for cache sharing; A direct-execution default for tasks below dispatch overhead. 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: Spawning with a one-line prompt and wondering why the sub-agent flails without context; Forking for everything, including tasks needing a specialist definition the fork lacks; Unbounded recursive forking melting the budget.
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: Registry with prompt/tools/model/permission per …
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)
- 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 4
Not startedImplement spawn: fresh context specialists
A spawn is a new employee: they know only what the dispatch tells them.
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
- Choose the Right Dispatch: Spawn, Fork, or Direct
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.
Build the spawn path. Maintain a registry of agent definitions (explorer, planner, verifier, general) each with: its own system prompt, tool list, default model (cheap+fast for read-only scouts, inherit for reasoning-heavy roles), and permission mode. On dispatch: look up the definition, build a FRESH context containing only the definition's system prompt plus the dispatch message - no parent history. Assemble the child's tool pool independently under its own permission mode, not a copy of the parent's. Because the child starts from zero, enforce dispatch-prompt discipline: task, relevant background, constraints, expected output format - a checklist the orchestrator prompt requires. Return the child's final report as a tool result the parent folds into its context.
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
Working spawn dispatch with per-definition prompts, tools, models, and fresh contexts.
Should not happen
- ✕Spawning with a one-line prompt and wondering why the sub-agent flails without context
- ✕Forking for everything, including tasks needing a specialist definition the fork lacks
- ✕Unbounded recursive forking melting the budget
- ✕Dispatching a sub-agent (with full startup cost) for a two-step task the parent could do inline
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…
- !Spawning with a one-line prompt and wondering why the sub-agent flails without context
- !Forking for everything, including tasks needing a specialist definition the fork lacks
- !Unbounded recursive forking melting the budget
- !Dispatching a sub-agent (with full startup cost) for a two-step task the parent could do inline
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
Spawned agents keep asking about things the parent already knows. That is the design - the fix is in the dispatch prompt, not shared state: require the orchestrator to include the missing background, or conclude this task wanted a fork instead.
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.