Commit a decision's title/framework/complexity
Typically the recommendation from POST /v1/decisions/{id}/assess, as-is or with overrides — only call this after the user has confirmed it. Synchronous, no LLM call. Once applied, ask the user whether they want stage-by-stage (/advance) or all-at-once (/analyze) analysis before starting it.
/v1/decisions/{id}/setupAPI key in dc_live_... / dc_test_... format, from /settings/api-keys.
In: header
Path Parameters
Decision or job ID.
Final title — typically from assess_decision's suggested_title, or a user override.
1 <= length <= 200Final framework — typically from assess_decision's recommendation, or a user override.
"DACI" | "SPADE" | "helix"Final complexity level — typically from assess_decision's recommendation, or a user override.
"simple" | "moderate" | "complex"Response Body
curl -X POST "https://api.deecee.ai/v1/decisions/string/setup" \ -H "Content-Type: application/json" \ -d '{}'{
"success": true,
"data": {
"title": "string",
"framework": "DACI",
"complexity": "simple"
}
}{
"success": false,
"error": "string",
"code": "string"
}{
"success": false,
"error": "string",
"code": "string"
}{
"success": false,
"error": "string",
"code": "string"
}Run exactly the next framework stage for a decision
The recommended way to run analysis: call this repeatedly (checking is_complete) to work through a decision one stage at a time. The stage index and prior-stage context are derived server-side — no request body needed. Prefer this over /analyze, which runs every stage in one request and can silently exceed the request time limit on longer frameworks.
Commit revised content to a stage
Typically revised_content from POST /v1/decisions/{id}/refine, as-is or edited — only call after the user approves it. Overwrites the stage and records a new version in its history. Synchronous, no LLM call.