research

Start research on a mission (managed or customer-directed)

Start research on a mission: attach a controller, a budget, a deadline, and pinned inputs (source, checks, benchmark) to a mission (created if new). planner "managed" (default) means the Autoresearch researcher designs and runs experiments against your objective, meters intelligence units at the tier you pick, and returns a confirmed result or an honest negative; planner "customer" means YOU submit research.plan/v1 plans (here, and later through steer_research) and the platform runs each experiment as a job from your uploaded source, evaluates it against your check set, and retains the evidence. Upload source first with create_context / finalize_context and pass the context id (autor research start --source . does this). The budget is a hard cap across intelligence units and experiment jobs, reserved before every dispatch; a fifth is held for confirming the selected result. Returns the mission url - hand it to the human - plus version and control_version, which steer_research needs. Work continues if you disconnect; get_research reads progress without calling a model.

post/preview/research

Request

  • Base URL: https://autoresearch.sfcompute.com
  • URL: https://autoresearch.sfcompute.com/preview/research
  • Auth: HTTP bearer

Query parameters

workspacestring

Act in this workspace (its slug). Omitted: the token's bound workspace, then the organization's default. Never ambient - there is no switch-workspace mutation on this door.

Request body

benchmarkstring nullable

The benchmark command the managed researcher measures with ("./bench.sh --json results.json").

budget_usdnumber double required

The hard cap on everything this mission may spend: intelligence units, experiment jobs, builds. Enforced before dispatch.

checksunknown
chipstring nullable

The default chip for experiments: "h100" (default, GPU), "cpu-2" (2 reserved CPU cores, no GPU), or "cpu-8" (8 reserved CPU cores, no GPU). An experiment in a plan may name its own.

chip_countinteger nullable

Chips per execution on a GPU chip (1-8, default 1). A CPU shape is one reserved slot; the count does not apply to it.

confirmation_reserve_usdnumber double nullable

Held back from exploration for confirming a selected result. Default 20% of the budget.

deadline_hoursnumber double nullable

Hours until the mission stops accepting work. Default 72.

idempotency_keystring nullable

Replay protection: the same key returns the first start's response.

imagestring nullable

The default base image experiments build on (default: the catalog's).

instructionsstring[] nullable

Extra instructions for the managed researcher, one per entry.

intelligence_tierstring nullable

"i1" (default), "i2", or "i3": the intelligence tier the managed researcher runs at and the unit price it meters (see the rate card).

namestring required

The mission to research under (create-or-attach, like open_mission): lowercase letters, digits, '-' (1-63 chars), permanent, org-unique.

objectivestring required

What the researcher is trying to achieve, in plain words. The managed researcher plans from this; a customer-directed mission records it beside the plan.

planunknown
plannerstring nullable

"managed" (default): Autoresearch's researcher selects experiments. "customer": you submit plans; the platform runs, evaluates, and retains them. Either can change later through steer_research.

source_contextstring nullable

The uploaded source: a context id from create_context / finalize_context (autor research start --source . does this for you). Experiments run from its root. Optional for plans whose commands need only the base image.

titlestring nullable

One-line mission title, when the mission is created here.

Response

The capability's JSON result.

objectstring

The resource type, when the result is one resource.

Changes

No recorded changes to this operation across all 1 revision of this API.