Features

Orchestration & autonomy

Some work is one question and one answer. Some is a goal that needs several specialists, an hour of research, or the same task repeated over two hundred rows. Trellaris has four primitives for that โ€” and each one is bounded, because unbounded autonomy is how agent platforms produce surprise invoices.

PrimitiveUse whenBounded by
OrchestratorA goal needs several different agents.Step cap, cost cap over the run family, wall clock.
Background runsThe work takes minutes to hours.Step cap, deadline, resume cap.
Fan-outThe same task over many items.Item cap, family cost cap, one level deep.
Wake-upsSomething should be checked later.Horizon and pending-count policy caps.

The orchestrator

A built-in supervisor agent. You give it a goal; it decomposes the goal, routes each step to the best agent you can see, runs independent steps in parallel, critiques the result, and synthesizes an answer with citations back to the work that produced it.

  1. Plan

    The goal becomes a task graph. Planning runs on the cheap model tier.
  2. Route

    Each step is matched to a candidate agent by vector similarity, then reranked by a cheap-tier model, falling back deterministically if the rerank is unavailable. Native, remote, and adapter-backed agents are all routable through one interface.
  3. Execute in waves

    Independent steps fan out as child runs, each with its own session and its own event stream. The chat view shows the task tree live.
  4. Critique and replan

    A critic checks the result against the goal and can trigger a replan, capped at two rounds so it cannot loop.
  5. Synthesize

    A strong-tier model composes the final answer, and delegation chips in the thread show which agent contributed what.

What makes it safe to leave running

Turn it on under Build โ†’ Capabilities. Once enabled it is a normal org-ring agent, so chat, automations, channels, and inbound A2A can all invoke it without any special casing.

Background runs and Deep Research

A background run is for work that outlives a chat turn. It produces a plan first, then executes it step by step, checkpointing as it goes.

CapabilityBehaviour
Visible planThe plan is written as a run artifact you can read before the work finishes.
ProgressEach completed step checkpoints and reports to the inbox.
SteeringSend guidance mid-run; it is consumed at the next step boundary and extends the plan rather than derailing it.
Pause and resumeExplicitly, at any point.
Crash recoveryIf the worker dies, the run resumes from its last checkpoint rather than being written off โ€” up to a resume cap, after which it fails honestly.
DeadlineOn hitting its wall clock, the run synthesizes what it has and marks the answer budget-limited.

Deep Research is the built-in agent built on this: a research question becomes a plan, each subtopic is searched and read, and the synthesis turn composes findings under the citation contract. Enable it under Build โ†’ Capabilities.

Defaults (deployment-configurable)

Fan-out

map_over takes a list โ€” items, or the rows of a CSV โ€” and spawns one child run per item through the same execution path, then collects the results into a single artifact on the parent.

Wake-ups

schedule_followup lets an agent arrange to be woken once, later โ€” "check on Thursday whether the vendor replied". It becomes a one-shot automation, fires exactly once, and is visible and cancellable in the automations list like anything else. Horizon and pending-count caps come from the wakeup policy; a breach returns a tool error the agent can explain rather than failing the run.

Autonomy in practice

Autonomy is the dial that decides how much of the above happens without a person. The effective level is the lower of what the agent declares and the organization's floor.

LevelReadsWritesDestructive
supervisedRunParkPark
trustedRunRunPark
autonomousRunRunRun
Autonomy relaxes the baseline, never an explicit rule An approval policy โ€” or an agent flagged requires_approval โ€” parks the call at every level, including autonomous.

Choosing a primitive

The shape of the workReach for
One question, one specialistJust chat to the agent
Several specialists, one goalThe orchestrator
Long, open-ended investigationDeep Research / a background run
Same task, many itemsmap_over
Recurring on a clockA cron automation
One-off, laterschedule_followup