A persistent, multiplayer environment for long-horizon or recurring agentic work, built around a conversational orchestrator, self-evaluating graph-based skills, stateful applets and curated attention. Design and spawn multiple goal-driven agents to solve complex problems.
Bring your own model keys.
Durable execution
A task's scope is fixed before it starts: its tools, its instructions, the context it reads. Run nine is as lean as run one, and it begins from what the eight before it recorded.
Push the spaceship-titanic model past 0.85 accuracy. Start from last week's feature set and keep going until it clears.
Running tabular-model-tuning as a campaign on lbValue, target ≥ 0.8500. This is run #9 of the twice-daily schedule, and I've pulled the four learnings the earlier runs recorded.
Representative run · a fixed example, drawn with the product's own surfaces.
Ask in the space. The Helmsman selects the skill, fills its inputs and starts the run.
human.chat.askCron, one-shot, or on-completion of another run. Leased and de-duplicated, so a fire happens once.
agent.schedule.* · 0 7 * * 1A public HMAC-verified endpoint per space. Filter and map the payload, then start a session from it.
POST /v1/webhooks/ingest/…Skills & contracts
Agent tasks, deterministic operations and human decisions are the node kinds. One shape can be scored against another, and the Helmsman rewrites the graph from what the runs showed.
Fixed agent roles
What varies is the skill, the memory and the tools each task is given.
The Helmsman steers. It runs the conversation, and what it attends to shifts with the state of the space. It starts skills and follows up on them, reads accumulated learnings, connects integrations, and writes or adjusts skills.
Task execution is delegated to a Runner.
The Runner executes. Its scope is fixed before it starts: one task, the tools that task needs, and instructions written for it. It completes the task or fails it, and a blocked Runner returns to the Helmsman.
A Runner calls no other agent.
The Coach runs the hill-climbing loop. It reads finished runs as evidence — their scores, their failures and their costs — and proposes a change to the skill.
Applying a proposal requires an operator.
Multiplayer AI
Both act on the same state through the same validated actions, and Role-based access controls (RBAC).
The learning loop
A campaign scores every run against a target. The Coach reads the finished runs as evidence — their scores, their failures, the learnings they recorded — and proposes the next change to the skill, which an operator ratifies.
Train task timed out twice; reduce estimator count.
The suite scores accuracy and nothing else.
Integrations & MCP
165 operations ship with the platform, and every connector or MCP server a space installs adds more.
Coding pipelines
Claude Code and OpenCode take resolved inputs from the graph and return outputs the platform validates, so coding lanes fan out, converge and stop for a person like any other task.
Access is limited to a few invited testers, on your own model keys. If you're working on similar problems, or want the architecture in more detail than a landing page can carry, get in touch.
