The Autonomous Runtime Framework doesn't just run one agent at a time. It decomposes complex tasks into parallelizable subtasks, dispatches them to the right engine for each job, governs every branch independently, and merges verified results into a single coherent output. This is what work at augmented scale looks like.
The User Interfacing Agent (UIA) is the entry point for orchestrated work. You describe a task to the UIA. It analyzes the task, produces a work plan, and coordinates the other agents that do the actual work.
The UIA is not a special agent type it's a role. Any ARF-compatible runner can be the UIA. What makes it the UIA is that ARF routes your initial prompt to it and gives it the orchestration API: the ability to spawn sub-agents, assign tasks to the board, receive results, and present consolidated output back to you.
The UIA operates through ARF's proxy. Every UIA decision what subtasks to create, which engine to dispatch to, how to merge results is recorded in the proof chain. You can audit the orchestration itself, not just the output.
UIA IRON-WOLF-1 ● anthropic/claude User: Refactor the auth module, add tests, update the API docs, and review for security issues. UIA→ Decomposing into 4 subtasks: [A] Refactor auth module → COPPER-ANVIL-2 [B] Write test suite → SILVER-HAWK-3 [C] Update API documentation → JADE-WOLF-4 [D] Security review → IRON-GATE-5 BOARD tasks queued: 4 · running: 0 · done: 0 Awaiting approval to dispatch… ▶ Approve dispatch? [y/n/edit]
ARF's Autonomous Runtime Framework dispatches tasks to engines based on task type, cost, and capability. Creative reasoning goes to high-capability models. Mechanical transforms format conversion, test generation from spec go to faster, cheaper local models.
Fan-out dispatch is configured in TOML. You define routing rules based on task tags, token budget, latency requirements, and model capability tier. ARF handles the rest: translating prompts to the target engine's format, managing concurrent connections, and collecting results.
Governance applies to every dispatched task independently. Each sub-agent has its own health grade, its own circuit breaker, its own entry in the Merkle DAG. A failing sub-agent doesn't take down the whole work graph ARF can retry, reroute, or surface the failure to the UIA for re-planning.
ARF's coordination mechanism is called the Board an append-only JSONL file that serves as the single source of truth for what work is planned, in progress, completed, or failed.
Every task the UIA creates is appended to the Board as a JSONL record. Every status transition queued → dispatched → running → done is a new append. Nothing is ever deleted or updated in place. The Board is a complete, auditable history of the work graph.
Multiple agents can read the Board simultaneously. Agents check the Board to see what work is available, claim tasks by appending a claim record, and append completion records when done. The UIA monitors the Board to detect when all branches of a work graph are complete, then initiates the merge phase.
{"t":"task.create","id":"T001","type":"refactor","status":"queued"} {"t":"task.create","id":"T002","type":"test","deps":["T001"],"status":"queued"} {"t":"task.create","id":"T003","type":"security","status":"queued"} {"t":"task.claim","id":"T001","agent":"COPPER-ANVIL-2","at":"01HX…"} {"t":"task.claim","id":"T003","agent":"IRON-GATE-5","at":"01HX…"} {"t":"task.done","id":"T003","agent":"IRON-GATE-5","grade":"A","hash":"d4e8…"} {"t":"task.done","id":"T001","agent":"COPPER-ANVIL-2","grade":"B","hash":"9b1…"} {"t":"task.claim","id":"T002","agent":"SILVER-HAWK-3","at":"01HX…"} {"t":"task.running","id":"T002","progress":0.34} …