Agent harness
An agent harness manages the model and tool loop for an agent. It supplies context to model calls, exposes permitted tools, and returns results for the surrounding run. A domain-specific harness uses the persona’s definitions and workspace bindings to keep the work within the team’s scope.
The loop inside a run
Section titled “The loop inside a run”Inputs from the runtime
Section titled “Inputs from the runtime”A harness takes the selected playbook step, authorized context, model binding, and available tools. The playbook determines the operation and its constraints. The runtime retains the team scope, run state, budgets, and effect policy. An implementation can provide both responsibilities in one process. The draft leaves the interface between them to each implementation.
Model calls and tool calls
Section titled “Model calls and tool calls”- Assemble the instructions and context for the active step.
- Invoke the model chosen for the step’s capabilities.
- Validate any proposed tool call against the declared tool and arguments before dispatching through the authorized path.
- Add permitted results to the step context and continue within the budget.
- Return validated output, a request for review, or a failure to the surrounding run.
Example meeting brief
Section titled “Example meeting brief”The model can choose which changes deserve attention. The harness still validates that every cited meeting comes from the authorized calendar result and that the brief fits the expected output. The sequence below illustrates responsibilities.
Playbook step: summarize meeting changes runtime → supplies allowed meeting records and output contract harness → assembles context and invokes the workspace-bound model harness → validates the summary and meeting references runtime → records the result for review or an eligible next stepPause at a governed effect
Section titled “Pause at a governed effect”When an agent proposes to publish the brief, hand the proposed action back to the runtime for its policy checks. A separate approval can bind the destination, acting account, and exact content before dispatch. See tools and governed execution.