> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pidgeon.health/llms.txt
> Use this file to discover all available pages before exploring further.

# Local-first human and agent workflow

> Divide healthcare interoperability work so an agent can help with inspectable evidence while the human keeps scope and accountability.

An agent is most useful in healthcare interoperability when it can inspect a
bounded task and produce evidence the operator can review. It is least useful
when a plausible answer quietly replaces the source material or the human
decision.

## Divide the work deliberately

| Stage   | Human responsibility                                                | Agent-assisted work                                                     |
| ------- | ------------------------------------------------------------------- | ----------------------------------------------------------------------- |
| Frame   | Define the question, allowed data, environment, and acceptance rule | Turn the question into a proposed checklist or command plan             |
| Prepare | Select synthetic fixtures or approved local inputs                  | Generate repeatable synthetic cases and enumerate controlled variations |
| Execute | Approve the operation and its scope                                 | Run local generation, validation, comparison, or reference commands     |
| Inspect | Review source input, findings, and exceptions                       | Organize results and point to the evidence behind each finding          |
| Decide  | Accept, reject, escalate, or revise                                 | Record the decision context without making the decision itself          |

## Keep the evidence local

Pidgeon's local workflows can run with no cloud message-content egress. Keep
message content and detailed technical evidence on the controlled machine, and
pass only the minimum bounded context to an agent or external service that the
team has approved.

<Warning>
  “Local-first” describes the workflow boundary, not a universal promise that no
  Pidgeon surface ever uses a network. Account, update, licensing, and explicitly
  enabled provider features have their own documented boundaries.
</Warning>

## Make every finding inspectable

An agent-supported finding should carry:

* the input or stable fixture identifier;
* the exact tool and version;
* the command or operation;
* the relevant rule or comparison;
* the observed output;
* uncertainty or missing context; and
* the human disposition.

If the evidence cannot be inspected, the result is a suggestion, not a
technical conclusion.

## Use the community interfaces

The public `pidgeon` CLI provides a scriptable local interface. The governed
`@pidgeonhealth/pidgeon-mcp` adapter exposes community capabilities to a
compatible MCP client while keeping the underlying operation in the local CLI
or an explicitly selected desktop Bridge.

Start with the [public packages quickstart](/guides/public-packages-quickstart)
and use synthetic data for the first controlled run.

## Preserve the human gate

Do not treat these tools as clinical decision support, an autonomous
remediation system, or a substitute for implementation ownership. The agent
can accelerate preparation, execution, and explanation. The accountable human
still defines the boundary and signs off on what happens next.