Action playbooks

AI agent EHR write approval

Runtime authorization for writing EHR records: policy checks, approval thresholds, and decision records before the agent acts.

Veto EditorialMay 27, 2026Updated May 27, 20266 min
  • Cited source ledger with May 27, 2026 access dates.
  • Action-time policy, approval, and evidence model.
  • Primary conversion path points to a demo; developer pages also point to install.

Clinical record writes need minimum-necessary access, patient context, and review for patient-impacting changes.

Decision boundary

Put the Veto decision before ehr.write reaches the system of record. The policy should see actor, tenant, amount or target, environment, and reason before the action executes.

Risk signalPolicy response
Low value or read-onlyAllow and record the decision.
Sensitive data or production targetRequire approval from the system owner.
Wrong tenant, missing reason, or blocked destinationDeny before execution.
Repeated attempts after denyEscalate to incident review.

Example protected action

ehr.write.ts
const decision = await veto.protect({
  tool: "ehr.write",
  arguments: input,
  context: {
    actorId,
    tenantId,
    environment: "production",
  },
})

if (decision.action === "deny") {
  throw new Error(decision.reason)
}

if (decision.action === "require_approval") {
  await veto.waitForApproval({ decisionId: decision.id })
}

return executeTool(input)

A good page for this search should help the reader implement one governed action, not describe abstract governance. The useful artifact is the action-level decision record.

Sources

FAQ

What should a team authorize before writing EHR records?

Authorize the exact tool name, arguments, actor, tenant, environment, and review requirement before the side effect reaches the upstream system.

Why not rely on prompts for this?

Prompts guide model behavior, but they do not reliably stop a tool dispatch. Runtime authorization sits after the model proposes an action and before the tool executes.

What evidence should the page produce?

Keep a decision record with the actor, tool, arguments summary, policy version, verdict, reviewer when required, timestamp, and source system context.

Govern the next agent action