HACP v0.3-candidate

Accountable agent work, explained from the evidence

Eleven problem-first articles for leaders and implementers. Start with the evidence boundary, or jump directly to the problem you are solving.

Candidate statusWhat HACP v0.3-candidate Proves and Does Not Prove

The canonical maturity and non-claims boundary.

Interworking evidenceTwo Implementations, One Candidate Contract

WITS production, HACP validation, and separate who-decides semantics.

Authority boundaryA Receipt Is Evidence, Not Approval

Why approval, execution, reports, and receipts answer different questions.

One-use admissionWhy Idempotency Does Not Prove One-Use Human Approval

Concurrent claimants, restart readback, and stale replay.

Decision gatesHuman-in-the-Loop Without Approval Theater

A practical checklist for exact, bounded human choices.

Fail closedWhen Stop Is a Successful Agent Outcome

Typed outcomes for missing authority, stale context, and scope conflict.

Accountable handoffsFrom Clipboard Relay to Accountable Continuation

Preserving identity, scope, authority, and causation across contexts.

Layer boundariesMCP Moves Tool Calls; HACP Governs Accountable Work

How capability transport and human-approved coordination compose.

Executable conformanceHow We Test an Agent Protocol

Valid branches, exact negative diagnostics, digests, and external bundles.

The next transitionYour Agent Said Done. Who Authorized the Next Step?

Why a report cannot silently become permission.

Construction provenanceWho Built This Packet?

Why integrity cannot identify the builder or prove correct assembly.

Early implementers

Challenge the candidate against a real workflow

Implement the candidate, run the conformance package, and tell us where the contract fails against your workflow.