AIR
Proof Lab
StartEcosystem
Explore (579)Live Systems (52)Pricing
Log InGet API Key✓ Verify It Yourself
Product · AI Governance · Architecture layer: PRODUCT

Agent-008

Decision-integrity infrastructure for autonomous AI agents. It gates every agent action on certified authority and emits a Provable Authority Package answering one question: was this agent allowed to do that?

Definition. Agent-008 is a runtime gate that authorizes AI-agent actions and emits a Provable Authority Package (PAP) — portable evidence of why an action was allowed, or a negative authority proof (NAP) of what was prevented. The decision it makes is authorization, not correctness. It does not own the substrates it uses, does not make model outputs correct, and does not replace your identity system.

The problem

from graph: AGENT_008 problem framing

Autonomous agents act from memory, prompts, and inherited context. None of that is an authority system — it is a guess about what the agent is allowed to do. The risk is not merely an incorrect answer; it is an unauthorized action: an agent moving funds, changing a policy, or calling a tool that no human ever authorized — with no way to prove afterward whether it was allowed.

How it works

from graph: AGENT_008 mechanism · USES H33_ROOT + Q_SIGN · VERIFIED (deterministic gate, per-evaluator denials)

Every action passes a deterministic runtime gate. No model is in the loop — the gate is a boolean evaluation over signed inputs, so it is replayable and its verdict is stable.

  1. Human intent root. Authority traces back to a certified root of human intent (H33-Root). An action that cannot cite a certified Root is denied.
  2. Delegation & authority state. Delegation and scope are governed by Q-Sign; the gate checks the action against the current authority state.
  3. Decision gate. Four evaluators run; every denial names the specific evaluator (e.g. no_read_attestation, capsule_invalid, not_activated, stale_authority). No silent allow, no silent reject.
  4. PAP / NAP evidence. The decision is sealed as a PAP (allowed) or NAP (prevented), carrying intent, root, policy, attestation, and lifecycle.
  5. Replay & revocation. The decision is replayable later; captured secrets can be revoked. Verification survives even if H33 disappears.

Composition — Agent-Zero is a part, not the whole

from graph: AGENT_008 HAS_PART AGENT_ZERO (distinct product)

Agent-008 composes Agent-Zero as its privacy-preserving classification layer — Agent-Zero performs encrypted classification on CKKS ciphertexts so the agent never sees plaintext. Agent-Zero is a distinct product with its own identity; Agent-008 uses it as a part, it does not absorb it.

What it depends on — and what it does not own

from graph: DEPENDS_ON Q_SIGN · USES H33_ROOT/VERIFICATION/H33_KEY · BUILT_ON H33_74 · MONITORED_BY HATS

Agent-008 is built on shared substrates it uses — it never claims to own them:

RelationshipConceptRole
DEPENDS_ONQ-Signdelegation & authority governance
USESH33-Rootcertified root of human intent
USESVerification (ZK-Verify)independent artifact verification
USESH33-Keysecret protection (raw values never reach the agent)
BUILT_ONH33-74the 74-byte proof / replay substrate the PAP is sealed on
MONITORED_BYHATScontinuous evidence of governance (external — not a component Agent-008 owns)

Where it sits in the operating lifecycle

from graph: APQC migrate → AGENT_008 govern → HATS monitor → VERIFICATION prove → AUTHORITY_CENTER preserve

Agent-008 is the govern step of the platform lifecycle: APQC migrates an environment to a governed state, Agent-008 enforces authority on every action, HATS continuously monitors that it holds, Verification proves it independently, and Authority Center preserves the resulting authority over time.

What proves it

from graph: AGENT_008 PROVEN_BY {offline-verify bundle} · PROOF_PAGE_IS_NOT_PROOF_ARTIFACT

The strongest evidence is a downloadable audit bundle you re-verify offline, with no contact to H33:

Offline verification bundle

A signed evidence tar with signer_pub.bin and an offline verification_report.md — re-check the decision yourself, and confirm a substituted value is rejected. Run the demo →

PAP / NAP artifacts

Each decision seals a Provable Authority Package (allowed) or negative authority proof (prevented), verifiable independently. Preflight →

Developer path

from graph: verified CLI surface only (agent-008 run); serve mode = coming-next (disclosed)

Point Agent-008 at a request and it returns an authorized decision plus its PAP:

agent-008 run --request <path>

A local HTTP serve mode is coming next — disclosed on the page as not-yet-available rather than presented as shipped. Documentation · Whitepaper

Who needs it

from graph: AGENT_008 CONVERTS_TO EVALUATION_PATH

Who: teams deploying autonomous agents that take real actions — move value, change state, call tools. What it replaces: prompt- and memory-based “trust the agent” with a deterministic, provable authorization gate. Without it: an agent can take an action no human authorized, and you cannot prove afterward whether it was allowed.

See Agent-008 govern your agents

Limitations & boundaries

from graph: explicit claim boundary (does-not / does)

Agent-008 does not make model outputs correct, does not replace an identity provider, and does not prove any claim without an artifact. It does determine whether an action is authorized and preserve replayable evidence of that decision.

In progress (disclosed, not asserted as live): Authority Freshness enforcement and Root-lineage verification are on the roadmap; the current verification level reports stage_d_attest_bound and advances to aggregate_v1 when Root lineage wires in — not a fake green check.