AgentGuard is the audit layer, not the actor.

What does AgentGuard record?

AgentGuard records a signed technical receipt for each governed decision: model, cost estimate, cap result, capability tier, scope, timestamp, and chain hash. Prompts, completions, API keys, and signing keys stay in the customer environment.

Does AgentGuard approve business actions?

No. AgentGuard can block, downgrade, shadow, or log an AI provider call based on the local policy you configure. It does not approve contracts, payments, claims, filings, or customer communications on your behalf.

How should auditors use receipts?

Receipts are cryptographic records that can support internal review, vendor review, and dispute workflows. A verifier can check the Ed25519 signature and hash chain without sending customer data to AgentGuard.

What if a workflow needs professional review?

Use capability tiers, reviewer cascade, and block rules to route sensitive outcomes to the review process your organization already uses. AgentGuard shows what the agent attempted and how the local policy handled it.

Where can I verify a receipt?

Use agentguard.run/verify or the SDK CLI. Verification runs in the browser or terminal and does not require uploading prompts or completions.

Functional-use disclaimer

All terminology and labels used in AgentGuard materials are descriptive of software functionality only, not legal definitions or guarantees of compliance. Terms such as receipt, audit log, evidence, audit trail, attestation, signed, verified, attested, compliance, compliant, outcome, settlement, capability tier, and settles refer to cryptographic software records and programmed state transitions only. They do not state that any record has binding legal effect, official certification, or equivalent status to records maintained by courts, banks, auditors, regulators, or agencies.

Terms drawn from audit, evidence, settlement, credit, debt, market, liquidity, maturity, and similar domains are used only in a functional and descriptive sense. An audit log is a sequence of recorded software events. Evidence means a record that may support a user review. Settlement means a final software state. None of these terms should be read as legal, financial, accounting, or regulatory advice.

Financial-context words such as trade, trading, liquidity, maturity, market, clearing, and exchange, if used in examples, describe token, budget, or workflow mechanics only. AgentGuard does not operate as a broker-dealer, exchange, clearinghouse, investment adviser, insurer, government agency, or regulated marketplace.

Words such as offer, obligation, credit, debt, payment, settle, maker, and taker refer only to hypothetical or user-operated agent workflows, simulated transaction states, or software configuration examples. AgentGuard does not transmit money, extend credit, custody funds, offer financial instruments, or guarantee settlement of obligations.

References to certify, verify, attest, signed, or validated are cryptographic and computational terms. They mean that software performed a signature, hash, schema, or chain check. AgentGuard does not claim that receipts are admissible legal evidence by default, that a court or regulator must accept them, or that use of AgentGuard alone fulfills any legal standard. The software is provided as-is as a technical audit tool.