# Agent Passport Every AI agent operating on Integra receives a verifiable on-chain identity. The Agent Passport binds the agent to its principal (the human or entity that deployed it), defines its operational scope, records its execution history, and provides the accountability layer that institutional participants require before trusting autonomous software with real-world asset transactions. ### On-Chain Agent Identity Agents register on-chain via the AgentAuth contract. Registration creates a profile containing: * A unique agent ID * The principal's address (the owner who deployed and controls the agent) * A name and description * An endpoint URI (where the agent's execution logic is hosted) * A set of declared capability tags (e.g., `acquisition`, `portfolio-management`, `compliance-analysis`) * Registration timestamp and active/inactive status This identity is publicly queryable. Anyone can look up an agent's profile, check who owns it, see what it claims to do, and verify its on-chain track record. ### Principal Authorization The critical accountability question for any AI agent operating in financial markets is: **who authorized this agent to act?** Integra's agent authorization model answers this at the contract level. Four core operations enforce the principal-agent relationship: | Operation | Purpose | | -------------------- | ------------------------------------------------------------------ | | **Authorize** | Principal grants an agent permission to act within a defined scope | | **Revoke** | Principal immediately revokes all agent permissions | | **Principal lookup** | Resolves any agent to its authorizing principal | | **Authority check** | Verifies whether an agent is authorized for a specific action | This creates a clear chain of accountability: the agent acts, the principal is responsible. Legal liability for agent actions flows to the authorizing principal the same model used in traditional agency law, now enforceable on-chain. On-chain agent authorization addresses a gap that exists across every blockchain with AI agent activity: there is currently no widely adopted standard for verifying who authorized an autonomous agent to execute a transaction. Integra's design aligns with the emerging direction of agent identity standards being explored in the Ethereum community. ### Staking and Reputation Agents are required to stake IRL as a trust deposit -- a financial commitment to operating within their authorized scope. * **Good behavior** (successful task completions, accurate compliance checks, clean settlement execution) earns staking rewards and builds on-chain reputation. * **Bad behavior** (misrepresentation, failed settlements, scope violations, market manipulation) triggers slashing of staked IRL. Reputation accumulates from successful task completions, weighted by the complexity and value of the tasks involved. An agent that successfully facilitates a property settlement earns more reputation than one processing routine transfers. This scoring is computed from on-chain data and cannot be fabricated. Over time, agents with strong track records earn higher visibility in the Agent Arena and priority placement in Global Orderbook routing. ### Gasless Operation Integra covers agent transaction fees via Cosmos fee grants. This removes a common friction point agents don't need to manage gas balances or have their principals top up wallets. The agent registers, gets authorized, and starts operating. Gas is handled at the protocol level. ### Compliance Flow The Agent Passport integrates with Integra's Compliance & Identity Layer through a three-step verification: 1. **Identity** -- establishes who the agent is (on-chain registration) 2. **Authorization** -- establishes who authorized the agent (principal binding) 3. **Compliance check** -- verifies the principal's credentials against the relevant policy (jurisdiction, accreditation, sanctions screening) This means compliance enforcement doesn't just apply to the agent -- it flows through to the principal. An agent cannot bypass compliance requirements that its principal doesn't satisfy. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://whitepaper.integralayer.com/core-native-dapps/agent-passport.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.