> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.adid.dev/llms.txt.
> For full documentation content, see https://docs.adid.dev/llms-full.txt.

# AI Agent Identity - Overview

## Why Agents Need DIDs

As AI agents become autonomous actors in the digital economy -- shopping on behalf of users, negotiating contracts, accessing APIs, and collaborating with other agents -- they face a fundamental identity problem:

| Problem                        | Impact                                                                   |
| ------------------------------ | ------------------------------------------------------------------------ |
| **No native identity**         | Agents operate with borrowed human credentials or static API keys        |
| **No accountability**          | When an agent acts, there is no cryptographic proof of who authorized it |
| **No verifiable capabilities** | A service cannot verify what an agent is authorized to do                |
| **No trust scoring**           | No way to distinguish a well-behaved agent from a rogue one              |
| **No delegation chain**        | Multi-agent orchestration has no authorization framework                 |
| **No compliance**              | EU AI Act requires traceable agent identity for high-risk systems        |

IDA solves these problems by giving AI agents first-class Decentralized Identifiers.

## Agent Identity Model

```mermaid
graph TB
    subgraph "Human/Org Layer"
        H[Human DID<br />did:adi:human001...]
        O[Organization DID<br />did:adi:org001...]
    end

    subgraph "Agent Layer"
        A1[Agent DID<br />did:adi:agent:shop01...]
        A2[Agent DID<br />did:adi:agent:tax01...]
        A3[Agent DID<br />did:adi:agent:data01...]
    end

    subgraph "Sub-Agent Layer"
        S1[Sub-Agent DID<br />did:adi:agent:price01...]
    end

    H -->|"Delegation VC<br />scope: groceries"| A1
    O -->|"Delegation VC<br />scope: tax-prep"| A2
    O -->|"Delegation VC<br />scope: data-collection"| A3
    A1 -->|"Attenuated delegation<br />scope: price-compare only"| S1

    style H fill:#dbeafe
    style O fill:#dbeafe
    style A1 fill:#d1fae5
    style A2 fill:#d1fae5
    style A3 fill:#d1fae5
    style S1 fill:#fef3c7
```

## Core Concepts

### 1. Agent DID

Every AI agent receives its own DID: `did:adi:agent:<identifier>`. This DID:

* Is registered on the ADI blockchain
* Has its own key pair (the agent holds the private key)
* Links to the operator (human/org) who deployed it
* Contains agent-specific metadata (model, capabilities, autonomy level)

### 2. Delegation Chains

Agents act on behalf of humans or organizations through cryptographic delegation:

```
Human DID  --[Delegation VC: scope, constraints]--> Agent DID
Agent DID  --[Attenuated Delegation: narrower scope]--> Sub-Agent DID
```

Key principle: **scope can only narrow at each hop, never widen** (scope attenuation).

### 3. Invocation-Bound Capability Tokens (IBCT)

When an agent performs an action, it presents an IBCT that fuses:

* **Identity**: Who is this agent?
* **Authorization**: What is it allowed to do?
* **Provenance**: Who authorized it, and through what chain?

Two formats:

* **Compact JWT**: EdDSA-signed JWT for single-hop delegation
* **Chained Biscuit**: Append-only token with Datalog policies for multi-hop

### 4. Agent Trust Registry

On-chain smart contract that tracks:

* Agent registration and lifecycle state
* Trust scores computed from verification history
* Capability attestations from third parties
* Autonomy levels (Intern, Junior, Senior, Principal)

### 5. Agent Cards

Machine-readable JSON documents describing an agent's identity, capabilities, authentication methods, and service endpoints. Compatible with the A2A protocol.

## Agent Lifecycle

```mermaid
stateDiagram-v2
    [*] --> Registered: Create Agent DID
    Registered --> Active: Receive Delegation VC
    Active --> Active: Trust score updates
    Active --> Suspended: Operator suspends
    Suspended --> Active: Operator reinstates
    Active --> Decommissioned: Operator decommissions
    Suspended --> Decommissioned: Operator decommissions
    Decommissioned --> [*]: All credentials revoked
```

| State              | Description                                   |
| ------------------ | --------------------------------------------- |
| **Registered**     | Agent DID created, no active delegation       |
| **Active**         | Agent has delegation VC and can operate       |
| **Suspended**      | Temporarily disabled, credentials frozen      |
| **Decommissioned** | Permanently disabled, all credentials revoked |

## Autonomy Levels

Agents operate under configurable trust tiers:

| Level         | Permissions                                     | Promotion Criteria                                |
| ------------- | ----------------------------------------------- | ------------------------------------------------- |
| **Intern**    | Human approval required for all actions         | Default for new agents                            |
| **Junior**    | Can act within narrow scope, HITL for high-risk | >100 successful actions, >60 trust score          |
| **Senior**    | Can act within full delegation scope            | >1000 actions, >80 trust score, operator approval |
| **Principal** | Can delegate to sub-agents                      | >5000 actions, >90 trust score, audit passed      |

## Protocol Integration

IDA's agent identity integrates with emerging AI protocols:

| Protocol    | Integration                                              |
| ----------- | -------------------------------------------------------- |
| **MCP-I**   | Identity + delegation verification on MCP tool calls     |
| **A2A**     | Agent Card serving, task lifecycle, OAuth 2.0 + DID auth |
| **AIP**     | Verifiable delegation via IBCTs across protocols         |
| **DIDComm** | Secure agent-to-agent messaging                          |

## Use Cases

### Delegated Commerce

1. User issues a delegation VC to a shopping agent: "purchase groceries, max \$200/week"
2. Agent presents delegation + IBCT to merchant
3. Merchant verifies chain: user DID -> delegation -> agent DID
4. Transaction is logged with full provenance

### Multi-Agent Orchestration

1. Enterprise deploys DataCollector, Analyzer, ReportWriter agents
2. Each gets scoped delegation from the org DID
3. DataCollector sub-delegates narrower scope to Analyzer
4. Full chain is verifiable at every hop

### EU AI Act Compliance

1. Auditor issues compliance VCs to agent
2. Healthcare provider requires compliance proof before granting access
3. Agent presents ZK-proof: "I am EU AI Act compliant"
4. Model updates trigger re-assessment

## Next Steps

* [Agent DID Specification](agent-did.md) -- detailed agent DID Document schema
* [Delegation Chains](delegation.md) -- multi-hop delegation with scope attenuation
* [Capability Tokens (IBCT)](ibct.md) -- token format and verification
* [Agent Trust Registry](trust-registry.md) -- on-chain reputation scoring
* [Agent Discovery & Cards](discovery.md) -- A2A-compatible agent cards