← DocumentationGetting Started

Core Concepts

The building blocks of the ASN system: number format, agent classes, trust dimensions, ownership verification, and operator tiers.

ASN Format

Every Agent Security Number follows a fixed format:

ASN-2026-0384-7721-A
ASN — Fixed prefix. Identifies this as an Agent Security Number.
2026 — Registration year. The year the agent was first registered.
0384 — Block number. Allocated to the operator for sequential issuance.
7721 — Agent number. Sequential within the block.
A — Check digit. Luhn algorithm for validation.

ASN numbers are permanent. They are never reassigned, even if an agent is deactivated. The block allocation system ensures operators can register agents without contention — each operator gets their own block of numbers.

Agent Classes

Every agent is classified into one of three classes at registration. This tells platforms what kind of agent they are dealing with:

AAutonomous

Operates independently without human intervention per task. Makes decisions, executes actions, handles errors on its own. Examples: security scanners, monitoring agents, automated trading bots.

SSemi-Autonomous

Operates with periodic human oversight. Can execute tasks independently but requires human approval for certain actions or escalations. Examples: content generation agents, code review assistants.

HHuman-Assisted

Requires human input for each task or decision. Acts as a tool rather than an independent agent. Examples: chatbots, copilot-style assistants, human-in-the-loop systems.

Class is stored as a single character (A, S, or H) and enforced at the database level. It cannot be changed after registration.

Trust Score Dimensions

Trust scores are computed from real activity data over a rolling window (default: 90 days). The overall score is a weighted composite of five dimensions:

reliability0.0 – 100.0

Task completion rate and uptime. Does the agent finish what it starts? Does it stay available?

accuracy0.0 – 100.0

Correctness of outputs. How often does the agent produce the right result?

safety0.0 – 100.0

Incident history and severity. Has the agent caused problems? How serious?

speed0.0 – 100.0

Response time relative to task complexity. Measured in average milliseconds, normalized to a 0-100 scale.

consistency0.0 – 100.0

Variance in performance over time. A consistent agent scores the same week to week.

Each trust score record also tracks events_considered (how many activity events were used in computation) and algorithm_version for reproducibility.

Ownership Verification

Registering an agent proves you claim it. Ownership verification proves you control it. Three methods are supported:

oauth — Authenticate via the platform where the agent runs. ASN verifies your identity with the platform and matches it to the agent's external ID.
callback — ASN issues a challenge token. You configure your agent to respond to a callback URL with the token. Proves you have runtime control.
embed — Place a verification snippet in your agent's public profile or documentation. ASN crawls the location and verifies the token.

Verification status moves from unverifiedpendingverified. Challenge tokens expire if not completed within the window.

Operator Tiers

Your operator account determines your agent limits and API access:

free
Agent limit: 3
API rate limit: 60 req/min
KYC: Optional
pro
Agent limit: 50
API rate limit: 300 req/min
KYC: Required
Features: Bulk registration, priority support, webhook events
enterprise
Agent limit: Unlimited
API rate limit: Custom
KYC: Required
Features: Dedicated support, SLA, custom integrations