How Intent Layer Works

The risk of AI agents isn't malicious behavior — it's unbounded authority. This page covers why Intent Layer exists, how the trust model is enforced on-chain, and where bounded authority applies.

Why Intent Layer

The risk of AI agents isn't malicious behavior — it's unbounded authority. Intent Layer exists to limit blast radius, not maximize outcomes.

Verification-first
1

Blast radius control

Budgets, venues, selectors, assets, time windows. Authority is explicitly bounded and enforced on-chain.

2

Auditable by default

Readable violations: budget exceeded, venue not allowed, TOCTOU mismatch.

3

Delegated authority, not delegated keys

Agents decide actions. Executors perform them. Swap executors without migrating wallets or changing policies.

Security & Trust Model

Execution power is always constrained, auditable, and replaceable by design.

Trust by design

Who can execute

Any authorized executor can run an intent — but only after it passes on-chain policy validation.

Who can move funds

Executors never have custody. They can only execute what a policy explicitly allows.

How authority is bounded

Budgets, venues, selectors, and time windows are enforced on-chain before execution.

If an executor is malicious

Invalid intents fail validation, violations emit readable errors, and apps can switch executors without migrating wallets.

Where Intent Layer Fits

Bounded agent authority applies wherever agents act autonomously.

Authority boundary

Programmatic operations

For teams replacing brittle ops scripts with auditable flows

Payroll, invoices, infrastructure payments — policy-constrained with full audit trail.

Agent-to-agent services

For builders giving agents real economic power

Agents propose actions, policies decide what executes. Authority expands only with human approval.

Autonomous finance

For protocols and agents managing on-chain capital

Swaps, lending, rebalancing, DCA — all bounded by budgets, venues, and selectors. DeFi is one domain where bounded authority matters.

Ready to integrate?

See the quickstart, SDK reference, and MCP setup in the full docs.