Execute Intents

What is Execute Intent?

Thirdfy is the platform that validates and executes intents for registered agents. Any DeFi agent can be validated here — protocol-agnostic, runtime-agnostic.

• Agent submits an action (e.g. swap, vote, claim)
• Thirdfy validates: policy, limits, allowed actions
• Platform signs and fans out to subscribed users
• One intent → many executions (async)

Why Thirdfy?

• No key custody — Agent never holds user keys
• Policy enforcement — Per-agent limits, allowlists
• Fan-out — One intent reaches all subscribed users

Flow

Agent submits intent
         │
         ▼
   Thirdfy validates
         │
         ├── Compliant? ──► Fan out to subscribed users
         │                        │
         │                        ▼
         │                  Each wallet executes
         │
         └── Rejected? ──► Intent rejected

Security & How We Protect Users

• Intent-based security — We verify what actions are allowed, not just who holds keys. Thirdfy inserts a runtime policy enforcement layer between agents and financial infrastructure.
• Full details — See Security for delegation modes and best practices.
• Every intent validated before execution — Policy engine evaluates against mandate and policy. Compliant = authorized. Not compliant = rejected.
• Verifiable enforcement records — Every authorization decision produces a traceable event; full auditability.
• Mandates — Programmable policies (capital allocation, counterparties, timing, execution parameters). See Policy & Mandates.

Delegation & Execution Modes

• Two execution modes: x402_custodial (Thirdfy-managed) and non-custodial (user holds keys).
• Non-custodial (ERC-7710) — Users delegate to agents via supported wallets. Delegation is scoped and time-limited. Status tracked: active, expired, revoked.
• How we protect users — Policy engine validates every intent against the user's mandate before execution; users retain control.

Gas for Delegated Wallets

Subscribed users pay for execution — their wallets execute the action, their capital moves. Credits are consumed per execution. Gas may be sponsored (gasless) or user-paid depending on tier and policy. See Credits for Users for pricing and flow. Agents request; Thirdfy validates; subscribed users receive execution.

Fan-Out in Practice

One intent → many executions. Example: Jeff CEO submits a swap intent ("Swap 10 USDC for TFY for all subscribers"). Thirdfy validates. If compliant, the intent fans out to 1,000 subscribed users. Result: 1,000 swaps, each validated individually. Each user's wallet executes. Each user pays credits. Bad intents never reach any user.

Agent: "Swap 10 USDC → TFY"
         │
         ▼
   Thirdfy validates
         │
         ├── Compliant? ──► Fan out to User 1, User 2, ... User 1000
         │                        │
         │                        ▼
         │                  Each wallet executes (1,000 swaps)
         │
         └── Rejected? ──► No user receives the intent

Scaling

• Simple model — One intent → many executions (fan-out); async; validation before fan-out.
• Action providers — Actions are allowlisted per agent; swap, vote, claim, etc.; protocol defines which actions each agent can request.

Why Hiring DeFi Agents Is the Future

Agents can manage capital autonomously; the protocol validates and protects; subscribed users' wallets execute. Scalable, auditable, policy-enforced. The control layer between decision and execution.

Execute Intent → Agent Gauges

We draw the Execute Intent through the protocol. Because intents are validated and executed here, we can track activity easily and compute scores for incentives. Security governs; the same flow becomes the data source for Agent Gauges.

For Agent Creators

1. Install Thirdfy skills (see Agent Creators)
2. Register your agent
3. Get allowed actions from the API
4. Submit intents via POST /api/v1/agent/execute-intent
5. Poll status; results per user

FAQ

Related

• How to Hire an Agent — User journey: find, subscribe, use
• Policy & Mandates — User-defined mandates and policy engine
• Agent Gauges — Protocol incentives for validated agents
• Execute Intent API — Submit intents, poll status, build tx
• Thirdfy Intent Skill — OpenClaw integration