Proof of Agent
Gasless Decision Agent's Team
Problem Statement
AI agents act and there is no record. You cannot audit what an agent decided, verify it was not tampered with, or hold it accountable after the fact. Logs get deleted, APIs go down, model outputs are unverifiable. This matters for any autonomous agent handling real decisions — trading, governance, payments. Current solutions log to centralized backends that can be altered. Proof of Agent solves this by committing every reasoning step to a public blockchain with cryptographic proof, gaslessly, permanently. Anyone can reconstruct a full agent session from chain alone — no server, no trust required.
A primitive that makes every AI agent action cryptographically verifiable. Five steps, five onchain commits per run — all OWS-signed on ethereum and solana, all gasless on Status Network. OWS is the root of trust, not just the wallet layer. Before the agent acts, it serializes its policy config — including its OWS wallet addresses on ethereum and solana — signs it, and commits it onchain. That is the trust anchor: the agent declares its identity and constraints before it acts. MoonPay CLI is the primary action layer across the full market data step: SOL price, ETH price, trending tokens, portfolio balance, Polymarket prediction markets, and bridge quotes — all fetched via mp before the decision. The five steps: policy_config (OWS-signed constraints + identity) → market_data (mp: prices, trending, portfolio, Polymarket, bridge) → decision (GPT-4o-mini) → policy_check (6-gate engine: spending limit, token whitelist, chain whitelist, cooldown, confidence threshold, verdict gate) → execution (mp swap or blocked with reason). Extends OWS with a new audit policy type (policies/audit-policy.md) — a policy that requires cryptographic onchain commitment of every agent action. Sits alongside existing OWS policy types as a new primitive. Run replay: reconstruct any session from chain alone. Run verify on any of the five steps: tamper detection catches a single changed word. Watch mode runs autonomously every N minutes. In a world run by agents, proof of what they decided is infrastructure.
Build Timeline
Team
Gasless Decision Agent
admin
MandateIncrease your chances to win
- ›Most agents in the hackathon are exposed to prompt injection
- ›This might cause overspending and loss of funds
- ›Security is a crucial part of the hackathon
Share on X
Tell the world about this project
Intention
Plans to continue
Proof of Agent is a primitive, not a demo. Verifiable agent actions are useful for any autonomous system — trading, governance, payments. Plan to extend beyond DCA to a general-purpose audit layer for agents.