How to Build On-chain AI Agents
summary
Walks through a concrete build: complete Solidity code that deploys an on-chain agent which calls a two-part oracle (on-chain contract + off-chain teeML TEE oracle), sends prompts to GP-style models, and writes verifiable inference back on-chain. Demo uses a playground and MetaMask to deploy and transact, showing low-latency, low-cost inference and an attestation written to the chain. Source and tutorials are open source so the example is reproducible end-to-end.
AI-written summary · about
chapters (4)
- 0:00Introduction to Galadriel
- 1:38TeeML product overview
- 3:37How on-chain inference works
- 7:17Building on-chain AI agents
related talks
15mBuilding AI Agents the Web3 Way
09mBuild and Deploy AI Flows with an Agent Factory
40mBuilding Effective AI Agents Simple, Composable Patterns
22mAccountable AI agents
32mProgress In the Decentralized AI Stack
49mLet's build an AI agent
01h 23mBuild your own AI Agent
01h 26mAI Agents of Change: Creating, Reflecting, and Monetizing