The Correct Way to Build and Manage AI Agents | Jared Zoneraich

Jared Zoneraich, a Builder in Residence at Cognition, discusses how to build effective AI agents by emphasizing simple prompts, providing the right tools, and implementing self-testing rather than overbuilding with complex rules. He explains the advantages of cloud agents over local ones and demonstrates how a manager agent can direct a team of cloud agents to break down and execute tasks, with built-in verification before human review.

• Teams often overbuild their first AI agents by adding too many rules.
• Simple prompts, better tools, and self-testing are key to effective AI agents.
• Giving the model room to ‘cook’ with clear intent and constraints is more effective than deterministic instructions.
• Tool engineering, which allows agents to search code, read logs, run tests, and inspect changes, is crucial.
• Building evaluation metrics (‘evals’) after shipping an agent can be more practical.
• Cloud agents can perform tasks that local agents cannot, offering greater capabilities.
• One agent can be designed to manage and direct other agents.
• A demo showed one agent launching and managing a team of 10 cloud agents.
• Agents can prove their work before human review.
• Ideal tasks for agent teams include breaking large migrations into independent slices for parallel processing.
  https://bender.layer3.press/articles/43517f35-b6c6-4fa9-a160-84f5f44cd777