The Correct Way to Build and Manage AI Agents | Jared Zoneraich
Why better agents need fewer rules, the right tools, and their own tests, plus how to set up a manager agent to direct 10 cloud agents at once.
If you enjoy my content, subscribe to my YouTube for more practical AI tutorials and interviews and upgrade to unlock my personal AI OS with useful AI skills, $270 in AI tool credits, live monthly workshops, and courses on Hermes and Codex (coming soon).
Dear subscribers,
Today, I want to share a new episode with Jared Zoneraich.
Jared is a Builder in Residence at Cognition, the team behind Devin. He showed me why teams often overbuild their first agents, and how simple prompts, better tools, and self-testing work together instead. Then he demoed one manager agent breaking down a task, directing 10 cloud agents, and deciding what a human needs to review.
Watch now on YouTube, Apple, and Spotify.
Jared and I talked about:
(00:00) Why teams overbuild their first AI agent
(02:50) Let the model cook before adding rules
(03:16) Why tools matter more than better prompts
(10:51) Why you should build evals after shipping
(16:06) What cloud agents can do that local agents can’t
(20:30) How to get one agent to manage other agents
(25:39) Demo: One agent launches a team of 10
(28:03) How agents prove their work before you review it
(33:18) The best tasks for agent teams to work on
I’m proud to partner with Riverside
I produce a podcast every week and it used to take me at least 10 hours to record, edit, cut clips, write posts, and publish everywhere. Riverside has cut that time by half.
In addition to recording at 4K local with clean audio, I can also now edit using the transcript, add captions, make clips, and create and publish social posts all from one place. Riverside is trusted by teams like Spotify, Microsoft, and Vercel and you can try it for one month free at creators.riverside.com/PeterYang with code PeterYang.
Top 10 takeaways I learned from this episode
How to build great AI agents
Start by expressing your intent to the model in a simple prompt. “Let the model cook” by expressing your intent and constraints clearly instead of forcing it to follow deterministic instructions.
Give the model relevant tools to pull context. “Tool engineering” is giving the model ways to search your code, read logs, run tests, open the app, and inspect what it changed.