David Ondrej Podcast — selected agentic engineering conversations
L8 Principal's Agentic Engineering Setup (just copy him)
Six curated interviews on software factories, agent environments, review, and harness design
A manually reviewed selection from the David Ondrej Podcast featuring Armin Ronacher, Dexter Horthy, Thorsten Ball, Matt Pocock, Kun, and Magnus Müller. The conversations examine how agentic engineering shifts attention from code generation toward product judgment, architecture, working environments, context, orchestration, verification, and small adaptable harnesses. Practitioner observations and forecasts are not controlled findings.
In this collection Browse 6 summaries 5 of 6
David Ondrej interviews Kun about a solo-development workflow with one coordinating agent and many parallel sessions. It moves routine coordination out of the human loop while returning ambiguous decisions to Kun and validating consequential changes before merge.
Key Points Covered
- Use a coordinator instead of personally juggling sessions: Kun's First Mate receives his requests and routes work to crew agents in Herder. It lets him inspect an individual session only when direct intervention is useful 00:00–01:03(opens in a new tab), 08:53–13:52(opens in a new tab).
- Reserve human attention for ambiguity: Kun describes his day as dumping thoughts into First Mate and handling decisions it cannot make. He says explicit escalation instructions keep autonomy from silently drifting in the wrong direction 21:01–22:47(opens in a new tab).
- Turn complex design reviews into interactive artifacts: For a workspace-organization decision, Lavish produces an HTML review and editable diagram. Kun can inspect alternatives and send a selected trade-off back to the agent 13:52–15:47(opens in a new tab), 18:53–21:01(opens in a new tab).
- Route models according to task and quota: First Mate follows rules for selecting models and reasoning levels. Kun tracks subscription limits and argues that background jobs need a cheaper slow mode rather than premium low latency 15:47–18:53(opens in a new tab).
- Validate changes through a separate pipeline: No Mistakes derives requirements from the original agent session, rebases, and performs adversarial review. It fixes clear defects or escalates product implications, then tests, checks documentation, and watches CI 37:41–41:34(opens in a new tab).
- Spend review effort according to risk: Kun treats validation as a cost of quality for production systems. He skips the heaviest process for some demos or simple changes. His dashboard attributes many caught issues to adversarial review and stale documentation 42:33–45:28(opens in a new tab).
- Build workflow tooling from observed bottlenecks: He says First Mate stopped setup work from consuming his product time. He says the broader toolchain emerged from concrete problems in coordinating sessions, reviewing generated code, and planning visually 45:28–49:36(opens in a new tab).
- Optimize interfaces for agents, not just humans: Kun expects more services to become headless. He presents benchmarks where CLI-shaped AXI wrappers reduce turns, latency, or token cost compared with the MCP interfaces he tested 49:36–56:47(opens in a new tab).
Full video: https://www.youtube.com/watch?v=8ZgpAXe5V5w(opens in a new tab)