AI Agents: No Excuse for Lack of Rigor
Anker Goyel and Claire Vo reveal how AI agents are rewriting the rules for database optimization and high-risk infrastructure refactoring, pushing the boundaries of engineering rigor.
How this startup uses AI agents to eliminate bugs and optimize infrastructure
With Claire Vo, Anker Goyel · Sunday, June 21, 2026
Claire Vo and Anker Goyel discuss how AI agents are transforming software engineering, particularly for complex infrastructure and database optimization. Goyel highlights the importance of rigorous evals as a modern approach to product requirements and quality, emphasizing a shift to a "maker schedule" by leveraging agents for tedious tasks and even "quantifying taste" to scale design quality. The conversation also touches on achieving backlog zero and the critical role of continuous integration in an AI-driven development environment.
Key takeaways
- AI agents are solving deep technical challenges like database query optimization by exhaustively trying different column store formats and execution engines, a task impractical for humans. Read more →
- AI agents eliminate excuses for product backlogs. Anker Goyel states, "there's just no excuse to not have rigor... we don't really have a backlog," meaning every "paper cut" or performance issue gets addressed immediately. Read more →
- Machine learning fundamentally changes programming from defining how to build something, to defining what the successful outcome looks like. Read more →
- Re-evaluate your time now: Anker Goyel argues many daily interactions, directions, and decisions made by engineers (and founders) fall "below the agent line" and can be delegated to AI. This isn't theoretical; it's a call to audit your current workload. Read more →
4 articles from this episode
AI Engineering: No Excuse for Backlog Zero
Anker Goyel outlines how AI agents transform software engineering, enabling 'no excuse' quality, backlog zero, and a shift from constructing to carving products with rigorous CI and feedback loops.
AI Evals Are Modern PRDs: Quantify Design Taste with Anker Goyel's Method
Stop writing generic PRDs. Anker Goyel explains how AI evals define success with examples, and his 'Quantifying David' method scales expert design taste for higher product quality.
Anker Goyel's 'Agent Line': Reclaim Your Maker Schedule with AI
Anker Goyel's 'Agent Line' framework helps founders delegate tasks to AI, shifting from 'manager' to 'maker' work. Learn to apply it this week.
More How I AI episodes
- Stripe built a company brain: Meet KaiSep 13 · 5 articles
- GPT-6 Astra blew away every one of my benchmarksSep 6 · 5 articles
- 7 Grok Bot agents I use every daySep 6 · 5 articles
- I built a Claude Cowork system that does a week of PM work in a daySep 6 · 5 articles