In the news
When agents improve agents
Pydantic · David Sanchez · Published · 3 min read
In 30 seconds
- What happened
- Pydantic AI adds self-improving loops where agents check their own work, remember past runs, and keep going until goals are met, not just until plans run out.
- Why it matters
- Engineers building production AI systems need this when they want agents to iterate toward actual success rather than stopping after one attempt.
- Watch out
- LLM judges are unreliable graders prone to position bias and self-preference; calibration against humans and careful rubric versioning are essential, not optional.
Listen to this summary
- agent
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.