Part 10Agents & Tool Use
Building Tool-Using Agents That Work Reliably
Tool-use reliability is a systems property: tool design, a guarded control loop, permission gates, and pass^k evals on verifiable end states.
2 articles.
Part 10Agents & Tool Use
Tool-use reliability is a systems property: tool design, a guarded control loop, permission gates, and pass^k evals on verifiable end states.
Part 13Agents & Tool Use
Enforce JSON Schema at decode time, design schemas that keep quality high, and add validation, repair and truncation handling on top.