Google released Agents CLI v1.8.0 to optimize Agent quality
The story so far
Google has released Agents CLI v1.8.0, which implements Hill-Climbing optimization for Agent quality through commands like eval generate, eval grade, etc. Using the custom_response_quality metric to score 4 cases from 1 to 5, it was found that changing the system prompt word to a chef role resulted in an average score dropping from 4.0 to 2.75. This tool supports model backend experiments and automatic alerts, improving Agent performance through iterative cycles.
AI-written from the reports · Updated 21 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Google Developers BlogHill-Climbing Agent Quality with Agents CLI Evaluation
Agents CLI v1.8.0 achieves Hill-Climbing optimization of Agent quality through commands like eval generate, eval grade, etc., using the custom_response_quality metric to rate 4 cases from 1 to 5, finding that changing the system prompt to a chef role reduced the average score from 4.0 to 2.75. This tool supports model backend experiments and automatic alerts, improving Agent performance through iterative cycles.