Optimize agent promptsStay organized with collectionsSave and categorize content based on your preferences.
TheQuality
Flywheelis a continuous cycle of evaluation, analysis, and optimization. You
evaluate your agent's performance, analyze the results to identify clusters of
failures, and then optimize to address those
specific issues. Each iteration improves agent quality.
The Agent Development Kit (ADK) provides an extensible framework for automated agent optimization. Automate agent optimization using the ADK's built-inadk optimizecommand. This command applies theGEPA algorithmto iteratively refine root system instructions by evaluating them against your test suite.
The framework is extensible: you can implement custom optimization strategies, or develop custom samplers that integrate with your own evaluation pipelines.
For more details on how to get started with optimizing agents using ADK, seeOptimize agentsin ADK's documentation.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-04-27 UTC."],[],[]]
