“function-calling”
Versioning Tools: Backward-Compatible Function Evolution for Agents
Treat LLM function-calling tool schemas as a public API you cannot break — additive-only evolution rules, deprecation with dual registration, model behavior on schema changes, and golden tool-call fixtures that catch regressions before deploy.
Tool-Selection Evals: Verifying the Agent Picks the Right Tool
Build eval suites that verify your agent selects the correct tool for each task, with precision metrics, confusion matrices, and regression testing for tool selection.
Function Calling and Structured Output for On-Device Agents with Gemma 4
Make on-device agents reliable with Gemma 4 function calling and constrained decoding. Learn structured output patterns, parse-error fallbacks, and how to build a trustworthy tool-calling loop with LiteRT-LM.
Tools, Function Calling, and the Agent Execution Loop
The agent loop is a model deciding which tools to call, observing results, and iterating. Learn function declarations, tool_choice modes, and parallel calling.