“llm-agents”
Google ADK Workflows: From ReAct Loops to Graph Execution
How one ADK agent's think-act-observe loop generalizes into Sequential, Parallel and Loop agents, session state, and ADK 2.0 graph workflows.
Contract Testing Your Agents: Asserting Behavior Before Deployment
Stop asserting on prose. Define the inputs, tool schemas, output shapes, and side effects an agent must honor, then test those contracts deterministically in CI.
Metrics for Agent Health: Error Rates, Tokens, and Turn Length
A concrete OpenTelemetry metric set for LLM agents — golden signals, instrument choice, cardinality discipline, exemplars, and a dashboard layout you can ship.
Structured Outputs for Agents: JSON Schema Validation with Pydantic
Ensure reliable agent outputs with JSON Schema validation using Pydantic. Learn to define typed tool outputs, validate LLM responses, and build production-grade structured output pipelines.
Context Engineering: Managing What the Agent Sees
Master context engineering for LLM agents. Learn to control what information reaches the model, manage token budgets, and optimize context windows for better agent performance and lower costs.