# Building Reliable Agents

## Docs

- [Agent Version History](https://mintlify.wiki/langchain-ai/lca-reliable-agents/agents/agent-versions.md): Progressive improvements to the OfficeFlow agent from v0 to v5
- [Analyzing Agent Behavior](https://mintlify.wiki/langchain-ai/lca-reliable-agents/agents/analyzing-agents.md): Use LangSmith traces to understand and improve agent performance
- [OfficeFlow Agent Overview](https://mintlify.wiki/langchain-ai/lca-reliable-agents/agents/officeflow-overview.md): Meet Emma, the AI customer support agent for OfficeFlow Supply Co.
- [Agent Implementation](https://mintlify.wiki/langchain-ai/lca-reliable-agents/api/python/agent.md): Python agent implementation reference for building conversational AI agents with tool calling and conversation history
- [Evaluator Functions](https://mintlify.wiki/langchain-ai/lca-reliable-agents/api/python/evaluators.md): Python evaluator function reference for testing and validating agent behavior
- [Tool Functions](https://mintlify.wiki/langchain-ai/lca-reliable-agents/api/python/tools.md): Python tool function reference for database queries and knowledge base search
- [Agent Implementation](https://mintlify.wiki/langchain-ai/lca-reliable-agents/api/typescript/agent.md): TypeScript agent implementation reference for building conversational agents with tools and memory
- [Evaluator Functions](https://mintlify.wiki/langchain-ai/lca-reliable-agents/api/typescript/evaluators.md): Reference for evaluation functions used to assess agent performance and behavior
- [Tool Functions](https://mintlify.wiki/langchain-ai/lca-reliable-agents/api/typescript/tools.md): Reference for agent tool functions including database queries and knowledge base search
- [Evaluation Strategies for AI Agents](https://mintlify.wiki/langchain-ai/lca-reliable-agents/concepts/evaluation.md): Learn how to systematically measure and improve agent quality using datasets, experiments, and automated evaluators
- [Why Observability Matters for AI Agents](https://mintlify.wiki/langchain-ai/lca-reliable-agents/concepts/observability.md): Understanding the unique challenges of debugging AI agents and how observability tools provide visibility into non-deterministic systems
- [LangSmith Tracing Fundamentals](https://mintlify.wiki/langchain-ai/lca-reliable-agents/concepts/tracing.md): Learn how to instrument your AI agents with LangSmith tracing to capture every LLM call, tool invocation, and decision
- [Code-based Evaluators](https://mintlify.wiki/langchain-ai/lca-reliable-agents/evaluation/code-based.md): Write deterministic evaluators that check agent behavior like unit tests
- [Creating Test Datasets](https://mintlify.wiki/langchain-ai/lca-reliable-agents/evaluation/datasets.md): Build robust test datasets for systematic agent evaluation
- [Running Experiments](https://mintlify.wiki/langchain-ai/lca-reliable-agents/evaluation/experiments.md): Execute evaluation experiments to measure agent performance systematically
- [LLM-as-Judge Evaluation](https://mintlify.wiki/langchain-ai/lca-reliable-agents/evaluation/llm-judge.md): Use language models to evaluate subjective criteria that are hard to check with code
- [Pairwise Comparison Evaluation](https://mintlify.wiki/langchain-ai/lca-reliable-agents/evaluation/pairwise.md): Compare two agent versions side-by-side to measure which performs better
- [Building Reliable Agents](https://mintlify.wiki/langchain-ai/lca-reliable-agents/introduction.md): Master the art of building, observing, evaluating, and deploying production-ready AI agents with LangSmith
- [Online Evaluation for Production Agents](https://mintlify.wiki/langchain-ai/lca-reliable-agents/production/online-evals.md): Implementing continuous evaluation pipelines for production agent systems
- [Moving Agents to Production](https://mintlify.wiki/langchain-ai/lca-reliable-agents/production/overview.md): Transitioning reliable agents from development to production environments
- [Uploading Traces at Scale](https://mintlify.wiki/langchain-ai/lca-reliable-agents/production/trace-upload.md): Production-grade trace upload patterns for LangSmith and observability platforms
- [Python Setup](https://mintlify.wiki/langchain-ai/lca-reliable-agents/setup/python.md): Complete guide to setting up the Python environment for the Building Reliable Agents course
- [TypeScript Setup](https://mintlify.wiki/langchain-ai/lca-reliable-agents/setup/typescript.md): Complete guide to setting up the TypeScript environment for the Building Reliable Agents course