# AI Agents: A Lead Engineer's Handbook

```{toctree}
:hidden:

ch1_intro
ch2_patterns
ch4_evals
ch5_context_engineering
ch6_case_studies
ch7_conclusion
ch_cost
ch_data
ch_deploy
ch_guardrails
ch_hitl
ch_latency
ch_llm
ch_memory
ch_monitor
ch_orchestration
ch_prod
ch_security
ch_tool
ch_trust
dd_evals
dd_agent_coding
```

##

**Foreword:** The shift from simple LLM calls to autonomous, reasoning systems. This guide provides a clear thinking framework for designing, building, and deploying production-grade AI agents, drawing from the industry's leading research and practical implementations.

___

- [Agent Fundamentals: What, Why, and When?](ch1_intro.md)
- [Agentic Patterns](ch2_patterns.md)
- [Evals](ch4_evals.md)
- [Context Engineering](ch5_context_engineering.md)
- [Industry Case Studies: Insights from the Field](ch6_case_studies.md)
- [Best Practices and Decision-Making Framework](ch7_conclusion.md)
- [Cost](ch_cost.md)
- [Data](ch_data.md)
- [Deploy](ch_deploy.md)
- [Guardrails](ch_guardrails.md)
- [HITL](ch_hitl.md)
- [Latency](ch_latency.md)
- [LLM](ch_llm.md)
- [Memory](ch_memory.md)
- [Monitor](ch_monitor.md)
- [Orchestration](ch_orchestration.md)
- [Prod](ch_prod.md)
- [Tools](ch_tool.md)
- [Trust](ch_trust.md)
- [Evals](dd_evals.md)
- [Coding Agents](dd_agent_coding.md)

___



<!--

___

- Intro: What, why, when ?
- Architecture Patterns
- AgentOps
    - [12-Factor Agents - Principles for building reliable LLM applications](https://github.com/humanlayer/12-factor-agents)
- Evals
- Context Engineering
- Industry Case Studies
- Frameworks
    - Langgraph [Building LangGraph: Designing an Agent Runtime from first principles](https://blog.langchain.com/building-langgraph/)
    - ADK
    - A2A
- Real World Products
    - Anthropic Deep Research, Microsoft Medical, Manus, Sakana AI, Google AlphaScientist
    - Oppo Guide
    - (https://blog.langchain.com/deep-agents/ - Langchain Deep Agents)
- Coding Agents
    - Theory
    - Gemini CLI Codebase
    - Claude Code: How to use
- RL Training of AI Agents
___


___



**Karpathy**
- [](https://youtu.be/LCEmiRjPEtQ?si=lKB4A79W8qiUZhNf)

**Context Engineering**
- [Context Engineering for Agents: Lance Martin](https://rlancemartin.github.io/2025/06/23/context_engineering/)
- [Cheatsheet] https://x.com/lenadroid/status/1943685060785524824/photo/1
- [Context Engineering for AI Agents: Lessons from Building Manus](https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus)

**Coding Agents**
- [Anthropic: Claude Code: Best practices for agentic coding](https://www.anthropic.com/engineering/claude-code-best-practices)

https://arxiv.org/pdf/2506.15741 - Oppo guide



**MCP**
- [Model Context Protocol (MCP) Tutorial: Build Your First MCP Server in 6 Steps](https://towardsdatascience.com/model-context-protocol-mcp-tutorial-build-your-first-mcp-server-in-6-steps/)

**Securing LLM Agents against Prompt Injections** 
- [Design Patterns for Securing LLM Agents against Prompt Injections](https://simonwillison.net/2025/Jun/13/prompt-injection-design-patterns/)


**Audio**
- [Advanced audio dialog and generation with Gemini 2.5](https://blog.google/technology/google-deepmind/gemini-2-5-native-audio/)

**Design Patterns**
- [Phil Schmid: Single vs Multi-Agent System?](https://www.philschmid.de/single-vs-multi-agents)
- [12-Factor Agents - Principles for building reliable LLM applications](https://github.com/humanlayer/12-factor-agents?ref=blog.langchain.com)

**Idea**
- [Document life, photo album, editing, music, styles/themes]

**Applications**
- [Gemini CLI](https://github.com/google-gemini/gemini-cli)
- [Anthropic: How we built our multi-agent research system](https://www.anthropic.com/engineering/built-multi-agent-research-system)
- [Microsoft: The Path to Medical Superintelligence](https://microsoft.ai/new/the-path-to-medical-superintelligence/)
- [Databricks: Introducing Agent Bricks: Auto-Optimized Agents Using Your Data](https://www.databricks.com/blog/introducing-agent-bricks)
- [I Copied the Multi-Agent Research System by Anthropic. No Coding!](https://www.productcompass.pm/p/multi-agent-research-system)

**Tools**
- [Writing effective tools for agents — with agents](https://www.anthropic.com/engineering/writing-tools-for-agents)
- [Web fetch tool](https://docs.claude.com/en/docs/agents-and-tools/tool-use/web-fetch-tool)

**Observability**
- [The Ultimate Guide to AI Observability and Evaluation Platforms](https://www.productcompass.pm/p/ai-observability-evaluation-platforms)


**Frameworks**
- [Building LangGraph: Designing an Agent Runtime from first principles](https://blog.langchain.com/building-langgraph/)
-->