{"product_id":"building-ai-agents-in-21-mohammad-saqib-9798184567396","title":"Building AI Agents in 21 Days: A Hands-On Course in Agentic Systems with Python and LLMs","description":"Building AI Agents in 21 Days\u003cbr\u003eA Hands-On Course in Agentic Systems with Python and LLMs\u003cbr\u003eby M. Saqib \u003cp\u003e\u003c\/p\u003e================================================================\u003cbr\u003eGo from a single line that calls a language model to a deployed, \u003cbr\u003eautonomous agent that plans, uses tools, checks its own work, and\u003cbr\u003erecovers from failure - in three focused weeks.\u003cbr\u003e================================================================ \u003cp\u003e\u003c\/p\u003eMost \"AI agent\" books hand you a framework and a magic import. You\u003cbr\u003eend up with a demo you can't debug and only a hazy idea of what the\u003cbr\u003eagent actually does. This book is the opposite. You build the agent\u003cbr\u003eyourself, from the loop up, in plain Python - so when something\u003cbr\u003ebreaks, you know exactly why. \u003cp\u003e\u003c\/p\u003eYou call Claude through the official Anthropic Python SDK and write\u003cbr\u003eevery part by hand: the control loop, the tools, memory, retrieval, \u003cbr\u003eplanning, guardrails, and the deployment around it. Frameworks like\u003cbr\u003eLangGraph and CrewAI are explained so you can read them - but you\u003cbr\u003enever hide behind one. By Day 21 an agent is no longer magic. It is\u003cbr\u003esomething you can build, measure, and ship. \u003cp\u003e\u003c\/p\u003e\u003cb\u003eWHAT YOU GET\u003c\/b\u003e\u003cbr\u003e- 21 day-chapters (3 weeks x 7 days) of careful, worked teaching -\u003cbr\u003eno filler, no hand-waving.\u003cbr\u003e- 150+ runnable Python listings with real output.\u003cbr\u003e- 246 figures and diagrams - loop diagrams, sequence diagrams, and\u003cbr\u003emeasured plots.\u003cbr\u003e- A clean, print-friendly layout, and a per-day workshop (quiz and\u003cbr\u003eexercises) so each idea lands in your hands. \u003cp\u003e\u003c\/p\u003e\u003cb\u003eTHE 21 DAYS\u003c\/b\u003e\u003cbr\u003eWeek 1 - Foundations\u003cbr\u003e Day 1. What Is an Agent? The Loop That Thinks\u003cbr\u003e Day 2. Tool Calling - Giving the Model Hands\u003cbr\u003e Day 3. The Agent Loop\u003cbr\u003e Day 4. ReAct - Reasoning Before Acting\u003cbr\u003e Day 5. Memory \u0026amp; the Context Window\u003cbr\u003e Day 6. Structured Output You Can Trust\u003cbr\u003e Day 7. Errors, Timeouts, and a Resilient Loop\u003cbr\u003eWeek 2 - Capability\u003cbr\u003e Day 8. Designing Tools the Model Can Use\u003cbr\u003e Day 9. Retrieval as a Tool (RAG)\u003cbr\u003e Day 10. Planning vs. Reacting\u003cbr\u003e Day 11. Multi-Step Tasks \u0026amp; Working State\u003cbr\u003e Day 12. Self-Correction \u0026amp; Reflection\u003cbr\u003e Day 13. Cost and Latency Budgeting\u003cbr\u003e Day 14. Tracing and Observability\u003cbr\u003eWeek 3 - Robustness and Scale\u003cbr\u003e Day 15. Evaluating Agents\u003cbr\u003e Day 16. Guardrails and Safety\u003cbr\u003e Day 17. Human in the Loop\u003cbr\u003e Day 18. Multi-Agent Orchestration\u003cbr\u003e Day 19. Long-Running \u0026amp; Background Agents\u003cbr\u003e Day 20. Deploying an Agent\u003cbr\u003e Day 21. Capstone - A Complete Agent, End to End \u003cp\u003e\u003c\/p\u003e\u003cb\u003eWHO IT'S FOR\u003c\/b\u003e\u003cbr\u003eYou know ordinary Python - functions, dictionaries, exceptions. You\u003cbr\u003edo NOT need any machine-learning background, and you will not train a\u003cbr\u003emodel; you call one and build the system around it. You need an\u003cbr\u003eAnthropic API key; each call costs a fraction of a cent, and the\u003cbr\u003ewhole book runs for about the price of a coffee. \u003cp\u003e\u003c\/p\u003e\u003cb\u003eBY DAY 21 YOU CAN\u003c\/b\u003e\u003cbr\u003e- build the agent loop that calls a model, runs its tools, and feeds\u003cbr\u003ethe results back until the task is done;\u003cbr\u003e- design tools, schemas, and structured output the model uses well;\u003cbr\u003e- ground an agent's answers in your own documents with retrieval;\u003cbr\u003e- make an agent plan, reflect, and correct itself;\u003cbr\u003e- measure and cut what every run costs in tokens and time;\u003cbr\u003e- evaluate an agent like code, guard it against bad input and prompt\u003cbr\u003einjection, and deploy it as a real service. \u003cp\u003e\u003c\/p\u003eThe agent stops being a black box. Go build one that works.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eAuthor:\u003c\/b\u003e Mohammad Saqib\u003cbr\u003e\u003cb\u003eISBN-13:\u003c\/b\u003e 9798184567396\u003cbr\u003e\u003cb\u003ePublisher:\u003c\/b\u003e Independently Published\u003cbr\u003e\u003cb\u003eLanguage:\u003c\/b\u003e English\u003cbr\u003e\u003cb\u003ePublished:\u003c\/b\u003e 06\/27\/2026\u003cbr\u003e\u003cb\u003ePages:\u003c\/b\u003e 498\u003cbr\u003e\u003cb\u003eFormat:\u003c\/b\u003e Paperback\u003cbr\u003e\u003cb\u003eWeight:\u003c\/b\u003e 1.88lbs\u003cbr\u003e\u003cb\u003eSize:\u003c\/b\u003e 10.00h x 7.00w x 1.00d","brand":"Mohammad Saqib","offers":[{"title":"Paperback","offer_id":48853046296831,"sku":"9798184567396","price":29.99,"currency_code":"USD","in_stock":true}],"url":"https:\/\/www.whiterainbookhouse.com\/products\/building-ai-agents-in-21-mohammad-saqib-9798184567396","provider":"WR Book House","version":"1.0","type":"link"}