Building Agentic AI From Workflows to Production

4+ Hours of Video Instruction

Build, evaluate, and scale production-ready AI agentsfrom simple workflows to multi-agent systems.

Overview

Building Agentic AI from Workflows to Production is a hands-on, code-driven course that goes from deterministic AI workflows to fully autonomous agents, multi-agent architectures, and multimodal systems.

Learn How To

• Build production-ready AI workflows with LangGraph and RAG
• Evaluate retrieval and generation quality using precision, recall, rubrics, and LLM-as-judge
• Convert workflows into ReAct agents with tool-calling LLMs
• Measure agent performance with explicit metrics (tool selection accuracy, cost per task) and implicit metrics (drop-off rate, user satisfaction)
• Architect multi-agent systems using sequential, aggregator, routing, supervisor, and any-to-any patterns
• Build an end-to-end multi-agent AI SDR with MCP and Docker
• Construct multimodal coding agents using Moondream for visual understanding
• Benchmark reasoning models and understand when extended thinking helps (and when it doesnt)
• Build computer-use agents and voice agents with real-time STT/TTS pipelines
• Implement long-term memory, compliance guardrails, and constitutional constraints
• Scale agentic systems from MVP to enterprise using the autonomycostcontrol framework

Who Should Take This Course

Developers, data scientists, ML engineers, and technical product managers who want to build, evaluate, and deploy intelligent AI agents. This course is ideal for practitioners who have experimented with LLM APIs and want to move beyond prototyping into reliable, cost-effective production systems.

Course Requirements

• Python 3 proficiency and comfort with interactive environments (Jupyter, Google Colab, or similar)
• Basic familiarity with LLM APIs (such as OpenAI, Anthropic, or open-source models)
• Understanding of core concepts like embeddings, vector databases, and prompt engineering (helpful but not required; these are covered as they arise)

Lesson Descriptions

Lesson 1: Production-Ready AI Workflows

This lesson establishes the foundation: what AI workflows are, how they differ from agents, and why evaluation should be built in from the start. Youll build a complete text-to-SQL workflow with RAG using LangGraph and the BIRD benchmark dataset, indexing evidence into a vector database, retrieving relevant context via embedding similarity, and generating SQL queries from natural language. Youll then evaluate retrieval quality with precision and recall, test SQL correctness against ground truth, and compare six LLMs head-to-head on accuracy, latency, cost, and success rate.

Lesson 2: From Workflows to Agents

Youll convert the text-to-SQL workflow from Lesson 1 into a fully autonomous ReAct agent equipped with three tools: evidence lookup, SQL execution, and schema retrieval. Along the way, youll learn how tool-calling LLMs work, how agents reason in loops, and how real-world agents like ChatGPT are structured. A major focus is evaluation: youll measure agents using explicit metrics (tool selection accuracy, cost per task, token efficiency) and implicit metrics (drop-off rate, copy rate), and apply rubric-based LLM grading.

Lesson 3: Agentic Systems in Practice

When a single agent isnt enough, you need multi-agent architectures. This lesson covers six design patterns: sequential, aggregator, routing, any-to-any, supervisor, and supervisor (tool-calling) with the tradeoffs of each. Youll build a complete multi-agent AI SDR (sales development representative) using MCP and Docker, with agents handling web research, CRM actions, and email outreach. Youll also run agent prompt-engineering experiments on an Airbnb policy compliance dataset, discovering that a single two-sentence prompt addition can dramatically improve tool use and accuracy. The lesson closes with a deep-research hybrid workflow combining planning agents, replanning, and agentic execution.

Lesson 4: Multimodal, Reasoning, and Coding Agents

This lesson moves beyond text. Youll build coding agents where tool calls are raw Python code rather than JSON payloads, using Moondream for visual understanding. Youll benchmark reasoning models and see how reasoning might sometimes improve accuracy on visual tasks but at significant speed and cost tradeoffs. Youll construct a computer-use agent using both multimodal and DOM-grounded approaches, and build a production voice agent with Twilio, Groq Whisper, Llama-4-Scout, and TTS.

Lesson 5: Future Directions in Agentic AI

The final lesson tackles what it takes to run agents in production at scale. Youll implement long-term memory architectures inspired by the Extended Mind Thesis, giving agents a notepad tool and measuring whether self-recorded learnings improve future performance (they do). Youll explore the three layers of guardrails (input, prompt, output), implement constitutional constraints, and examine MCP security risks including tool poisoning and command injection.

Resources

https://github.com/sinanuozdemir/building-agentic-ai

About Pearson Video Training

Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, and Que. Topics include IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at http://www.informit.com/video.