CUSTOMISED
Expert-led training for your team
Dismiss

Building Production-Ready AI Agents training course

A hands-on course that takes you from core Python and LLM basics to designing, building & deploying production-grade AI agents with tools, memory, retrieval (RAG), multimodal capabilities, & multi-agent systems.

JBI training course London UK

"Our tailored course provided a well rounded introduction and also covered some intermediate level topics that we needed to know. Clive gave us some best practice ideas and tips to take away. Fast paced but the instructor never lost any of the delegates"

Brian Leek, Data Analyst, May 2022

Public Courses

11/05/26 - 3 days
£2500 +VAT
22/06/26 - 3 days
£2500 +VAT
03/08/26 - 3 days
£2500 +VAT

Customised Courses

* Train a team
* Tailor content
* Flex dates
From £1200 / day
EDF logo Capita logo Sky logo NHS logo RBS logo BBC logo CISCO logo
JBI training course London UK

  • Explore Python Fundamentals
  • Build an Agent Core
  • Work with LLMs
  • Create Conversational AI & Multimodal Apps
  • Build MCP Servers
  • Learn RAG Fundamentals
  • Design Multi-Agent Systems
  • Implement Agent Memory & Workflows
  • Work with Structured Facts
  • Develop Adaptive Retrieval
  • Handle Production Concerns
  • Use LangChain with Python
  • Build a Capstone Project

Module 1 — Python Fundamentals - Optional module.

  • Work fluently with Python data structures, modules/packages, CLI args, and logging.
  • Model domain objects with dataclasses and define contracts with Protocols.
  • Write async code: asyncio tasks, queues, timeouts, and cancellation.
  • Build and test a basic HTTP API with FastAPI and httpx.

Module 2 — Agent Core

  • Understand the message format that drives an agent (system, user, assistant, tool messages).
  • Build a tool-calling loop: schema in, action out, result back, repeat.
  • Implement a tool registry with schema validation, routing, and error handling.
  • Add safety rails (allowlists, rate limits, redaction) and an evaluation harness with golden tests.

Module 3 — Working with the LLM

  • Call the LLM chat-completion API directly — message roles, parameters, streaming.
  • Build a CLI chat loop with conversation history and a FastAPI streaming endpoint with SSE.
  • Implement session storage: in-memory first, then file-based.
  • Apply prompting patterns that hold up in production (structured outputs, grounding).

Module 4 — Conversational AI + Multimodal

  • Build a conversational AI application that integrates the agent core, LLM calls, and prompt engineering from earlier modules.
  • Apply prompt engineering: system prompts, few-shot examples, structured outputs, and grounding.
  • Work with multimodal inputs and outputs: vision/image analysis, speech-to-text, text-to-speech.
  • Add guardrails: model selection, token budgeting, content filters, and confidence thresholds.

Module 5 — MCP Servers

  • Understand MCP concepts: tool discovery, schemas, calling conventions.
  • Build a minimal MCP server in Python, then add practical tools.
  • Implement real-world tools: data lookups, queries, sensor reads.
  • Add per-tool auth scopes and structured logging for observability.

Module 6 — RAG Fundamentals

  • Design chunking strategies (size, overlap, structure-aware splits) for long documents.
  • Produce embeddings, store them in a vector index, and query effectively.
  • Apply retrieval strategies: hybrid search, metadata filters, reranking, and grounded answers with citations.
  • Run basic RAG evaluation: recall/precision on retrieval and adversarial queries.

Module 7 — Multi-Agent Systems

  • Decide when multi-agent designs are worth the latency and operational complexity.
  • Model roles (router, researcher, coder, critic) and coordination patterns (supervisor, swarm, debate).
  • Share context and tools safely across agents and apply conflict resolution / consensus strategies.

Module 8 — Agent Memory + Workflows

  • Implement short-term memory (conversation/session) separate from long-term profile or notes.
  • Apply summarisation to fit context limits; model decay and explicit "do not remember" controls.
  • Compare workflow patterns: ReAct, plan-and-execute, and tool routing for multi-step tasks.

Module 9 — Structured Facts

  • Use structured outputs (Pydantic models, JSON Schema) to get reliable, typed data from an LLM.
  • Build a fact extraction pipeline that decomposes text into individual claims with provenance.
  • Construct a knowledge graph from extracted entities and relationships.
  • Implement grounded QA that answers questions from the graph and cites source documents.

Module 10 — Adaptive Retrieval

  • Build a retrieval router that selects the right source (vector store, knowledge graph, keyword search) based on query type.
  • Implement query decomposition — breaking complex questions into focused sub-queries.
  • Add a self-critique loop (corrective RAG) that evaluates retrieved documents and re-retrieves when quality is low.
  • Orchestrate multi-source retrieval — merging results from different backends with relevance scoring.

Module 11 — Production Concerns

  • Add tracing and structured logging so every tool call is attributable and debuggable.
  • Define metrics and timelines that surface latency, errors, and dependency health.
  • Implement reliability (retries, timeouts, circuit breakers, fallbacks) and cost controls (caching, batching, token budgets).
  • Outline deployment: containers, running MCP alongside HTTP APIs, and config per environment.

Module 12 — LangChain with Python

  • Understand what LangChain provides vs building from scratch: chains, agents, tools, memory, and output parsers.
  • Rewrite a hand-rolled agent loop using LangChain components and compare the trade-offs.
  • Connect LangChain to an MCP server and RAG pipeline built in earlier modules.

Module 13 — Capstone Project

  • Build a full agentic application: chat UI or CLI, RAG, MCP tools, and a coordinated multi-agent path for complex questions.
  • Write demo scenarios and integration tests that guard against regressions.
  • Document extension points for adding tools, data sources, and policies.

 

JBI training course London UK

 
  • Developers who want to build AI-powered or agent-based applications
  • Python programmers looking to level up with LLMs and modern AI tooling
  • Backend or full-stack engineers interested in integrating AI into products
  • Data engineers and ML practitioners exploring practical LLM systems
  • Technical founders or product builders creating AI-driven solutions

 


5 star

4.8 out of 5 average

"Our tailored course provided a well rounded introduction and also covered some intermediate level topics that we needed to know. Clive gave us some best practice ideas and tips to take away. Fast paced but the instructor never lost any of the delegates"

Brian Leek, Data Analyst, May 2022



“JBI  did a great job of customizing their syllabus to suit our business  needs and also bringing our team up to speed on the current best practices. Our teams varied widely in terms of experience and  the Instructor handled this particularly well - very impressive”

Brian F, Team Lead, RBS, Data Analysis Course, 20 April 2022

 

 

JBI training course London UK

Newsletter


Sign up for the JBI Training newsletter to receive technology tips directly from our instructors - Analytics, AI, ML, DevOps, Web, Backend and Security.
 



This course teaches you how to design and build modern AI-powered applications using Python and large language models. You’ll learn how to create intelligent agents, integrate tools, and work with real-world data using techniques like RAG.

The curriculum covers everything from core fundamentals to advanced systems like multi-agent architectures and adaptive retrieval. You’ll also explore production-ready practices, including reliability, observability, and deployment strategies.


By the end, you’ll build a complete, agentic application that combines LLMs, APIs, and scalable workflows.

CONTACT
+44 (0)20 8446 7555

[email protected]

SHARE

 

Copyright © 2025 JBI Training. All Rights Reserved.
JB International Training Ltd  -  Company Registration Number: 08458005
Registered Address: Wohl Enterprise Hub, 2B Redbourne Avenue, London, N3 2BS

Modern Slavery Statement & Corporate Policies | Terms & Conditions | Contact Us

POPULAR

AI training courses                                                                        CoPilot training course

Threat modelling training course   Python for data analysts training course

Power BI training course                                   Machine Learning training course

Spring Boot Microservices training course              Terraform training course

Data Storytelling training course                                               C++ training course

Power Automate training course                               Clean Code training course