Manas Dasgupta
AI trainer · Author · 10,000+ professionals taught

Learn to build AI agents and LLM systems that work in production.

Hands-on courses in Generative AI, RAG, multi-agent orchestration, LangChain, LangGraph, MCP, AI evaluations and LLMOps. Taught by Manas Dasgupta to 10,000+ AI professionals across 60+ countries.

Browse courses See the learning track
Manas Dasgupta, AI trainer and author
Manas DasguptaAI Trainer · Author

10,000+ learners · 60+ countries

In one paragraph

Manas Dasgupta is an AI trainer and author who teaches engineers to build production AI systems: LLM applications, RAG with hybrid search and vector databases, AI agents and multi-agent orchestration with LangChain, LangGraph, OpenAI Agents SDK, MCP and CrewAI, plus evaluations, LLMOps and guardrails. He has taught 10,000+ AI professionals across 60+ countries.

For
Software engineers, data professionals and ML engineers moving into AI engineering
Time
Self-paced courses with hands-on projects
Next step
Start the learning track

Courses authored for

10,000+ AI professionals taught
60+ Countries
8 Publishers and platforms authored for
The learning track

From your first LLM call to production multi-agent systems

Four stages, in the order AI engineering teams build: models first, then knowledge, then agents, then everything that keeps them reliable in production.

All courses
  1. Stage 1 · Foundations

    Generative AI and large language models

    How LLMs work, prompting, structured outputs and tool calling: the base every AI application stands on.

    • Generative AI
    • Large Language Models (LLMs)
    • Prompting
    • Tool calling
  2. Stage 2 · Knowledge systems

    RAG, hybrid search and vector databases

    Ground model answers in your own data with retrieval pipelines that are accurate, fast and explainable.

    • RAG
    • Hybrid search
    • Vector databases
    • Knowledge systems
  3. Stage 3 · Agents

    AI agents and multi-agent orchestration

    Design agent architectures, connect tools through MCP and orchestrate teams of agents with the major frameworks.

    • LangChain
    • LangGraph
    • OpenAI Agents SDK
    • MCP
    • CrewAI
    • Flowise
  4. Stage 4 · Production

    Evaluations, LLMOps, observability and guardrails

    Measure quality, monitor cost and behaviour, and secure AI systems against misuse before and after launch.

    • AI evaluations
    • LLMOps
    • Observability
    • Security & guardrails
Courses

Courses

Courses on Udemy, Coursera, O'Reilly, Packt, Pearson and more, in one place. Click a course for the syllabus; enrol on the platform.

All courses
Corporate training

Trusted to train teams at ABB, TIAA, EY and more

13 corporate and industry programs in Generative AI and Agentic AI, for engineering teams, business functions, HR and leadership.

Corporate training
Programs delivered for
  • ABB
  • Hector Beverages (Paper Boat)
  • Digit Insurance
  • TIAA (Teachers Insurance)
  • BCIC
  • NHRD
  • EY
  • NHRD Delhi NCR
  • UpGrad
  • TNS Foundation
  • Smartsheet
ABB · Sweden

Generative AI for Engineers

TIAA (Teachers Insurance) · United States

Generative AI for IT Executives

EY

AI Leadership for CHROs

Delivered through EY

Smartsheet

Use-case-driven Application of Agentic AI and AI in Talent Acquisition

For your organisation

Train your team on Generative AI and Agentic AI

Programs for engineers, business functions, HR and leadership, built around your team's own use cases.

See the training tracks Contact us
Watch

Latest videos

Every video is summarised in text, with key points and chapters.

All videos

Write the evaluation before the feature

An evaluation set is a list of real inputs with the answers you expect. Building it before the feature forces the team to agree on what...

In AI Engineering · 10 Sep 2026

Should this feature use AI? A one-page test

Most features that teams want to build with AI do not need it. This video walks through a one-page test: is the task tolerant of...

In AI Engineering · 1 Sep 2026

Channel trailer: what this channel covers

A two-minute introduction to the channel: short, answer-first videos on AI product development and technology leadership, each built...

Channel · 1 Aug 2026
Read

Latest writing

All articles
Answers

Questions people ask

Short, direct answers. Each links to a page with the detail.

All answers

What is AI product development?

AI product development is the practice of building product features whose behaviour depends on a machine-learning model, usually a language model. It differs from ordinary product work in three ways: output is probabilistic, quality must be measured with evaluations, and launch plans need guardrails for wrong answers.

Full answer

How do you evaluate an LLM feature before launch?

Build an evaluation set of at least 50 real inputs with expected outputs, grade responses with a mix of exact checks, model-based graders and human review, and set a pass threshold before launch. Run the same set on every prompt or model change so regressions are caught before users see them.

Full answer

Does Manas Dasgupta deliver corporate AI training?

Yes. Manas Dasgupta designs and delivers corporate programs in Generative AI and Agentic AI for technical teams, business functions, HR and leadership. Clients include ABB in Sweden, TIAA in the United States, Digit Insurance, Hector Beverages (Paper Boat), EY and Smartsheet, with industry programs through NHRD and BCIC. Send your team size and goals for a proposal.

Full answer
Course
Open full page ↗