01
Agents with tools and MCP
Give an agent real tools through structured calls and Model Context Protocol servers.
live, online and hands-on
Tools, MCP, RAG, LangGraph, FastAPI, evaluation and deployment. Ten live sessions where you build and ship a working agent.
Overview
Three working systems, built live, each one a step closer to production.
Give an agent real tools through structured calls and Model Context Protocol servers.
Ground answers in your own data and orchestrate multi-step flows you can reason about.
Wrap the agent in FastAPI, test it with evaluations and deploy it.
Tech stack
Real, current tools used in production AI engineering. You install them once and use them in every session.
Python
The language for every session
Claude API
Model calls and tool use
Pydantic
Structured outputs and validation
MCP
Connect tools and data
Qdrant
Vector search for RAG
LangGraph
Multi-step agent workflows
FastAPI
Serve your agent as an API
pytest
Tests and evaluations
Docker
Package and deploy
Git
Version your work
Curriculum
How an agent decides, calls a tool and returns a result.
Schemas, validation and clear errors the agent can recover from.
Build and connect MCP servers and tools.
Chunking, embeddings and retrieval from your own documents.
Improve answer quality and measure it.
Model an agent as a graph of steps and state.
Memory, planning and handling failure across steps.
Serve your agent as an API.
Write evaluations and tests for agent behaviour.
Deploy, then review capstone projects together.
Draft outline. The final session plan is confirmed before each batch opens.
Outcomes
Running code you built yourself and can explain.
You know how tools, retrieval and workflows fit together.
An API with tests and evaluations around it.
A project reviewed by an engineer.
Who it is for
A good fit if you
Start with the workshop if you
Instructor
Rajath Kumar K S
Founder of Analog Data. Teaches AI engineering through live online cohorts and workshops.
How registration works
Choose Register. It opens a dedicated secure registration page.
Fill the form and pay on that page.
You receive confirmation and session details by email.
FAQs
On the cohort registration page. Every Register button opens it as a separate secure page.
Sessions are taught live online. Recording access, if any, is confirmed on the registration page.
Python 3.12 and a code editor. A setup guide is shared before the first session.
The price is shown on the page plus GST. The registration page lists exactly what it covers.
Yes. Ask for a GST invoice on the registration page, or contact us about team training.
Ready when you are
₹7,499 + GST · 25 hours live online · 7th to 18th Dec 2026, 7:00 PM to 9:30 PM IST, Monday to Friday, no weekends
₹7,499 + GST
Register ↗