3 Weekend Bootcamp + guided practical assignment
+ Professional Certificate from IIT Hyderabad
Build AI Agents That Actually Work
A hands-on professional certification program for those who want to design, build, evaluate, and operate production-grade AI agent systems.
Designed for what professionals need in 2026
Program fees
Early Bird
₹20,000*
Available for the first 30 participants
Standard
₹25,000*
Regular registration
* Exclusive of taxes
Note:
- Corporate group registrations are eligible for additional discounts. Contact us to check eligibility and avail discounted pricing.
- Accommodation available upon request at an additional nominal cost.
Why this program
Most AI courses teach prompts. Our program teaches AI engineering.
Learners build the runtime patterns now expected in applied AI teams: tool use, retrieval, memory, orchestration, guardrails, tracing, and continuous improvement.
Production-first
Move beyond prompting into reliable, observable, scalable, and production-ready AI agent engineering.
Guided practicals
Participants complete guided assignments between classroom sessions with live mentoring, code reviews, and final demonstrations.
Built for professionals
Designed for software engineers, data scientists, full stack developers, AI enthusiasts with Python experience.
State-of-the-art stack
Use practical tools and frameworks including LangChain, LangGraph, Qdrant, LangFuse, and Model Context Protocol.
IIT Hyderabad Recognition
Professional certification awarded to participants who successfully complete the assessments.
3-week program schedule
Focused lectures, deep labs, and a single connected build.
01 August (Saturday)
In person @ IITH Campus
Foundations of Reliable AI Agents
LLM runtime, structured outputs, tools, and single-agent control loops.
Lectures
- How agentic systems differ from simple chatbots
- Model selection, context windows, tokens, sessions, and state
- Structured outputs with Pydantic and schema validation
- Native tool calling, retries, rate limits, callbacks, and failure recovery
Hands-on labs
- Build a raw Python LLM client with session state
- Convert messy business emails into typed JSON objects
- Implement a tool-calling loop with exception handling and retry logic
02 August (Sunday)
In person @ IITH Campus
Knowledge, Memory, and Production RAG
Embeddings, vector stores, retrieval quality, and memory design.
Lectures
- Semantic search, embeddings, vector spaces, and similarity
- Chunking, metadata filters, reranking, and query expansion
- Short-term memory, long-term memory, and session continuity
- Prompt injection risk in RAG and defensive retrieval patterns
Hands-on labs
- Spin up Qdrant or Chroma locally and run metadata-filtered queries
- Build a RAG assistant over policy and operations documents
- Add memory summaries and evaluate retrieval precision
03-07 August
Online
Project Development Week
Guided online learning, project development, and mentor support.
08 August (Saturday)
In person @ IITH Campus
Graph-Based Multi-Agent Systems
LangGraph orchestration, checkpoints, plugins, skills, and human review.
Lectures
- When to use one agent versus many agents
- Supervisor, choreography, planner-executor, reflection, and review patterns
- LangGraph state, edges, checkpoints, breakpoints, and resumability
- MCP, plugins, skills, and safe enterprise tool integration
Hands-on labs
- Build a researcher-writer-reviewer workflow in LangGraph
- Add checkpointing and resume a paused workflow
- Expose a local business API or file tool through an MCP-style interface
09 August (Sunday)
In person @ IITH Campus
Evaluation, Observability, and Launch Readiness
Tracing, guardrails, deployment patterns, and continuous improvement.
Lectures
- Why agent evaluation differs from model evaluation
- Component tests for tools, retrieval, memory, planning, and final answers
- LangFuse tracing, cost tracking, latency, and failure analysis
- Guardrails, human-in-the-loop approvals, monitoring, and improvement loops
Hands-on labs
- Instrument an agent workflow with LangFuse traces
- Create evaluation cases for hallucination, retrieval misses, and tool failures
- Package the final app with FastAPI and a lightweight deployment checklist
10-14 August
Online
Project Development Week
Guided online learning, project development, and mentor support.
15-16 August
Hybrid
Final Weekend
Project demonstrations, presentations, feedback, and award of the IIT Hyderabad Professional Certificate to participants who successfully complete the program.
Technologies covered
SOTA stack, practical by default.
The program keeps vendor lock-in low while teaching patterns that transfer across model providers and enterprise stacks.
LangChain
LangGraph
Qdrant
LangFuse
Model Context Protocol
Long-Term Memory
Enterprise RAG
Multi-Agent Collaboration
Evaluation Pipelines
Guardrails
Guided industry practical experience
Build one end-to-end production AI application.
Throughout the program, participants progressively build one production-ready AI agent application. Each module extends the same codebase with structured outputs, tool calling, memory, enterprise RAG, multi-agent workflows, observability, evaluation, guardrails, and production reliability patterns.
- Implement structured outputs and tool calling in a production-style AI agent application.
- Add long-term memory and enterprise RAG over relevant knowledge sources.
- Build multi-agent collaboration and LangGraph workflows.
- Integrate MCP, observability, evaluation pipelines, guardrails, and reliability patterns.
- Demonstrate the final solution, submit source code, and receive feedback.
Learning outcomes
Participants leave with production instincts, not isolated notebooks.
Design
Choose the right agent architecture, decide when to use RAG, select memory strategies, and design reliable tools.
Build
Create production-ready AI agents, tool-enabled applications, multi-agent workflows, MCP servers, and enterprise RAG systems.
Deploy
Debug AI agents, observe execution using LangFuse, evaluate quality, handle retries and failures, and secure applications.
Demonstrate
Complete the guided practical assignment, submit source code, and present the final solution for certification.
Certify
Demonstrate your proficiency through an IIT Hyderabad Professional Certificate that reflects successful completion of the program and its assessments.
Who should attend
Built for practitioners who already understand the basics of LLMs.
AI Enthusiasts
Software Engineers
Data Scientists
Full Stack Developers
AI Engineers
Solution Architects
Prerequisites
- Python basics
- REST API familiarity
- Beginner-level Generative AI awareness
No prior LangGraph or LangChain experience required.
Meet your instructors
Academic rigor meets real-world industry practice.
Dr. Praveen Tammana
Faculty Lead
Assistant Professor, CSE, IIT Hyderabad
An applied researcher specialising in AI and Computer Systems, Dr.Praveen combines cutting-edge research with engineering rigor to help participants build robust, production-ready AI systems. Prior to joining academia, he worked with leading global technology companies including Cisco Systems, Intel, and Juniper Networks, bringing valuable industry experience in designing large-scale computing and networking systems.
As Academic Lead of the Applied AI Professional Program, he brings a systems-first perspective to the architecture of production-ready AI applications, enabling participants to build scalable, reliable, secure, and enterprise-deployable AI solutions.
- Postdoc, Princeton University
- Ph.D., University of Edinburgh
- Masters, IIT Madras
- 40+ Publications
- 847+ Citations
- Certificate of Teaching Excellence Award, IIT-H (2021–22)
N. V. S. S. Koundinya
Industry Lead
AI Solution Architect
Specializes in architecting production-ready AI systems that combine the latest advances in Generative AI, Agentic AI, Machine Learning, LLM Engineering, RAG, and MLOps with enterprise software engineering principles. His work focuses on building scalable AI applications that move beyond prototypes into real-world business solutions. For over six years, he has actively mentored students, and working professionals, in designing and deploying production-ready AI systems.
As Industry Lead of the Applied AI Professional Program, Koundinya brings hands-on expertise in building reliable AI agents, enterprise AI workflows, and production-grade AI applications using the latest open-source frameworks and engineering best practices.
- BITS Pilani Graduate
- 8+ Years in AI/ML
- Enterprise AI Architect
- Patent Holder
- 16 Publications
FAQ
Clear expectations before enrollment.
Do learners need prior LangChain experience?
No. Participants should have working knowledge of Python, familiarity with REST APIs, a basic understanding of LLMs and Generative AI, and experience using OpenAI-compatible APIs.
Is this mostly theory?
No. The program is hands-on first, with instructor-led sessions, guided practical assignments, live mentoring, code reviews, and final demonstrations.
Will MCP, checkpoints, retries, and callbacks be covered?
Yes. These are included because today's agent systems need reliable tool integration, stateful execution, and observable runtime behavior.
What do participants leave with?
A cohesive production-style AI agent application, source code, evaluation artifacts, presentation feedback, and a certificate after meeting the certification criteria.
Will I receive a certificate?
Participants who successfully complete the program requirements will receive an IIT Hyderabad Professional Certificate.
Contact us
Questions before you register?
Reach out to us for queries, bulk registrations, and accommodation-related concerns.
1 August - 16 August
Register for the Applied AI Professional Certification Program.
Accommodation: Limited on-campus accommodation at IIT Hyderabad may be available on a request basis, subject to availability. Accommodation charges are separate from the program registration fee.