Agentic AI with LangChain & LangGraph
Build tool-using agents and stateful workflows with LangChain and LangGraph, with evaluation and guardrails.
- ✓ Instructor-led live sessions, online or in Bengaluru
- ✓ Hands-on labs in every module
- ✓ Capstone project with trainer review
- ✓ Curriculum customisable for corporate teams
- ✓ Certificate of completion
Next batch: Sat, 05 Dec 2026 · 38 hours · 5 days
Agentic AIAgentic AI with LangChain & LangGraph
Duration: 38 hours · 5 days
Next batch: Sat, 05 Dec 2026
Format: Online live · Bengaluru classroom
Modules: 9 · Topics: 42
Level: Intermediate to Advanced
Fee: ₹17,999
Trusted by leading experts
Upcoming batches
Open batches for individuals; corporate batches on your dates.
| Programme | Starts | Mode | Schedule | Duration | |
|---|---|---|---|---|---|
| Agentic AI with LangChain & LangGraph | Sat, 05 Dec 2026 | Online live | Weekend (Sat) | 6 Saturdays | Enquire |
| Agentic AI with LangChain & LangGraph | Mon, 11 Jan 2027 | Online live | Weekday | 5 days | Enquire |
| Agentic AI with LangChain & LangGraph | Sat, 27 Feb 2027 | Online live | Weekend (Sat) | 6 Saturdays | Enquire |
Soaring demand, and where it takes you
Agentic AI is one of the fastest-moving areas of enterprise AI, and developers who can build controllable, testable agents are sought after.
Become an expert
Roles this programme prepares you for:
Become a Agentic AI Developer
Builds tool-using agents and agent workflows.
- Explain the agent loop and tool calling
- Use LangChain models, prompts, retrievers and tools
- Build stateful agent workflows as LangGraph graphs
About the course
A developer course on building AI agents with LangChain components and LangGraph orchestration: tool calling, stateful graphs, memory, human approval steps, tracing and evaluation. Participants build agents that complete real multi-step tasks.
Build tool-using agents and stateful workflows with LangChain and LangGraph, with evaluation and guardrails.
Why should I attend?
Python developers
Backend and integration engineers
ML engineers moving into agents
Technical leads evaluating agent frameworks
Prerequisites
Python (classes, async basics); experience calling an LLM API; JSON and REST familiarity
Level
Intermediate to Advanced
Delivery modes, duration and fee
Online live
Instructor-led virtual classroom; weekday (full-day) or weekend (Saturday) batches
Bengaluru classroom
In-person batches at our Bengaluru training venue
On-site at your office
Private corporate batch anywhere in India, scheduled around your teams
Blended
Live sessions plus guided self-paced labs and mentor check-ins
Duration: 38 hours · 5 days
Course fee (open batch): ₹17,999
Corporate / team batches: per-participant or flat batch pricing on request, based on group size, format and customisation.
What will you learn
- Explain the agent loop and tool calling
- Use LangChain models, prompts, retrievers and tools
- Build stateful agent workflows as LangGraph graphs
- Add memory, checkpoints and human-in-the-loop approval
- Trace and debug agent runs
- Evaluate agents with scenario test suites
Skills you will gain
Frameworks
Agent design
Quality
Tools and platforms covered
Python
LangChain
LangGraphLangSmith
OpenAI API
FastAPI
DockerCourse curriculum
M01 Agent fundamentals
- Reason-act loops
- Tool calling
- Where agents fail
- Planning vs reactive agents
- Choosing a model for tool use
🧪 Hands-on: Build a single-tool agent
M02 LangChain building blocks
- Models and prompts
- Retrievers
- Tool definitions
- Output parsers and structured responses
- LCEL composition
🧪 Hands-on: Wrap two APIs as tools
M03 LangGraph state graphs
- Nodes, edges and state
- Conditional routing
- Loops and limits
- Subgraphs
- Parallel branches
🧪 Hands-on: Build a routing graph
M04 Memory and human-in-the-loop
- Checkpointing
- Interrupts and approvals
- Long-running tasks
- Persistent memory stores
- Resuming after failures
🧪 Hands-on: Add an approval step
M05 Tracing and evaluation
- Tracing runs
- Scenario tests
- Metrics
- Golden datasets for agents
- Cost and latency metrics
🧪 Hands-on: Evaluate an agent on 20 scenarios
M06 Deployment
- Serving agents as APIs
- Permissions
- Cost control
- Rate limiting
- Rollout and versioning
🧪 Hands-on: Deploy the agent in a container
M07 Retrieval-augmented agents
- Retrieval as a tool
- Agentic RAG with query planning
- Grounding and citations
- Handling empty results
🧪 Hands-on: Build an agent that decides when and what to retrieve
M08 Guardrails and security
- Prompt-injection defences
- Tool allow-lists
- Output validation
- Sandboxed code execution
🧪 Hands-on: Red-team your agent and fix the findings
M09 Capstone: production agent
- Use-case scoping
- Graph design
- Evaluation
- Deployment demo
🧪 Hands-on: Deliver a traced, evaluated LangGraph agent behind an API
Hands-on projects
Research agent
An agent that searches, reads and summarises sources with citations.
Ticket triage agent
An agent that classifies tickets, looks up data and drafts replies for approval.
Why train with us
Built around your stack
Labs and examples adapted to the tools, cloud and data your team actually uses.
Practice-first
Every module ends in a lab, and the course ends with a reviewed capstone.
Practitioner-led
Delivered by Karthick Selvam and vetted specialist trainers from our network.
Visible progress
Attendance, lab completion and assessment results shared with your L&D team.
Certificate of completion
Participants who complete the labs and capstone receive a Learning Dots certificate of completion for Agentic AI with LangChain & LangGraph. [confirm certificate wording / sample image]
Learner reviews
“[Verified learner review for this course]”
“[Verified learner review for this course]”
Meet your trainer
Karthick Selvam
Founder · Data Engineering Corporate Trainer, Bengaluru
[Trainer bio, experience and areas of expertise]
Frequently asked questions
Do we need prior LangChain experience?
No, but solid Python is required.
Can the curriculum be customised for our team?
Yes. Modules, depth, duration and labs can be tailored to your stack and goals.
What delivery formats are available?
Online live instructor-led sessions, Bengaluru classroom, or on-site at your office.
How do we enquire or book?
Use the enquiry form on this page or the Enquire button next to any batch.
What does it cost?
The open-batch fee is ₹17,999 per participant plus GST. Corporate batches are priced on group size, format and customisation.
How long is the course?
38 hours · 5 days. Corporate batches can be split into half-day sessions.
A closer look
About this course
A developer course on building AI agents with LangChain components and LangGraph orchestration: tool calling, stateful graphs, memory, human approval steps, tracing and evaluation. Participants build agents that complete real multi-step tasks.
What is Agentic AI with LangChain & LangGraph?
Build tool-using agents and stateful workflows with LangChain and LangGraph, with evaluation and guardrails.
Who this course is for
Python developers, Backend and integration engineers, ML engineers moving into agents, Technical leads evaluating agent frameworks.
What you will be able to do
Explain the agent loop and tool calling. Use LangChain models, prompts, retrievers and tools. Build stateful agent workflows as LangGraph graphs. Add memory, checkpoints and human-in-the-loop approval. Trace and debug agent runs. Evaluate agents with scenario test suites.
Career paths
Roles this course supports include Agentic AI Developer, AI Integration Engineer, Conversational AI Engineer. Agentic AI is one of the fastest-moving areas of enterprise AI, and developers who can build controllable, testable agents are sought after.
Related courses
Agentic AIBuilding AI Agents with LangGraph & CrewAI
Build tool-using agents and agent teams with two popular open-source frameworks, and learn when to use each.
Multi-Agent Systems: Design & Orchestration
Design systems where several specialised agents collaborate: orchestration patterns, communication, evaluation and governance.
Agentic AI for Business Process Automation
Identify, design and pilot agent-driven automations for operations, support and back-office processes, safely.
AI & GenAI guides
Generative AI vs Traditional AI: What Is the Difference?
Traditional AI mostly predicts or classifies. Generative AI produces new content. Both have a place in the enterprise.
What Is Prompt Engineering?
Prompt engineering is the practice of writing instructions that get reliable, useful output from a language model.
What Is ChatGPT and How Does It Relate to Other AI Assistants?
ChatGPT is a conversational AI assistant from OpenAI, built on large language models. It is one of several similar assistants.
How to Compare AI Assistants for Your Team
Several general-purpose AI assistants compete for enterprise use. Rather than chasing rankings, evaluate them against your own needs.