Building AI Agents with LangGraph & CrewAI
Build tool-using agents and agent teams with two popular open-source frameworks, and learn when to use each.
- ✓ 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: Mon, 04 Jan 2027 · 32 hours · 4 days
Agentic AIBuilding AI Agents with LangGraph & CrewAI
Duration: 32 hours · 4 days
Next batch: Mon, 04 Jan 2027
Format: Online live · Bengaluru classroom
Modules: 9 · Topics: 42
Level: Intermediate to Advanced
Fee: ₹14,999
Trusted by leading experts
Upcoming batches
Open batches for individuals; corporate batches on your dates.
| Programme | Starts | Mode | Schedule | Duration | |
|---|---|---|---|---|---|
| Building AI Agents with LangGraph & CrewAI | Mon, 04 Jan 2027 | Online live | Weekday | 4 days | Enquire |
| Building AI Agents with LangGraph & CrewAI | Sat, 30 Jan 2027 | Online live | Weekend (Sat) | 5 Saturdays | Enquire |
| Building AI Agents with LangGraph & CrewAI | Wed, 10 Mar 2027 | Bengaluru classroom | Weekday | 4 days | Enquire |
Soaring demand, and where it takes you
Organisations are moving from chatbots to agents that take actions, creating demand for developers who can build them with sound engineering practice.
Become an expert
Roles this programme prepares you for:
Become a AI Agent Engineer
Designs and builds production-minded agents.
- Design agents with clear goals, tools and limits
- Build stateful workflows with LangGraph
- Build role-based agent crews with CrewAI
About the course
Build AI agents with two leading open-source frameworks: LangGraph for fine-grained, stateful control and CrewAI for role-based teams of agents. Participants learn the strengths of each and when to use which.
Build tool-using agents and agent teams with two popular open-source frameworks, and learn when to use each.
Why should I attend?
Python developers
Automation and integration engineers
ML and AI engineers
Architects comparing agent frameworks
Prerequisites
Python; LLM API experience; basic understanding of prompting
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: 32 hours · 4 days
Course fee (open batch): ₹14,999
Corporate / team batches: per-participant or flat batch pricing on request, based on group size, format and customisation.
What will you learn
- Design agents with clear goals, tools and limits
- Build stateful workflows with LangGraph
- Build role-based agent crews with CrewAI
- Add memory and human approval
- Apply guardrails and least-privilege tool access
- Trace, evaluate and compare agent designs
Skills you will gain
LangGraph
CrewAI
Safety
Tools and platforms covered
Python
LangGraph
CrewAI
LangChain
OpenAI API
DockerCourse curriculum
M01 Agent design basics
- Goals, tools and constraints
- Tool schemas
- Failure modes
- Agent vs workflow decision guide
- Choosing models
🧪 Hands-on: Specify an agent for a business task
M02 LangGraph in depth
- State design
- Branching and loops
- Checkpoints
- Typed state with Pydantic
- Streaming intermediate steps
🧪 Hands-on: Build a stateful agent
M03 CrewAI in depth
- Agents and roles
- Tasks and processes
- Delegation
- Custom tools in CrewAI
- Hierarchical processes
🧪 Hands-on: Build a three-agent crew
M04 Memory and approvals
- Short- and long-term memory
- Human-in-the-loop
- Retries
- Vector-backed long-term memory
- Resuming interrupted runs
🧪 Hands-on: Add approvals to both builds
M05 Guardrails and security
- Prompt injection
- Tool permissions
- Output validation
- Sandboxing tools
- Audit logging
🧪 Hands-on: Harden an agent
M06 Evaluation and comparison
- Test scenarios
- Cost and latency
- Choosing a framework
- Framework portability
- Migration considerations
🧪 Hands-on: Compare the two implementations
M07 Tools and integrations
- Building robust tool schemas
- Calling internal APIs
- MCP tool servers
- Error handling
🧪 Hands-on: Connect an agent to a mock internal API through MCP
M08 Deploying agents
- Agents as services
- Queues and background jobs
- Monitoring
- Cost control
🧪 Hands-on: Deploy a CrewAI crew as a background service with monitoring
M09 Capstone: framework bake-off
- Build the same agent twice
- Evaluate on shared scenarios
- Compare cost and reliability
- Recommend
🧪 Hands-on: Present a reasoned framework recommendation with evidence
Hands-on projects
Content operations crew
A CrewAI team that researches, drafts and reviews content with human sign-off.
Operations agent
A LangGraph agent that handles a multi-step back-office task.
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 Building AI Agents with LangGraph & CrewAI. [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
Why two frameworks?
They suit different problems; knowing both helps you choose well.
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 ₹14,999 per participant plus GST. Corporate batches are priced on group size, format and customisation.
How long is the course?
32 hours · 4 days. Corporate batches can be split into half-day sessions.
A closer look
About this course
Build AI agents with two leading open-source frameworks: LangGraph for fine-grained, stateful control and CrewAI for role-based teams of agents. Participants learn the strengths of each and when to use which.
What is Building AI Agents with LangGraph & CrewAI?
Build tool-using agents and agent teams with two popular open-source frameworks, and learn when to use each.
Who this course is for
Python developers, Automation and integration engineers, ML and AI engineers, Architects comparing agent frameworks.
What you will be able to do
Design agents with clear goals, tools and limits. Build stateful workflows with LangGraph. Build role-based agent crews with CrewAI. Add memory and human approval. Apply guardrails and least-privilege tool access. Trace, evaluate and compare agent designs.
Career paths
Roles this course supports include AI Agent Engineer, Automation Developer, AI Solutions Architect. Organisations are moving from chatbots to agents that take actions, creating demand for developers who can build them with sound engineering practice.
Related courses
Agentic AIAgentic AI with LangChain & LangGraph
Build tool-using agents and stateful workflows with LangChain and LangGraph, with evaluation and guardrails.
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.