For a hands-on learning experience to develop LLM applications, join our LLM Bootcamp today.
Early Bird Discount Ending Soon!

Agentic AI Bootcamp

Agentic AI Applications
Vector Retrieval
Context-Aware
Model Orchestration
Multi-Agent
LangGraph Workflows
Agent Interoperability
Agentic Patterns
Observability

Learn to build enterprise-grade agentic ai applications.

Learn to build systems that reason

AI agents is the future of knowledge work

Learn to build agents, not just apps. Automate reasoning, planning, context retrieval and execution.

Instructors and guest speakers

Learn from though leaders at the forefront of building agentic AI applications

Luis - Agentic AI Panelist

Luis Serrano

Founder, Serrano Academy
Raja Iqbal-Data Science Dojo

Raja Iqbal

Founder, Ejento AI
Sebastian Witalec | Weaviate

Sebastian Witalec

Director of Developer Relations, Weaviate
John Gilhuly | Arize AI | Data Science Dojo

John Gilhuly

Head of Developer Relations, Arize AI
Kartik - Agentic AI Conference

Kartik Talamadupula

Head of AI, Wand AI
Zain - Agentic AI Panelist

Zain Hasan

Senior DevRel Engineer, Together AI
hamza farooq

Hamza Farooq

Founder, Travesaal AI
1703300423927 (1)

Sage Elliot

AI Engineer, Union AI

Loved by customers and partners

More than 10,000 working professionals have gone through our training program and recommend us.

Japneet Singh | LLM Bootcamp | Data Science Dojo
Play Video
Usman Dankoly | LLM Bootcamp | Data Science Dojo
Play Video
Alejandro W. | LLM Bootcamp | Data Science Dojo
Play Video
Stan Zaporozhets | LLM Bootcamp | Data Science Dojo
Play Video
Omar Smith | LLM Bootcamp | Data Science Dojo
Play Video
Roger Campbell | LLM Bootcamp | Data Science Dojo
Play Video
Tariq Hook | LLM Bootcamp | Data Science Dojo
Play Video
Ali Abuharb | LLM Bootcamp | Data Science Dojo
Play Video
Dave Horton | LLM Bootcamp | Data Science Dojo
Play Video
Francisco Morales | LLM Boorcamp | Data Science Dojo
Play Video
Shakeeb Syed | LLM Bootcamp | Data Science Dojo
Play Video
Yashwant Reddy | LLM Bootcamp | Data Science Dojo
Play Video
Sahar Nesaei | LLM Bootcamp | Data Science Dojo
Play Video
Florian Klonek | LLM Bootcamp | Data Science Dojo
Play Video
Large Language Models Bootcamp - Maryam Bagher
Play Video
Large Language Models Bootcamp - Kshitij Singh
Play Video
Large Language Models Bootcamp - Jared Miller
Play Video
Victor Green | Large Language Models Bootcamp | Data Science Dojo
Play Video
Ken Btler | Large Language Models Bootcamp | Data Science Dojo
Play Video
Abrar Bhuiyan | Large Language Models Bootcamp | Data Science Dojo
Play Video
Erika Davis | Large Language Models Bootcamp | Data Science Dojo
Play Video
Aishwariya Raman | Large Language Models Bootcamp | Data Science Dojo
Play Video
Luis Armando | Large Language Models Bootcamp | Data Science Dojo
Play Video
Amity Fox | Large Language Models Bootcamp | Data Science Dojo
Play Video
David Martins | Large Language Models Bootcamp | Data Science Dojo
Play Video
Ed Wiley | Large Language Models Bootcamp | Data Science Dojo
Play Video

Explore the bootcamp curriculum

Overview of the topics and practical exercises.

Module I

Building Context-Aware LLM Applications and MCP

Use components like Model I/O, loaders, memory, and retrieval chains to develop applications that retain and use context effectively.

Lecture | In-class discussion | Practical Exercise

Learn how to create intelligent applications that maintain context over time using LLM-specific tooling and architecture.

Key Topics:

  • Understanding Model I/O: prompts, responses, parsers
  • Retrieval chains using loaders and retrievers
  • Implementing memory: buffer memory, summarization memory, vector-backed memory
  • Combining modules into coherent, state-aware workflows
  • An Introduction to model context protocol
  • Hands-on exercises on module topics

Module II

Vector Databases

A comprehensive introduction to vector databases

Lecture | In-class discussion | Practical Exercise

Learn about efficient vector storage and retrieval with vector database, indexing techniques, retrieval methods, and hands-on exercises.

  • Rationale for vector databases
  • Vector search, text search, hybrid search
  • Product Quantization (PQ), Locality Sensitive Hashing (LSH) and Hierarchical Navigable Small World (HNSW)
  • Retrieval: Cosine Similarity, Nearest Neighbor Search
  • Relevance scoring in hybrid search using Reciprocal Rank Fusion (RRF)
  • Using auto-cut feature to remove irrelevant results dynamically
  • Improving search relevance by using language understanding to re-rank search results
  • Challenges: Scaling optimization. Reliability optimization. Cost optimization
  • Hands-on exercise on similarity search, hybrid search, vector compression, generative search and semantic caching.

Module III

Multi-Agent Applications

Build collaborative agents using tools and LangGraph to handle complex, multi-step tasks dynamically.

Lecture | In-class discussion | Practical Exercise

Build distributed, multi-tasking agents that collaborate to perform complex actions using tools, task routing and modular workflows.

Key Topics:

  • Introduction to tools, agents and autonomous behavior
  • Tools for building multi-agent systems (LangChain agents, toolkits)
  • Designing task-specific agents (e.g., planner, executor, summarizer)
  • Communication protocols between agents
  • Hands-on: Create a multi-agent system for a business use case

Module IV

Agentic Workflow Fundamentals

Explore LangGraph’s node-based workflows, async execution, and memory-aware agent routing.

Lecture | In-class discussion | Practical Exercise

Dive into LangGraph’s orchestration engine to create structured workflows, decision trees, and looping behaviors.

Key Topics:

  • Graph-based orchestration models
  • A Practical Guide to Coordinated LLM Agents Using LangGraph: Nodes (functions or agents), Edges (data/control flow), Cycles (iteration, self-correction), State
  • Add memory or context passing between agents
  • Node-based task design
  • Async vs sync execution in agentic flows
  • Conditional routing and stateful transitions
  • Integrating memory into LangGraph workflows
  • Hands-on exercises using LangGraph

Module V

Agentic Design Patterns:

Implement reusable LLM behavior patterns like ReAct, Reflection, and CodeAct for dynamic reasoning and action.

Lecture | In-class discussion | Practical Exercise

Implement advanced reasoning and decision-making patterns that enable LLMs to plan, reflect, and act intelligently.

Key Topics:

  • ReAct (Reason + Act) framework
  • Reflection: self-checking and improvement
  • CodeAct: write + execute code dynamically
  • Combining patterns into flexible agents
  • Use cases: coding agents, research agents, evaluators
  • Hands-on exercises on building ReAct, Reflection and CodeAct agentic workflows

Module VI

Interoperability of Agents:

Understand how agents communicate and collaborate across platforms like Google A2A and others for seamless orchestration.

Lecture | In-class discussion | Practical Exercise

Learn how to make agents interoperable across platforms, tools, and APIs for broader AI orchestration.

Key Topics:

  • Google A2A (Agents-to-Agents) overview
  • Cross-agent communication architecture
  • Creating API-ready agents
  • Token hand-off strategies across multiple LLMs
  • Building language-agnostic agent endpoints
  • Hands-on: Deploy agents that call and respond to each other

Session VII

Observability and Monitoring

Track, debug, and evaluate agent behavior and LLM performance using robust observability tools.

Lecture | In-class discussion | Practical Exercise

Establish robust monitoring to understand agent behavior, debug workflows, and ensure safety and reliability in production.

Key Topics:

  • Logging and tracing agent decisions
  • Callback mechanisms in LangChain & LangGraph
  • Tracking token usage, latency, success rate
  • Visual debugging of agent flows

Hands-on Exercise:

  • Add observability to your agent workflow

Technologies and Tools

Attend the LLM Bootcamp for free

We Accept Tuition Benefits

All of our programs are backed by a certificate from The University of New Mexico, Continuing Education. This means that you may be eligible to attend the bootcamp for FREE.

Not sure? Fill out the form so we can help.

Get a certificate from The University of New Mexico Continuing Education with 5 CEUs

UNM's continuing education | Data Science Dojo

Choose an upcoming cohort

CLASS DATES
CLASS TIMINGS
REGISTER NOW

7 July to 26th August
8 Mondays

9am – 12pm PST
(Instructor-Led Online)

Frequently Asked Questions

Are there any prerequisites?

Yes, a very basic LLM fundamentals and python programming language.

What software do I need to install on my laptop?

Just bring your laptop. We will provide all software, subscriptions, and browser-based sandboxes.

Is the program accredited?

Yes. You will receive a certificate from The University of New Mexico with 3 CEUs.

Are cloud subscriptions included?

Yes. During the bootcamp, you will be given all resources needed for completing the labs and exercises.

What is the refund policy?

Registrations are 100% refundable for requests received 5 business days before the bootcamp.

What is the duration of the bootcamp

The bootcamp is a 8-week, 30-hour program.