4.98/5 - 11,000+ student reviews

Agentic AI bootcamp

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

Technologies and Tools

4.95 Switchup Rating

11,000+

Alumni

2,500+

Companies Trained

900,000+

Community Members

For who

Who is this bootcamp for?

The Agentic AI Bootcamp is designed for professionals who already understand the basics of LLMs and are ready to take the next leap, building intelligent, autonomous AI agents using real-world tools and techniques.

Data and AI
professionals

You’ve worked with LLMs—now learn to build systems that reason, plan, and act. This bootcamp teaches you how to integrate tools like LangChain, vector databases, and RAG to build truly agentic workflows.

Engineers and
developers

Take your technical skills further by deploying LLM-powered agents in production environments. Learn how to connect APIs, fine-tune performance, and handle edge cases in real-time applications.

Product leaders and builders

Go beyond prompts. Understand the architecture behind AI agents and how to design agentic workflows that solve complex problems, automate internal processes, or power new customer-facing products.

Researchers and advanced learners

If you’re exploring the frontier of autonomous systems, this bootcamp offers a practical foundation in agent frameworks, memory, multi-agent setups, and evaluation methods—taught with the latest tools.

Instructors and guest speakers

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

Thierry Damiba

Developer Advocate, Qdrant

Zain Hasan

Senior DevRel Engineer, Together AI

Sage Elliot

AI Engineer, Union AI

Luis Serrano

Founder, Serrano Academy

Raja Iqbal

Founder, Ejento AI

Kartik Talamadupula

Head of AI, Wand AI

Hamza Farooq

Founder, Travesaal AI

Adam Cowley

Developer Advocate, Neo4j

Sophie Daly

Staff Data Scientist, Stripe

Earn A Verified Certificate

Earn a verified certificate from The University of New Mexico Continuing Education:

3 Continuing Education Credit (CEU)
Acceptable by employers for reimbursements
Valid for professional licensing renewal
Verifiable by The University of New Mexico Registrar’s office
Add to LinkedIn and share with your network

curriculum

Explore the bootcamp curriculum

Overview of the topics and practical exercises.

Gain a solid grounding in how reasoning-enabled agents extend traditional LLMs, exploring their building blocks, memory strategies, and design patterns through lectures, discussions, and hands-on labs.

Key Topics:

Foundations of Agentic AI: from next-token prediction to reasoning models, limits of classic LLMs vs reasoning LLMs, and the core pillars—reasoning, context, autonomy

Understanding LLMs: context windows, session memory, long-term memory (vector DBs, graphs, summaries), and data sources (pre-training, fine-tuning, in-context learning)

Retrieval-Augmented Generation (RAG): naïve RAG workflow and challenges, RAG as a context booster, preparing data for RAG pipelines

Agentic AI Components: cognition (reasoning, planning, self-reflection), knowledge representation, autonomy (actions, tools, monitoring)

Agentic Design Patterns: planning, tool use, reflection; Agentic RAG, router, loop; sequential, parallel, hierarchical flows

Architectures for Agents: single-agent vs multi-agent systems, human-in-the-loop strategies, hybrid reasoning and decision graphs

Advanced Context Techniques: session summaries, hybrid memory, Model Context Protocol (MCP), scalable context management

Observability, Safety & Governance: guardrails, explainability, monitoring and evaluation, ethical alignment and compliance

Hands-on exercises on reasoning, memory, RAG workflows, and safe agent design

Learn to build robust, modular LLM-powered applications with LangChain. Explore its core components, retrieval workflows, and chaining logic through lectures, discussions, and hands-on labs.

Key Topics:

Introduction to LangChain: purpose and scope, building LLM-powered applications, challenges with RAG

Core Components: LLMs and chat models, prompt templates and example selectors, document loaders and transformers

Output Parsers: structured data extraction, consistent formatting, error handling

Retrieval: embedding and vectorization, retrievers and metadata filtering, parent document retrieval

Vector Stores: storing embeddings, efficient similarity search, optimizing for large datasets

Chains: sequential prompt logic, pre/post-LLM steps, integrating tools and retrieval into chains

Tool Use: integrating APIs and external actions, passing results back into workflows, handling errors and retries

Domain specific language like LCEL : piping components with runnable, parallel branches, modular workflows

Hands-on exercises on building retrieval chains, parsing structured outputs, and combining LangChain modules into coherent workflows

Explore advanced techniques for orchestrating context-aware, reliable agentic systems. Learn how to design complex workflows, integrate tools, and collaborate across agents using LangGraph and proven agentic design patterns.

Key Topics:

Complex Agentic Workflows: system prompts, user prompts, retrieved context; memory, web search, vector DBs; critique loops and reviewer models

Chains: sequential control flows, pre/post-LLM steps, deterministic task execution

Agents and Reliability: dynamic decision flows, router agents vs fully autonomous agents, balancing autonomy and reliability

LangGraph Fundamentals: nodes, edges, state; condition-based execution; reliability for agent workflows

Tool Integration: node-based tool calls, API connectors and database lookups, updating state after tool use

Agentic Design Patterns: reflection for self-critique, tool use for external actions, planning for task decomposition

Multi-Agent Collaboration: parallel, sequential, loop, and router flows; error checking and discussion; human-in-the-loop supervision
Multi-Agent Architectures: hierarchical delegation, human approval nodes, shared resource tools

Agentic Design Patterns – Hands-On Exercises:

Reflection: Self-Discover framework for complex reasoning; iterative code refinement with LangGraph; stateful chatbot for prompt guidance

Planning: Tree of Thoughts (ToT) for structured idea generation; DAG-based task compilation with LangGraph; efficient reasoning via parallel branches

Tool Use: ReWOO (Reasoning Without Observation) for structured planning; function-calling for robust data extraction; handling unstructured inputs precisely

Multi-Agent Collaboration: hierarchical agent teams for layered tasks; multi-agent supervisor with LangGraph; collaborative agent workflows

Learn how to design, optimize, and integrate vector databases with agentic retrieval-augmented generation (RAG) workflows. Explore embeddings, hybrid retrieval, caching, and observability while implementing advanced reasoning-driven search pipelines.

Key Topics:

Vector Database Fundamentals: embeddings and vector storage; ANN vs kNN search; modern vector DB architecture and data model

Hybrid Retrieval Design: combining dense and sparse vectors; metadata filters and payload indexes; full-text tokenization for mixed queries

Advanced Techniques: Maximal Marginal Relevance (MMR) for diversity; Discovery API for broader coverage; HNSW health monitoring and healing

Agentic RAG Concepts: agents using AI native vector DBs as long-term memory; multi-step retrieval with reasoning loops; context selection and hallucination control

Memory Tiers & Named Vectors: short-term, episodic, and long-term memory; multi-modal embeddings in one collection; modality-specific retrieval

Semantic Caching: caching similar queries via vector similarity; TTL and invalidation policies; optimizing cost and latency

APIs & Operations: search, scroll, recommendation, discovery; index optimization and quantization; deployment (OSS, Docker, Cloud)

Monitoring & Observability: latency, recall, and throughput metrics; resource usage and drift detection; Web UI for search playground and ops

Hands-on Exercises: explore AI-native vector database fundamentals, implement hybrid search, apply re-ranking techniques such as MMR, monitor HNSW index health, and build a RAG pipeline with agentic orchestration.

Understand how agents communicate, discover capabilities, and coordinate tasks through standardized protocols. Learn how MCP, A2A, and ACP enable secure, scalable cooperation between intelligent systems, and practice implementing protocol-driven workflows.

Key Topics:

Multi-Agent Coordination: collaboration challenges with multiple agents; message routing and task management; scaling cooperation without chaos

Need for Agentic Protocols: discovery and negotiation rules; task and state management; enabling secure cooperation

Model Context Protocol (MCP): client–server architecture for LLM tools; standardized data and prompt access; tool, resource, and template exposure

MCP Architecture: hosts, clients, and servers; message exchange and artifacts; connecting apps, IDEs, and assistants

Agent-to-Agent Protocol (A2A): task-oriented communication flows; capability discovery with Agent Cards; message parts and artifact formats

Agent Communication Protocol (ACP): open ecosystem for cross-agent exchange; routing, discovery, and dynamic updates; interoperability across frameworks

MCP vs ACP vs A2A: scope and complexity comparison; message types and architecture; choosing protocols for different workflows

Hands-on Exercise – MCP Client Using Streamlit: set up environment, install dependencies, and load your OpenAI API key; connect an MCP client to servers and discover available tools; automate workflows by invoking tools, retrieving data, and validating outputs

Learn how to assess the reliability, safety, and effectiveness of LLM-based agents. Explore benchmarking methods, text-quality metrics, and RAG-specific evaluation frameworks to ensure business, ethical, and technical alignment.

Key Topics:

Need for Evaluation: reliability, accuracy, safety; business and ethical alignment; transparency and user trust

Challenges in Evaluation: hallucinations, prompt sensitivity, weak context; subjectivity and multiple valid answers; trade-offs between accuracy, fluency, and creativity

Benchmarking Approaches: MMLU for multitask accuracy; HELM for holistic metrics (accuracy, robustness, fairness); BBH & HotpotQA for reasoning and multi-hop QA

Text Quality Metrics: BLEU for n-gram precision; ROUGE (ROUGE-N, ROUGE-L) for recall; BERTScore for semantic similarity

RAG-Specific Evaluation (RAGAs): faithfulness and answer relevance; context precision and recall; joint retrieval + generation scoring

G-Eval for Open-Ended Outputs: fluency and faithfulness; answer relevance; claim-level scoring

Additional Benchmarks: GLUE for NLU tasks; TriviaQA for multi-hop QA; RealToxicityPrompts for safety and toxicity; BST for blended dialogue quality

Other Metrics: perplexity for prediction confidence; METEOR for synonym and stem alignment; MRR and MAP for ranking performance; ROSCOE for reasoning quality (SA, SS, LI, LC)

Hands-on Exercises: apply RAGAs to evaluate retrieval + generation pipelines, compare BLEU/ROUGE/BERTScore on generated text, and use G-Eval to assess open-ended agent responses

Learn how to achieve operational excellence when managing agentic systems. Explore practices for prompt management, observability, tracing, and continuous improvement to ensure agents remain reliable, transparent, and aligned with organizational, ethical, and user goals.

Key Points :

Need for Operational Excellence: reliability, accuracy, safety; business and ethical alignment; transparency and user trust as ongoing goals of AgentOps

Challenges in Operations: hallucinations and prompt sensitivity; brittle reasoning and weak context; subjectivity and multiple valid answers; trade-offs between accuracy, fluency, creativity, cost, and latency

Prompt & Policy Management: version control, modular structures, and governance; managing updates to prompts, instructions, and policies to reduce drift and ensure consistency

Observability & Tracing: logging agent decisions and actions; capturing inputs, outputs, and intermediate steps; tracing multi-step reasoning and tool use for debuggability and accountability

Operational Benchmarks: tracking success rates, error recovery, efficiency, and user satisfaction; aligning operational metrics with business KPIs

Lifecycle Practices: deployment pipelines with staging and production; continuous monitoring for drift and degradation; A/B testing and controlled rollouts; incorporating human feedback for sustainable improvement

Hands-on Exercise: Learn how to manage and version prompts, and how to debug, monitor, and trace AI applications.

Apply everything you’ve learned by designing and testing a complete multi-agent application. Work through structured phases from idea to production-ready prototype, incorporating version control, automated testing, and monitoring to ensure reliability and continuous improvement.

Project Tracks:

Conversational Workflow Orchestration: design a multi-turn assistant that coordinates tasks across multiple specialized agents

Knowledge-Enhanced Agent: integrate external search or APIs for fact-checking, grounding, and real-time information use

Document-Aware Action Agent: build an agent that retrieves and reasons over documents, then triggers external tools or services to act on insights

Orchestrated Collaboration (with MCP): build a system where agents seamlessly assume specialized roles and coordinate through the Model Context Protocol (MCP), enabling effortless integration with external tools, data sources, and enterprise systems.

Attendees Will Receive:

Comprehensive Datasets: a broad collection of documents across industries to support data needs and ensure robust functionality

Step-by-Step Implementation Guides: detailed instructions for each phase, from setup to deployment

Ready-to-Use Code Templates: prebuilt templates in Data Science Dojo’s sandbox environment for faster development

Learners Can Choose to Implement:

Virtual Assistant

Content Generation (Marketing Co-pilot)

Conversational Agent (Legal & Compliance Assistant)

Q&A Bot (IRS Tax Advisor)

Content Personalizer

MCP Chatbot – AI agent with calendar, CRM, and API integrations

Outcome:
By the end of this project, you’ll have a fully functional, production-ready multi-agent application that demonstrates your mastery of reasoning, retrieval, tool use, and protocol-driven interoperability.

Attend the Agentic AI 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 3 CEUs

Agentic AI Bootcamp

Use AGENTIC500 for USD 500 discount

Online

Morning Cohort

Sept 30 -> Nov 25

Every Tuesday 9 AM to 12 PM PT

$3000

$2499

Register Now ->

Online

Evening Cohort

Oct 09 -> Dec 4

Every Thursday 5 PM to 8 PM PT

$3000

$2499

Register Now ->

A Word From Our Alumni

"Partnering with Data Science Dojo aligns with our mission to make data science accessible. Their bootcamps contribute to safe AI deployment education."

"LLM bootcamp provides exceptional, hands-on initiation into LLMs and practical applications. A deep dive into the subject with theoretical knowledge."

"Six months of course material access post-training is valuable. Instructors ensure success, making it a top-notch learning experience in AI."

"Instructors simplified complex topics effectively. Hands-on learning enhanced my LLM understanding in 5 days. Intensive but immeasurable rewards."

"A rewarding opportunity to help students of all backgrounds learn new techniques. Being part of a passionate data science community was a real privilege."

"LLM Bootcamp provides hands-on experience with expert instructors, a comprehensive framework, and extensive resources for substantial upskilling."

"The effort in providing resources was commendable. Teachers and assistants were helpful, making it one of the best courses. I learned a lot for future use."

"Top-notch speakers, hands-on workshops, and networking make it a wonderful tech experience. Raja's in-depth teaching focuses on learning concepts."

"Comprehensive curriculum in generative AI, prompt engineering, and data retrieval. Excited about practical training opportunities."

"Collaborating with Data Science Dojo nurtures the next generation of LLM developers, commendable for fostering a dedicated creator community."

"This boot camp provided great content, equipping me with skills and confidence for efficient job execution. Enjoyable class and projects, a rewarding decision."

"The LLM Bootcamp offered an enlightening, well-structured learning experience, invaluable networking, and insights into real-world AI challenges. "

"Seamless navigation, invaluable hands-on exercises, and well-structured technical aspects for optimal, cost-effective results. Highly recommended for practical LLM knowledge."

"Comprehensive curriculum for in-depth understanding, seamless hands-on learning with cloud-based tools, and insightful talks by industry experts. Highly recommended."

"Outstanding boot camp, engaging discussions on coding and data security. A valuable and refreshing experience, recommended for advancing data science skills."

"Explored Data Science Dojo's LLM Bootcamp, gaining confidence with a comprehensive understanding. In-person experience, insightful instructors, and diverse insights."

"LLM Bootcamp surpassed expectations, bridging theory with practical examples. Engaging with cohorts, invaluable insights, and balanced intensity elevated understanding. Highly recommended for language models."

"LLM Bootcamp enriched my understanding of the language-tech intersection. Collaborating with peers was wonderful. Sophie DA's insightful presentation on practical applications is recommended for foundational knowledge."

"LLM Bootcamp shifted my problem-solving approach, sparking creativity with limitless applications. Highly recommended for anyone building their toolkit, fostering creativity in problem solvers, and providing invaluable insights for diverse applications."

"Dedicated a week to a profound learning experience with Data Science Dojo, sparking innovative ideas. The practical approach revolutionized our models. Highly recommended."

"Engaging with diverse participants and the Dojo staff provided valuable insights. Emphasizes the importance of understanding model performance. Highly recommended for all roles."

"The bootcamp's blend of theory and hands-on experience suited learners of all backgrounds. In just five days, I gained invaluable knowledge and tools for navigating the AI landscape. "

"The boot camp surpassed my expectations with insightful talks, practical insights, and comprehensive resources, essential for accelerating knowledge in LLMs."

"The Data Science Dojo Bootcamp exceeded expectations, offering comprehensive learning, hands-on experience, and valuable insights, transforming my confidence in AI."

"The Bootcamp accelerated my text analysis skills by engaging in in-person experience, industry insights, and valuable hands-on learning. Highly recommended!"

"The Bootcamp helped me bridge the gap between academia and industry, offering insightful talks and practical problem-solving exercises. "

"The Bootcamp exceeded my expectations, offering comprehensive training for both beginners and experienced data scientists. Highly recommended for all!"

Frequently asked questions, answered.

Who does the Agentic AI Curriculum target?

The Agentic AI bootcamp is designed for both technical and non-technical professionals, including engineers, product managers, and business leaders alike. While it includes high-level modules on AI fundamentals, prompt engineering, and strategic deployment, it also dives deep into technical components for developers.

What is the duration of the bootcamp?

The bootcamp is an 9-week, 30-hour program.

Is the program accredited?

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

Will I get a Certificate after the completion of the bootcamp?

Yes, participants who complete the bootcamp will receive a certificate of completion in association with the University of Mexico. This certificate can be a valuable addition to your professional portfolio and demonstrate your expertise in building large language model applications.

What is the difference between the Agentic AI and the LLM bootcamp?

The LLM bootcamp covers the fundamentals of large language models and takes you through a complete learning track—from the basics to deployment.

In contrast, the Agentic AI bootcamp focuses specifically on building and deploying AI agents, so we dive straight into hands-on development.

Are the online sessions live?

Yes, these sessions are live and are designed to be highly interactive.

What benefits will I receive in the Agentic AI bootcamp?

When you join the Agentic AI bootcamp, you will receive:

Live sessions with industry experts
1-year access to dedicated learner sandboxes
Exclusive access to Agentic AI coding labs
Access to all session recordings for review at your convenience
A verified certificate upon completion

What if I’m unable to attend a live session?

Each live session is recorded and made available for review to both online and in-person participants a few days after the boot camp concludes, allowing them to view it at their convenience.

What does the preparatory material include?

Basic understanding of LLM fundamentals and Python
LLM architectures: foundation models, prompts, embeddings, fine-tuning
Challenges & risks: prompt brittleness, context limits, security, cost
Transformers & attention: self-attention, multi-head attention, tokenization

Are there any prerequisites for the bootcamp?

You need a very basic level of Python programming for our Agentic AI bootcamp.

When will I receive the preparatory material for the bootcamp?

The preparatory material will be shared about two weeks before the bootcamp starts. You’ll receive an email with access details and instructions closer to the start date.

Are cloud subscriptions included?

No, cloud subscriptions are not included. Participants will need to use their own accounts.

What is the transfer policy for the bootcamp?

Transfers are allowed once with no penalty. Transfers requested more than once will incur a $200 processing fee.

What is the refund policy?

If, for any reason, you decide to cancel, we will gladly refund your registration fee in full if notified five business days before the start of the training. We would also be happy to transfer your registration to another cohort. Refunds cannot be processed if you have transferred to a different cohort after registration.

Will I get a job after completing the bootcamp?

While we do not specifically focus on job placement, we actively promote networking with our partners, attendees, and an extensive network of alumni. Once you register for the bootcamp, we are happy to assist with introductions if you’re looking to connect with professionals in your desired field.

LLM - Online Courses

Reviews

Consulting

Community

4.98/5 - 11,000+ student reviews

Agentic AI bootcamp

Technologies and Tools

4.95

Switchup Rating

11,000+

Alumni

2,500+

Companies Trained

900,000+

Community Members

For who

Who is this bootcamp for?

Data and AI professionals

Engineers and developers

Product leaders and builders

Researchers and advanced learners

Instructors and guest speakers

Thierry Damiba

Zain Hasan

Sage Elliot

Luis Serrano

Raja Iqbal

Kartik Talamadupula

Hamza Farooq

Adam Cowley

Sophie Daly

Earn A Verified Certificate

curriculum

Explore the bootcamp curriculum

We Accept Tuition Benefits

Agentic AI Bootcamp

Use AGENTIC500 for USD 500 discount

Online

Morning Cohort

Sept 30 -> Nov 25

Every Tuesday 9 AM to 12 PM PT

$3000

$2499

Register Now ->

Online

Evening Cohort

Oct 09 -> Dec 4

Every Thursday 5 PM to 8 PM PT

$3000

$2499

Register Now ->

A Word From Our Alumni

Frequently asked questions, answered.

Training Programs

Enterprise

Community

About

Data and AI
professionals

Engineers and
developers