Next Cohort · Last Week of Sep 2026 (Tentative) · Sat + Sun · 8:00–11:00 AM IST

You Can Ship Software.
The Agentic Stack Is What’s Missing.

Where you are: you write production code every day, but LLM APIs, RAG, LangGraph, MCP, multi-agent frameworks and cloud AI are still a pile of unfamiliar names you keep meaning to sort out.

The gap: tutorials are scattered and demo-shaped. Nothing gives you the stack in one deliberate sequence, with something working at the end of every week.

Where this takes you: six weeks, six working artifacts, and enough fluency to keep building on your own — the foundation the production and delivery programs assume you already have.

The current cohort is already running. The next cohort is tentatively the last week of September 2026. Enrol now and you get the recordings from Class 1 immediately, then join the live sessions when your cohort starts. Exact dates are confirmed by email before the cohort opens.

🎁 Special Bonus
Exclusive Python Foundations for Agentic AI — Live

A dedicated live foundation track, taught separately from the six core weeks — for people who can already code but have never used Python this way. Included with the current intake; not part of the standard Bootcamp.

Early only
Enrol now — start your prep immediately with the Python Prep Module. Instant portal access, so your environment is ready before your first live session.

Next cohort · last week of September 2026 (tentative) · Sat + Sun, 8:00–11:00 AM IST · recordings from Class 1 included.

  • Enrol now: Python Prep Module unlocks immediately, plus recordings of the running cohort
  • 6 weeks of live, structured teaching + 2 pre-bootcamp Python classes
  • One hands-on project artifact every week + one final portfolio build
  • Major Agentic AI frameworks — LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, Agno
  • Hands-on Model Context Protocol (MCP) foundations
  • Cloud AI stack across AWS Bedrock, Azure OpenAI, GCP Vertex AI
  • Full recordings + active learner community inside your Manifold AI Learning portal
📅 Next cohort · last week of Sep 2026 (tentative)|🕑 8:00 AM – 11:00 AM IST|Enrol early · unlock Python Prep now|🎥 Live + Recordings
Hear from the founder

Why Structured Learning Matters

A short note from Nachiketh on why most Agentic AI learners get lost — and how this bootcamp fixes it.

Why this bootcamp exists

The Agentic AI ecosystem exploded. The structured pathway didn't.

Every week there's a new framework, a new agent pattern, a new cloud AI service. Ten scattered tutorials on YouTube. Five different opinions on which stack to learn first. Twenty tools that look important but aren't obviously connected.

1

Prompt-only tutorials that stop at "chat with the model" and never reach real agent architecture.

2

Advanced architectures attempted before the core Agentic AI developer skills are comfortable.

3

Disconnected weekend courses that don't add up to a working developer skill set.

One structured pathway. Six weeks. Real fluency.

The Agentic AI Developer Bootcamp assembles the essential tools, frameworks, and cloud services into a coherent developer skill set — and gives you the project artifacts to prove it.

You leave with real fluency — the kind you can talk about in an engineering conversation, and the kind you can show in code.

What you'll build

Real engineering outcomes — not chat demos.

By the end of the bootcamp, you have both the skill and the artifacts to demonstrate it.

Build agents that call tools, structure outputs, and handle real errors — not chat wrappers.

Wire tool schemas and function calls with judgment — expose the right surface, hide the wrong one, and catch failure gracefully.

Use Claude Code, Cursor, and GitHub Copilot as core developer tools — inside a modern AI development workflow.

Build RAG assistants with LangChain and LlamaIndex — chunking, embeddings, retrievers, and the failure modes you have to see coming.

Design graph-based agent workflows in LangGraph — state, conditional routing, memory, and human-in-the-loop.

Compare and use multi-agent frameworks — CrewAI, AutoGen, Agno / Phidata — and know exactly when each fits.

Work with the Model Context Protocol (MCP) — hands-on MCP foundations covering client / server, tools, resources, prompts.

Navigate the cloud AI stack across AWS Bedrock, Azure OpenAI, and GCP Vertex AI.

Add tracing, evaluation, and observability to workflows with LangSmith and Langfuse.

Ship six weekly hands-on artifacts + one final portfolio project — every one of them in your GitHub.

Speak the language of Agentic AI development fluently — frameworks, patterns, evaluation, cloud, deployment.

Who this is for

Built for engineers and builders serious about Agentic AI.

If you're already writing code and curious about AI, you'll thrive here.

💻

Software Developers

Ready to add Agentic AI to your core skill set.

Backend / QA / DevOps / Cloud / Data Engineers

Moving into AI-native workflows and tooling.

🚀

Junior Developers

Looking for a serious, structured way into the modern AI stack.

🎓

Students Who Already Code

You've written code before and want to move into Agentic AI development.

📚

Working Professionals

Read about LangChain, CrewAI, and MCP but haven't built anything real yet.

💡

Curious Engineers

Want to hold their own in a modern AI engineering conversation — with the projects to back it up.

Program format

Structured. Live. Hands-on every week.

Duration
6 weeks + 2 pre-bootcamp Python classes
Next Cohort
Last week of Sep 2026 · tentative
Batch
Weekend · Sat + Sun
Live Session Time
8:00 AM – 11:00 AM IST
Live Sessions
Every week, structured and hands-on
Weekly Deliverable
One hands-on project artifact per week
Final Project
Portfolio-style Agentic AI build submitted as homework
Recordings
Every session available in your Manifold AI Learning portal
Community
Active learner group for questions, peer builds, and progress
Prerequisites
Some programming exposure helps. Python is covered in the pre-bootcamp classes.
Delivery Platform
Manifold AI Learning portal
Curriculum

A structured Agentic AI developer pathway — taught in a practical sequence.

Two pre-bootcamp Python classes get everyone ready. Six weekly modules take you through the full stack.

📄 Most-requested resource
Download the Detailed Curriculum
Full week-by-week curriculum, topics, tools, and project deliverables — for you to review with your team or revisit before enrolling.
⬇ Download Curriculum
Pre-Bootcamp · Class 1

Python for AI Developers

Setting the developer environment right before we build.

Topics

Python setup, VS Code and Cursor setup, virtual environments, variables, functions, lists, dictionaries, JSON handling, file handling, error handling, basic project structure.

Hands-on

Build a Python script that reads a file, extracts key information, and saves structured JSON.

Pre-Bootcamp · Class 2

APIs, SDKs & Developer Workflow

The developer discipline behind every serious AI application.

Topics

HTTP basics, API calls, API keys and secrets, environment variables, .env files, JSON request/response payloads, Python SDK usage, Git and GitHub basics, Claude Code and Cursor workflow awareness.

Hands-on

Build a CLI application that calls an LLM API and returns structured output.

Week 1

Agentic AI Architecture + LLM API Mastery

The mental model, the vocabulary, and your first shipped assistant.

Topics

Agentic AI vs Generative AI, agents vs workflows, the autonomy spectrum, core agent components, LLM API fundamentals, prompting design, system prompts, user prompts, structured outputs, JSON response engineering, Cursor / Claude Code / GitHub Copilot as first-class developer tools.

Hands-on

Build a working AI assistant using an LLM API with structured output.

Deliverable Structured Output AI Assistant
Week 2

Tool Calling, Function Calling & MCP Introduction

The layer that turns a chat model into a real agent.

Topics

Tool calling and function calling in depth, tool schema design, tool execution flow, tool error handling, common misuse risks, the Model Context Protocol (MCP), MCP client / server concept, tools, resources, and prompts inside MCP, where MCP fits in modern Agentic AI systems.

Hands-on

Build a tool-using assistant with a calculator, file-summary tool, mock search tool, and full error handling.

Deliverable Tool-Using Agent (with MCP awareness)
Week 3

LangChain, LlamaIndex & RAG Basics

The retrieval spine underneath every serious AI application.

Topics

Document loading, chunking strategy, embeddings, vector stores, retrievers, the full RAG pipeline, LangChain and LCEL, LlamaIndex, framework comparison, RAG failure modes and how to spot them early.

Hands-on

Build a document Q&A assistant using LangChain or LlamaIndex.

Deliverable Working RAG Assistant
Week 4

LangGraph, Memory & Agent Workflows

The graph-based agent workflow model behind modern production systems.

Topics

Why LangGraph exists, graph-based workflows, nodes and edges, state schemas, conditional routing, short-term memory, long-term memory patterns, human-in-the-loop, agent workflow design principles.

Hands-on

Build a LangGraph workflow with state, routing, tool call, memory, and a conditional branch.

Deliverable LangGraph Agent Workflow
Week 5

Multi-Agent Frameworks + Low-Code AI Tools

When you scale from one agent to many — and when you shouldn't.

Topics

CrewAI, AutoGen, Agno / Phidata, deep framework comparison, role-based agents, conversation-based agents, workflow-based agents, when multi-agent systems shine, when they become overkill, low-code / no-code AI tools — Langflow, Flowise, Relevance AI-style workflows.

Hands-on

Build a multi-agent research workflow with researcher, writer, and reviewer agents.

Awareness Demo

Recreate a similar workflow inside a low-code / no-code tool to see the trade-offs.

Deliverable Multi-Agent Research Assistant
Week 6

Cloud AI Deployment, Agentic Evals & Observability

The layer that separates a demo from a system you can trust to run.

Topics

AWS AI stack + Amazon Bedrock, Azure AI stack + Azure OpenAI, GCP AI stack + Vertex AI, deployment options, FastAPI awareness, Docker basics, LangSmith, Langfuse, AgentOps awareness, agentic evals fundamentals, trace-based debugging, golden dataset basics, LLM-as-judge basics, cost / latency / reliability / safety checks.

Hands-on

Instrument an existing agent or RAG workflow with tracing, a simple evaluation dataset, a response quality check, a tool failure check, and cost / latency observation.

Deliverable Evaluated Agentic Workflow
Tools & platforms covered

Real breadth — grouped by domain.

Intentional coverage, not a tag cloud. Every category maps to a real Agentic AI engineering discipline.

Developer Toolchain

PythonCursorClaude CodeGitHub CopilotGit & GitHubVS Code

LLM APIs & SDKs

OpenAI SDKAnthropic SDKLLM API fundamentalsStructured outputsTool callingFunction calling

Agentic Frameworks

LangChainLCELLangGraphLlamaIndexCrewAIAutoGenAgno / Phidata

Model Context Protocol (MCP)

MCP client / serverToolsResourcesPromptsIntegration patterns

Retrieval & RAG

Document loadingChunkingEmbeddingsVector storesRetrieversBasic RAGAgentic RAG basics

Cloud AI Platforms

AWS AI StackAmazon BedrockAzure AI StackAzure OpenAIGCP AI StackVertex AI

Observability & Evals

LangSmithLangfuseAgentOps awarenessTrace-based debuggingGolden datasetsLLM-as-judge

Low-Code / No-Code AI

LangflowFlowiseRelevance AI-style workflows

Deployment Stack

FastAPIDockerAWS / Azure / GCP deployment
Hands-on every week

Six weekly deliverables. Every one of them in your GitHub.

At Manifold, no week ends without an artifact you can point to. By the end of six weeks, you have seven artifacts you can develop into a portfolio.

Week 1

Structured Output AI Assistant

An LLM-backed assistant that returns clean, structured JSON on every call.

Week 2

Tool-Using Agent (with MCP awareness)

An agent that calls tools, handles errors, and works inside MCP concepts.

Week 3

Working RAG Assistant

Document Q&A over your own knowledge source with LangChain or LlamaIndex.

Week 4

LangGraph Agent Workflow

A graph-based agent with state, memory, routing, and conditional flow.

Week 5

Multi-Agent Research Assistant

Researcher, writer, and reviewer agents collaborating on a real task.

Week 6

Evaluated Agentic Workflow

One of your builds instrumented with tracing, evals, and observability.

Final portfolio project

A build that proves you can wire an Agentic AI system end-to-end.

Design your own project. Submit as homework. Add it to your portfolio.

Choose one of four archetypes

  • Personal Knowledge Assistant
  • Research Assistant
  • Business Workflow Assistant
  • Tool-Using Productivity Agent

Every project must include

  • LLM API usage
  • Prompting and structured output
  • At least one tool
  • Basic RAG or a knowledge source
  • A simple agent workflow
  • Basic tracing or logging
  • A simple evaluation checklist
Submission: GitHub repository or zip file, plus a short reflection note on what worked, what failed, and what you would improve. Optional: demo video and architecture diagram. This is the piece you show yourself first — and then the world, when the moment is right.
What makes this different

Depth without gatekeeping. Structure without fluff.

One structured pathway

A structured Agentic AI developer pathway — assembled inside one coherent 6-week curriculum. No hunting. No fragmentation.

Framework judgment, not checklists

You know when LangChain beats LlamaIndex, when LangGraph beats CrewAI, when MCP beats a plain tool call. Opinions grounded in practice.

Six weekly artifacts

No week ends without something in your GitHub. Your portfolio grows every session.

Cloud AI included in the developer pathway

Understand where Amazon Bedrock, Azure OpenAI and Vertex AI fit — and how developers move from local experimentation towards cloud-hosted AI applications.

Evaluation and observability built in

LangSmith, Langfuse, tracing, golden datasets, LLM-as-judge — the discipline that separates real engineers from demo builders.

Live teaching + community + recordings

You're not watching a course. You're inside a cohort.

Depth without gatekeeping

MCP, LangGraph, multi-agent orchestration, cloud AI, and evals — serious working depth, without unnecessary complexity or gatekeeping.

Outcomes

Leave with working fluency — and a portfolio that proves it.

This Bootcamp is a complete developer pathway. You finish with structured foundations, six weekly GitHub artifacts, one final portfolio-style project, and the judgment to keep building Agentic AI systems on your own.

After six weeks, you will be ready to:

  • Ship personal and portfolio Agentic AI projects with confidence
  • Contribute to Agentic AI initiatives at work with real implementation experience
  • Prototype AI-enabled workflows for your team or clients end-to-end
  • Choose the right tools for the job — RAG, orchestration, MCP, cloud AI, and evaluations
  • Design and iterate production-minded agent workflows with tracing and eval discipline
Learner voices

Learner experiences with Nachiketh's live cohorts.

The Agentic AI Developer Bootcamp is a new program. The experiences below are from engineers who previously attended Nachiketh's live Manifold AI Learning cohorts and reflect the teaching quality, hands-on depth and live learning experience — not this exact curriculum.

★★★★★

"I used to see an AI agent as just 'an LLM with a tool'. Now I think in terms of systems — explicit conversation memory, structured logging, and targeted error handling so failures are expected, traced, and contained. The biggest unlock was separating capability from control: tools give the agent power, LangGraph gives control through explicit state, nodes, and conditional routing. Production-grade Agentic AI is traceable workflows, not magic."

W1
Learner reflection · Week 1
Shared publicly on Substack
★★★★★

"I'm a backend Java engineer. With no prior exposure to AI, I got a good solid foundation and a clear direction. This program changed my thinking about how we should implement enterprise-level RAG and build production-ready agents."

AR
Anshul Rajput
Backend Engineer (Java) · 9–12 yrs · Cohort learner
★★★★★

"Before joining, I struggled with GenAI concepts. The cohort helped me bridge the gap between a Data Scientist role and a GenAI role. I would highly recommend it to anyone who wants to transition with a strong foundation."

K
Krishna
Lead Data Scientist · 12+ yrs · Cohort learner

From verified cohort feedback and public learner reflections · 9.6/10 average experience rating in our latest cohort feedback survey.

Launch cohort pricing

Founding-cohort rate is open.

Our way of investing directly in the learners who join first.

📅 Next Cohort · Late Sep
Next cohort · last week of Sep 2026 (tentative) · Sat + Sun, 8:00–11:00 AM IST
19,999 + GST
Price loading…
Regular price Price loading…
🛡️Seat-Transfer Guarantee — can't make this cohort? We'll move your seat to any future cohort, free.
Join the Next Intake →
Enrol now: start your prep with the Python Prep Module right away — instant portal access, included with this intake.
Everything included
  • Early registrations: Python Prep Module unlocks immediately so you can prep before live sessions
  • 6 weeks of live sessions (8:00 AM – 11:00 AM IST)
  • 2 pre-bootcamp Python classes
  • Six weekly hands-on project artifacts
  • Final portfolio project submission
  • All session recordings in your Manifold AI Learning portal
  • Learner community access
  • Full stack coverage — tools, frameworks, cloud, evals
FAQ

Everything you might want to check.

Is this beginner-friendly?

This is a practical Agentic AI developer program for engineers with programming exposure. If you code and you're serious about Agentic AI, you'll do well here. The two pre-bootcamp Python classes get you fully ready for Day 1.

Do I need Python?

Some Python comfort helps. If you're already writing Python, you're set. If you're new to Python but have other programming exposure, the pre-bootcamp classes will get you where you need to be.

Will Python be covered?

Yes. Two dedicated pre-bootcamp Python classes cover Python setup, environments, JSON handling, error handling, API calls, SDK usage, Git and GitHub, and the developer workflow around Claude Code and Cursor.

Is this hands-on?

Every single week. Six weekly deliverables plus one final portfolio project. Every artifact lives in your GitHub.

Will it cover LangGraph?

Yes — Week 4 is a dedicated LangGraph module covering graph-based workflows, state schemas, conditional routing, memory, and human-in-the-loop.

Will it cover CrewAI and AutoGen?

Yes — Week 5 covers CrewAI, AutoGen, Agno / Phidata, and framework comparison, including when multi-agent systems help and when they don't.

Will it cover MCP?

Yes — Week 2 covers hands-on Model Context Protocol foundations: client / server, tools, resources, prompts, and where MCP fits in modern Agentic AI systems.

Will it cover Claude Code and Cursor?

Yes. Claude Code, Cursor, and GitHub Copilot are treated as first-class developer tools throughout the bootcamp — from the pre-bootcamp classes onwards.

Will it cover cloud?

Yes — Week 6 covers AWS AI stack + Amazon Bedrock, Azure AI stack + Azure OpenAI, GCP AI stack + Vertex AI, plus deployment awareness across FastAPI and Docker.

Will there be a project?

Yes — six weekly deliverables plus one final portfolio-style project you design and submit as homework. Four project archetypes to choose from with clear component requirements.

Do I get recordings?

Yes — every session is recorded and available inside your Manifold AI Learning portal.

What happens after this bootcamp?

You leave with practical Agentic AI developer fluency, six hands-on artifacts and one final portfolio-style project. From there, you can continue improving your projects, contribute to internal or client AI initiatives, build new Agentic AI applications, or specialise further in areas such as RAG, orchestration, cloud AI and evaluations.

The program is designed to stand on its own. You do not need to enrol in another Manifold AI Learning program to complete the promised learning outcomes.

Is there a job guarantee?

No. This is a learning program. Manifold AI Learning does not offer or imply any job, placement, hiring, salary, or income guarantee. Outcomes depend on your own execution, portfolio quality, and market circumstances.

What is the refund / access policy?

Since access to live sessions, recordings, community, and learning materials is provided after enrollment, refunds are limited once your account is activated. Please review the program details before enrolling. For any questions, contact support before purchase.

Six weeks. A structured Agentic AI developer pathway. Seven artifacts you can develop into a portfolio.

The current cohort is running now. The next cohort is tentatively the last week of September 2026 — Saturdays and Sundays, 8:00 to 11:00 AM IST, with recordings from Class 1 the moment you enrol.

Launch Cohort pricing — Price loading…

Enrol now and start prep with the Python Prep Module — instant portal access, included with this intake.

Join the Next Intake →

Not ready to enrol yet? Register for the free demo session first →

Enrol — Price loading… →