Agentic AI Mastery.
From Software Engineer to AI Architect.
In this job market, AI Engineers are the ones companies compete for, often at 1.5 to 2x the pay. This cohort is specially designed to make you an industry-ready AI Engineer, with real depth in context and harness engineering, single and multi-agent orchestration patterns, agent evals and observability, memory taxonomy, MCPs, A2A, and inference optimisation. So your career and your salary stay ahead.
/* loved by engineers from big tech and startups */
Twelve modules. Every one exists for a reason.
Grouped into five levels of increasing Agentic AI depth. Each module lists what you'll actually master and what you'll build.
Foundations of Agentic AI
How LLMs Actually Work
Deep dive into the internals of an LLM, i.e. the Transformer architecture. Here we will learn about Tokenisation, Word Embeddings, and the Attention Mechanism. By the end of this module you will understand how an LLM actually works.
Multi-head causal attention in PyTorch from scratch, then nanoGPT, a decoder-only Transformer, trained on Tiny Shakespeare.
A Brief History of the Evolution of Intelligence
The eighty-year arc that brought us here, from the first mathematical model of a neuron to the ChatGPT moment. Every design decision inside a modern LLM is a deliberate answer to a question raised decades ago.
A Perceptron from scratch in NumPy, train it on a linearly-separable problem (Rosenblatt), watch it fail on XOR (Minsky & Papert), then add a hidden layer with backpropagation and watch it succeed.
Retrieval for Agentic Systems
Retrieval Systems: RAG, Agentic RAG & GraphRAG
The full retrieval stack in one thread. Start with the production RAG pipeline, advance to agentic retrieval with query decomposition and routing across sources, then move past vectors into knowledge graphs for the multi-hop questions vector search cannot answer.
GraphRAG over your domain: pick a real dataset (legal, medical, codebase, or product docs), build a knowledge graph with hybrid graph + vector retrieval, and ship LLM Q&A with citations.
Building Agents
Tool Use & Single-Agent Patterns
The difference between a chatbot and an agent: tool use, reasoning loops, and the pattern decision tree that separates good single agents from broken ones. Implemented from scratch so you understand them without framework magic.
ReAct and CodeAct agents from scratch, compared on a real multi-step research task.
Multi-Agent Orchestration, MCP & A2A
How agents talk to tools and to each other over open protocols, then coordinate as teams. Build MCP servers and clients, wire up Agent2Agent communication, and orchestrate supervisors, debate, and consensus, the patterns that separate production-ready multi-agent systems from research toys.
A multi-agent code review system (reviewer + fixer + tester) orchestrated with LangGraph, exposed to other agents over MCP and A2A.
Context Engineering, Agent Harness, Deep Agents & Secure Execution
Long-horizon agents that plan, decompose, and spawn sub-agents over a virtual file system to survive complex, multi-step goals, well beyond a single reasoning loop. Because a deep agent writes and runs its own code, it cannot run untethered: every agent executes inside a hardened sandbox, paired with browser agents that act on the real web safely.
A long-running deep agent that plans and spawns sub-agents inside a gVisor/Daytona sandbox, with a browser agent that completes a real task end-to-end (books a flight or scrapes a live site).
Memory Systems for Agents
Give your agents the ability to remember, across turns, across sessions, across users. Build a standalone memory service that any agent can plug into, then put it to work inside a coding agent of your own.
Mini Claude Code Clone, a terminal coding agent (Aider-style) that reads files, edits code, runs tests, iterates on errors, and plugs into a memory layer you build in this module.
Securely Deploying Agents on Production
Evaluating AI Systems & Agents
You cannot improve what you cannot measure. The complete evaluation engineering stack: from designing benchmarks and golden datasets to running automated eval pipelines, LLM-as-judge frameworks, and the continuous eval harness that catches regressions before they reach production.
An end-to-end eval harness for the coding agent you built in the Agents level: golden dataset construction, an LLM-as-judge scoring pipeline, a CI gate that blocks regressions, and a Braintrust dashboard tracking quality across prompt and model versions.
Production Deployment, Observability & LLM Security
Ship, watch, defend. Agents in production need tracing, guardrails, and red-teaming against the attacks specific to LLM systems, all the failure modes that never show up in development.
Production Coding Assistant (MCP + gVisor + HITL + observability), or Deep Research Clone (long-running citation-backed research agent).
Depth & Frontier
Training & Fine-Tuning Models
Go inside the model. Understand how models are pre-trained, then fine-tune open-source models for your own use cases with the techniques production teams actually ship.
LoRA fine-tune of Llama 3 8B on a custom instruction dataset, published to Hugging Face.
Inference Optimisation
Serving is where models go to die (or scale). KV cache, quantisation, Flash Attention, vLLM, the mechanics of fast, cheap inference at production scale.
nanochat from Scratch: a Karpathy-inspired full stack (pretrain to SFT to serve), end to end. Or a browser agent that builds on the deep-agent harness from the Agents level.
Reinforcement Learning & Reasoning Models
How models learn to reason. The reinforcement-learning techniques behind alignment and the new reasoning models, from RLHF to verifiable-reward RL, then the test-time-compute methods and architectures that make o1, o3, and R1 think.
A small GRPO fine-tune that adds verifiable-reward reasoning to a base model, then a side-by-side of CoT vs ToT vs self-consistency on a reasoning benchmark, with cost / quality analysis.
Joining this cohort was one of the best decisions I made for my AI learning journey. Before this, I was unsure where to start and overwhelmed by the noise around AI. Aseem's sessions gave me clarity, strong fundamentals, and the confidence to build my own agents. The focus on basic principles and real-world systems makes all the difference.
I would highly recommend this cohort to anyone who wants to understand Agentic AI beyond the hype and surface-level tutorials. What makes this program stand out is the way it combines fundamentals, system design, and real-world implementation thinking. The cohort does not just focus on tools or quick demos. It helps you understand how AI systems are actually designed, how LLMs and agents fit into modern product architectures, and how to reason about them as an engineer. If you want depth instead of buzzwords, this is the cohort to join.
Aseem's masterclass finally made AI click for me beyond just writing prompts. He goes deep into how the models and agents actually work under the hood, the attention math, the agent loops, the evals, exactly the kind of depth you need as an engineer who wants to build with AI, not just use it. Genuinely one of the most useful technical programs I've done in years.
Genuinely one of the best learning experiences I've had as an engineer. Aseem takes dense AI and systems topics and turns them into something you can actually build with, every session moves you from theory to working code. It's the rare cohort that respects your time and assumes you want real depth. Highly recommend it to anyone serious about going beyond the surface.
As a staff engineer, what I value most is depth and first-principles thinking, and this cohort delivers both. Aseem connects the math, the systems, and the production reality in a way I haven't seen in any other program. It's rare to find teaching that is this rigorous and this practical at the same time. I came in to fill gaps and left with a genuinely stronger mental model of the whole stack.
I learned a lot about the internal workings of AI, which is helping me use AI far more effectively for technical and complex problem-solving tasks.
Glad to be part of this cohort. What stands out is the practical depth, not just tools, but how AI, system design, and agentic patterns come together for real-world engineering. Looking forward to learning more.
What I appreciate most is the depth of learning. Instead of just covering the “what,” the cohort dives into the “how” and “why” behind AI concepts. Great experience so far!
As someone coming from a backend and system-design background, this cohort has helped me connect traditional engineering principles with modern AI systems. Every session leaves me with a long list of things to explore and apply. Great learning experience so far.
I'm attending this weekend cohort on AI agents, and now I finally understand how AI and agents actually work. Earlier, AI was just magic to me, now I understand the machinery behind it. Thanks Aseem for these sessions.
Coming from a distributed-systems background, I expected the AI parts to feel hand-wavy. They didn't. Every concept is grounded in how you'd actually design, ship, and operate it, latency, failure modes, evals, the works. This is the most engineering-honest AI course I've come across.
The pace is intense and the depth is real. We built things from scratch instead of gluing libraries together, and that completely changes how you think about the stack. Easily the best technical cohort I've taken.
I've done plenty of online courses that stay at the surface. This one goes all the way down, tokenization, attention, agent loops, evals, and then back up to production. I finally feel like I understand AI instead of just using it.
Joining this cohort was one of the best decisions I made for my AI learning journey. Before this, I was unsure where to start and overwhelmed by the noise around AI. Aseem's sessions gave me clarity, strong fundamentals, and the confidence to build my own agents. The focus on basic principles and real-world systems makes all the difference.
I would highly recommend this cohort to anyone who wants to understand Agentic AI beyond the hype and surface-level tutorials. What makes this program stand out is the way it combines fundamentals, system design, and real-world implementation thinking. The cohort does not just focus on tools or quick demos. It helps you understand how AI systems are actually designed, how LLMs and agents fit into modern product architectures, and how to reason about them as an engineer. If you want depth instead of buzzwords, this is the cohort to join.
Aseem's masterclass finally made AI click for me beyond just writing prompts. He goes deep into how the models and agents actually work under the hood, the attention math, the agent loops, the evals, exactly the kind of depth you need as an engineer who wants to build with AI, not just use it. Genuinely one of the most useful technical programs I've done in years.
Genuinely one of the best learning experiences I've had as an engineer. Aseem takes dense AI and systems topics and turns them into something you can actually build with, every session moves you from theory to working code. It's the rare cohort that respects your time and assumes you want real depth. Highly recommend it to anyone serious about going beyond the surface.
As a staff engineer, what I value most is depth and first-principles thinking, and this cohort delivers both. Aseem connects the math, the systems, and the production reality in a way I haven't seen in any other program. It's rare to find teaching that is this rigorous and this practical at the same time. I came in to fill gaps and left with a genuinely stronger mental model of the whole stack.
I learned a lot about the internal workings of AI, which is helping me use AI far more effectively for technical and complex problem-solving tasks.
Glad to be part of this cohort. What stands out is the practical depth, not just tools, but how AI, system design, and agentic patterns come together for real-world engineering. Looking forward to learning more.
What I appreciate most is the depth of learning. Instead of just covering the “what,” the cohort dives into the “how” and “why” behind AI concepts. Great experience so far!
As someone coming from a backend and system-design background, this cohort has helped me connect traditional engineering principles with modern AI systems. Every session leaves me with a long list of things to explore and apply. Great learning experience so far.
I'm attending this weekend cohort on AI agents, and now I finally understand how AI and agents actually work. Earlier, AI was just magic to me, now I understand the machinery behind it. Thanks Aseem for these sessions.
Coming from a distributed-systems background, I expected the AI parts to feel hand-wavy. They didn't. Every concept is grounded in how you'd actually design, ship, and operate it, latency, failure modes, evals, the works. This is the most engineering-honest AI course I've come across.
The pace is intense and the depth is real. We built things from scratch instead of gluing libraries together, and that completely changes how you think about the stack. Easily the best technical cohort I've taken.
I've done plenty of online courses that stay at the surface. This one goes all the way down, tokenization, attention, agent loops, evals, and then back up to production. I finally feel like I understand AI instead of just using it.
Live on weekends, supported every day.
Live weekend cohort
Saturday and Sunday sessions, with recordings of every class.
Hands-on
Weekly labs and a portfolio-grade capstone at the end of every level.
Support
Weekly office hours and capstone reviews per level.
Private Discord community
Dedicated channels per module and topic. Ask anything, any time. Every question and answer lives permanently, becoming a growing knowledge base for the cohort.
The full modern agentic and GenAI toolkit.
Grouped by the problem it solves. Every one of these appears in at least one module or lab.
The world is in the middle of something rare. AI is reshaping software faster than any shift since the internet. The engineers who go deep right now will shape what gets built over the next decade.
Aseem Rastogi
Software & AI Architect · Co-Founder, Hubbleflow.ai · Co-Founder, Agentcord.ai
read the full storyQuestions worth asking.
No. The course is built for software engineers who haven't yet touched ML seriously. We start from the Perceptron and backpropagation, then build up through the modern stack. If you can write production code in any language, you can take this.
$ hubbleflow community --join
join a fast-growing community of engineers going deep on AI.
Cohort updates, resources, and a place to ask anything, alongside people building the same things you are.
$