Start by taking our free AI Fluency Assessment. If you score below AI Local, this course is for you.
As a leader, you're expected to know where AI fits, but your own stack is a few disconnected chats, meeting summaries and half-baked automations.
It saves you 20 minutes a day, takes hours to manage, and looks nothing like your LinkedIn feed.
This isn't because AI agents aren't capable enough. It's because nobody has built you the system to harness them correctly.
In four weeks you'll build that system for yourself, so you can drive AI transformation with confidence, experience, and expertise, not hype.
Here's exactly what you'll build:
First principles understanding of agentic AI so you understand exactly how it works under the hood.
A team of AI agents that work on their own but always stay inside the security limits and trust boundaries that you set.
Custom skills that scrape any website, parse any file, and research the way you want it, not AI slop.
Your second brain: context and memory systems so that your agents know you and never forget what matters.
Dashboards and mini apps built with no code (CEO briefs, competitor research, etc.).
Take on what used to be impossible, then teach your team how to do it too.
Agents = LLM + harness: Understand the big shift in AI, and how agents actually work
Pick your harness: Claude Code vs Claude Chat, and how to decide
Optimize it: project and user instructions, model selection, permissions and session hygiene
The context window, sources of context, and how to avoid context rot
Memory: types of agent memory, session threads, auto-saved memory
Build your second brain by connecting your everyday apps and build thread docs your agent reads and updates.
Tools: where they come from, MCP under the hood, web scraping and browser automation
Artifacts: turn agent output into pages, dashboards and docs you can share
Skills: anatomy of a skill, building your own and sharing them with your team.
Scheduled tasks and routines: work that runs on a clock, not on you
Subagents in parallel, each with fresh context, on one piece of the job
Best practices and the AI-native operator's toolkit.

Founder at Luminary, ex Airbnb
Founders
You run a company and want it to run leaner. Learn where to deploy agents and how to build an AI-native organization.
Senior Operators
Be the champion of AI adoption yourself. Create hybrid teams of humans and agents that leverage the best of both worlds.
Consultants
You already advise on AI and want technical depth. Leave with a polished stack and judgment to tell clients where to invest.
We go deep, because that's where the value is. Stay on track and you'll never work the old way again.
The primary tool surface used for the class. Start with Pro and upgrade only if you need to

Live sessions
Learn directly from Akhil Raj Gupta in a real-time, interactive format.
Two 1:1s with Akhil (worth $1,000)
Private working sessions on your own setup: your workflows, your bottlenecks, your next steps.
Private WhatsApp group
Ask any question between sessions and Akhil answers. It stays open after the cohort ends.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers and alumni network
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Weekly Q&A and AI Build Labs
Two optional live sessions every week: a recap where you bring questions, and a lab where you build your own workflow with Akhil.
AI Fluency Assessment for your team
If you finish the full paid course, you get our AI Fluency Assessment, customized for your team, with free deep analytics on where everyone stands. Hosted on a private endpoint, with your data kept confidential. We do this for several companies, using our in-house methodology and platform.
The Luminary Promise
We want you to have a fantastic experience. A full refund at any point, no questions asked. In addition to the Maven Guarantee.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
13 live sessions • 37 lessons • 4 projects
Live sessions
2-3 hrs / week
Project Work & Reflection
2-3 hrs / week
Dec
6
Understand the anatomy of an agent, why you're probably already using one (but don't know it), and how harness engineering changes the game
From Generative To Agentic AI
How AI Agents Actually Work
Choose your main agent harness between Claude Code vs Claude Chat after reviewing the benefits and limitations of both
Claude Code vs Claude Chat
Claude Code Overview
Claude Chat Overview
How To Decide
How to modify agent instructions, permissions, and your environment for optimal work
Why This Matters
Write Your User-Level Instructions
Write Your Project-Level Instructions
Model Selection, Permissions, & Session Naming
Apply the lessons from the first 3 modules and update your project + user instructions, select the right model for the right task, and start to implement session hygiene
Update Your Harness Settings
Dec
9
Dec
10
Dec
13
Bad models don't kill agents, bad context does. This is how to set it up.
The Context Window
Sources Of Model Context
Context Rot
Agents that remember you and what matters to you compound productivity and create leverage because you don't have to re-explain yourself each time.
Types of Agent Memory
Session Level Threads
Auto Saved Memory
Connect the systems your work already lives in to enrich context. Start building a manual memory layer via session threads. Multiply both and you have a second brain.
Why This Matters
Context Layer & Connectors
Building Thread Docs
Build Your Second Brain
It's been hugely useful. By the end of the week I was spending most of my time at work on Claude. The course made me understand the different parts, what you need to get right, and how to get to the answer — and when things go wrong, I know why. It's opened the door to operating in a very different way.

Kamini Kumaran
It's been amazing. Concepts like subagents, context rot, connectors like Firecrawl and compacting are extremely useful — it's really helped me understand and be more familiar with AI and agentic AI. Loved the discourse in the cohort as well.

Dhruv Gupta
Akhil has done a wonderful job of explaining the basic fundamentals of how Generative AI works, and then taking us through the journey of practical application of the concepts through do-along sessions. What began with a simple chat with Claude, ultimately allowed me to orchestrate multiple agents at the same time. Highly recommended to make best use of generative AI not just to be more efficient, but to actually build things that are tech based.

Rituraj Chaturmohta
Had a fantastic experience. Akhil was extremely proactive and his ability to translate complex concepts into actionable steps is incredible. Loved the detailed readings and especially the 1:1 sessions focused on my specific workflows.

Prateek Chauhan
Honestly, you've done a fantastic job. The last two sessions were particularly great because we got hands-on. You've exposed me to the art of the possible — now it's on us to keep building on it. You went way above and beyond, Akhil!

Sharat Shankar
Great foundational course for anyone figuring out how to use AI to streamline everyday tasks and work smarter, with a lot of practical use cases. Sessions were quite interactive and insightful. Definitely helped me understand the fundamentals of AI better and more importantly, how to actually get better and more useful outputs from it. Highly recommended!

Arwal Dhar

Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$750
USD
2 cohorts