AI PM: Ship Your First Customer-Facing Agent
Move beyond internal demos and ship agents that survive contact with real customers — learn best practices for system design, agent ergonomics, evals, and monitoring.
Anyone serious about AI in 2026 can build prototypes for internal users. Putting one in front of paying customers at scale is a different beast altogether. The failure modes multiply, the polish bar is much higher, and nobody is watching over the model's shoulder when things go wrong.
This course helps you take that leap. Together we will build a real customer-ready agent — scoped, polished, evaluated, and instrumented — using a working codebase crafted by Luminary instructors.
By demo day, you'll know how to elevate your product beyond "just a wrapper" and sharpen your value proposition so customers actually want to use it. And you'll know how to launch and iterate without burning trust — with guardrails, evals, and observability built in from day one.
This cohort is built for people who already have a working understanding of core AI concepts — LLMs, prompting, and agents. We'll do our best to stay fully inclusive regardless of background — but by enrolling, you're confirming you meet that bar.
Who we built it for
AI PMs & Builders
Learn how you can shape the product, not just the roadmap — by getting hands-on with agentic design principles. Develop the taste to know what's worth building, long before it ships.
Engineers & Tech leads
Learn software design patterns that help you build agents that stand the test of time. Master the core architecture and evaluation frameworks that separate real AI teams from vibe coders.
Founders & Operators
Learn to build the moat that keeps your agent from being cloned in a weekend. Go beyond the wrapper — scope, ship, and own the workflow that makes your product hard to replace.
What we’ll cover
Skip the theory — week one starts inside a working customer-facing agent, taking it apart piece by piece. Learn what an agent is actually made of, then get started building your own.
- The anatomy : the core loop, tool calls, context, memory, and the system prompt — what each part does, where it breaks, and how to fix it
- The build-or-plug call: when your product needs its own agent — and when an MCP or skill inside a general assistant is enough
- Your takeaway: your agent v0 is running + you understand the frameworks to scope an agentic product
Capstone — Demo Day
Showcase your agent to a panel of experts; get actionable feedback that elevates your product experience to world class
Bonus Module — Background Agents
The future of AI products. Learn what differentiates a vanilla chatbot from a multi-purpose agent that can work while you sleep
Guest Lecture - Solving Agent Quality
Tactics from leading industry practitioners who think about this problem 24/7. Learn what's already used and in-flight at the best companies in the world.
How we'll interact
Live sessions
Fridays at 9:00 AM IST · 90 min each · all recorded for async catch-up.
Nov
Module 1
Nov
Module 2
Nov
Module 3
Dec
Module 4
Weekly office hours — drop-in Q&A and live feedback on your agent, Tuesdays at 9:00 AM IST.
Private cohort community — ongoing questions, peer review, and shared resources, always on.
Peer network — build relationships with founders and builders shipping agents to customers.
Who you'll learn from
Bharat Batra
Product Leader at Superhuman AI
Bharat Batra is a product leader at Superhuman AI. He has spent years building products from zero to launch — learning firsthand what separates a product people rely on from one that quietly churns.
His conviction: with AI, the moat isn't features — it's craft. Getting code out is easy. Making the core loop work extremely well, and keeping it reliable in front of real users, is the grueling part most teams skip. In this cohort he teaches exactly that craft for agents you put in front of customers.
Everything else you need to know
No — you need to be willing to build. The cohort provides a working codebase and scaffolding; if you can follow a guided build and use AI tools honestly, you're equipped.
Testimonials
What people are saying about the Luminary experience.
Senior professionals and founders across industries, in their own words.
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.
Akhil did an absolutely fantastic job in that he opened our eyes to the art of the possible with AI agents and sub-agents. The hands on working sessions were the highlight - he held our hand building agents and sub agents to do real world work!! I give this class a 5 star review for a host of reasons from real world applicability to Akhil's teaching style to his willingness to help one on one in getting you more knowledgeable!
The AI training with Akhil was a great experience. He took us from the basics to practical applications, making the concepts clear and easy to put into action. As a coach, he is intuitive, patient, enthusiastic about sharing his knowledge, and in tune with the latest developments in AI. The one on one sessions were a huge help and the flexible calendar allowed me to balance it with work schedule. The most valuable part for me was learning how to design and create an agentic AI environment for my work in inorganic growth. I came away with a stronger understanding of AI and the confidence to apply it to real business challenges. Thank you, Akhil, for an engaging and highly relevant learning experience. Wishing you the best!
I'd been using AI for brainstorming and a few automation experiments, and I was curious about what else was possible. But with so much content out there, I didn't know where to start. These 4 weeks gave me that foundation. Akhil is hands-on and breaks down the basics, so each step builds on the last and the results compound. The applications are endless, and I see myself deploying agents far beyond what I'd initially thought possible.
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.
I took Akhil's course to 10x myself and my business with AI. It delivered. Akhil cuts through the hype and teaches you how to actually use AI: to think, build, and operate faster. I came away with frameworks I use every single day, and a completely different view of what a lean, AI-first company can look like. If you're a founder who's serious about AI, this is the course to take.
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.
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.
Extensive use of agents with browser capabilities, artifacts, a “second brain” within Claude, and a “AI first” mentality that forces me to close the feedback loop by updating real-world decisions back into Claude.
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!
The course is very well structured, with practical learning that can be applied immediately. Akhil brings deep knowledge of AI and, more importantly, explains it in a very practical and relatable way. I came with several useful ideas that I have started implementing in my work.
Akhil’s course curation made the course accessible from both a conceptual and practical standpoint, notwithstanding my zero technical grounding. Provided you apply the principles and techniques taught, the course will benefit anyone whose work involves a computer. The heart and soul of the course, however, was the 1:1 sessions with Akhil. AI agents remain in their relative nascency with no settled playbook for their use. Being a practitioner himself, Akhil uses these sessions to tailor the contents into my own AI workflows. His command of AI as a technology added a further dimension. Several of my doubts went deeper than the course material and, at times, well beyond its scope. Akhil addressed those with ease. For anyone who wishes to use AI meaningfully rather than a glorified web search tool, I recommend this course without reservation.
Two things stood out for me. Learning how agents actually work and how to build a customised agentic system for myself took away so much of my anxiety about AI (it stopped feeling like a black box). And the cohort itself was so thoughtfully put together that it genuinely made the learning experience outstanding.
AI Courses & Workshops
Other programs you might like
Live and hands-on, alongside real-world experts and dedicated peers.
AI Strategy: Optimizing Customer Operations
A strategy course for CX and operations leaders bringing AI into complex, high-volume customer operations.
Starts Nov 13
Regular price $1,000Founding price $750