I believe in the power of small teams. Well, not because of fewer meetings - though that does help quite a lot 😊 . It is because small teams are forced to understand the entire system. One cannot hide behind process. They have to know the user, the product, the data, the edge cases, the failure modes, and the trade-offs.
That belief has shaped a lot of how I think about building products. And it has influenced how I think about AI too.
A small team with a working LLM feature is not automatically more powerful. But, a small team with a reliable AI workflow inside their product is significantly more potent. Having shipped AI-infused products - right from just using prompts in Jan 2023 to the most cutting edge ones in 2026, I’ve seen the field evolve.
And with my partners-in-crime Amit Kapoor and Anand Chitipothu, we want to teach you to make a difference to how you build your products.
We cover everything that makes your product reliable and predictable when using AI Agents.
- *️⃣ What happens when the output is inconsistent?
- *️⃣ What happens when the model needs product data?
- *️⃣ What happens when the conversation has state?
- *️⃣ What should be remembered?
- *️⃣ When should the system use tools?
- *️⃣ How do you know if it is working well enough to ship?
We are running a one-day workshop in Bangalore to answer exactly these questions.
We will build one product together, layer by layer:
Search → Prompt → Schema → Context → State → Memory → Tools → Evals
By the end, you will understand how a simple LLM call evolves into an agentic AI workflow that can live inside your real product.
This is for builders, engineers, founders, and product people who want to move beyond demos and understand how AI products hold together.
✨ One day. One product. Eight layers.
13 June · Bengaluru · ₹4,999 · 30 seats