Applied With AI — Build Production AI Systems, Not Tutorial Demos

Current workshop

Production Agentic AI Workshop

You'll build a complete multi-agent banking system across 4 live sessions. Every module exists because the previous one's failure demands it — hallucination, then mis-calling, then prompt rot, then security gaps. Each fix introduces the next real problem.

Weekend 1 · Session 1

Coordinated Multi-Agent Desgin

Start with a naive LLM that hallucinates bank data with confidence. Wire in real APIs. Watch it break differently — then fix routing with prompt engineering, versioning, and a multi-agent split.

Weekend 1 · Session 2

Build your own MCP server

Assemble the Accounts domain MCP server from scratch. Understand schemas-as-contracts. Wire Transactions and Service domains into the same protocol — three MCP servers, one coordinator.

Weekend 2 · Session 3

Auth, memory, and guardrails

Add OIDC authentication and role-based authorization. Build Redis-backed conversation memory and shared agent state. Layer on prompt injection prevention, PII redaction with Presidio, and sensitive output filtering.

Weekend 2 · Session 4

Observe, evaluate, and deploy

Add observability and tracing across multi-agent flows. Build an evaluation suite with golden datasets. Containerize three separate deployable units and ship everything to AWS — live.

Enroll to the workshop — ₹4,499 Format: 2 weekends · 4 live sessions · All code provided

Is this right for you?

Built for working engineers

This workshop assumes you can already write code. Concepts are taught by building — each session ships working software, not slides.

This workshop is for you if

You've built APIs and backend systems before, in any language.
You want to go beyond AI wrappers and build real-time agentic systems.
You want to learn the engineering behind AI — auth, guardrails, deployment — not just the model calls.
You'd rather spend 2 weekends building than 40 hours watching videos.

This workshop is not for you if

You're brand new to programming — this assumes you can already code.
You want a self-paced recording — this cohort is live and weekend-scheduled.
You're looking for a prompt-engineering cheat sheet — this goes into real infrastructure.
You want to stay in a notebook — this is built around real APIs and real deployment.

Your instructor

Taught by someone who's shipped this

Sanjay Kumar

Senior Cloud Architect · 17+ years · Anthropic CCA-F certified

I've spent 17 years building enterprise software, architecting cloud solutions, and deploying AI systems for large organizations. Somewhere along the way, I noticed a gap: engineers were learning AI through toy demos and prompt tutorials. Nobody was teaching what it actually takes to ship an AI system — with real APIs, proper error handling, auth, and a deployment that doesn't fall apart under load.

Today I teach production-grade AI engineering through hands-on projects — RAG pipelines, AI agents, multi-agent systems, and MCP-based applications. My content has reached over 1,000 engineers through live cohorts and hands-on workshops.

If you're a developer who wants to go beyond AI wrappers and build systems you're confident putting into production, you're in the right place.

Anthropic CCA-F Certified 17+ Years Enterprise Architecture Cloud & AI Systems

Ready to build production AI systems?

Founding cohort pricing — locks after 50 seats fill or the cohort starts, whichever comes first.

₹7,499 ₹4,499

40% founding cohort discount — one-time offer

Book your seat now

4 live weekend sessions Session recordings All code and datasets Direct Q&A with instructor

Build a Production Multi-Agent System.
Deploy it to Cloud.

Curriculum sent!