← Back to Workshops

Agentic AI for Products & Systems · Two-day hands-on workshop

Build an agent on your own real project. Decide if it should ship.

For senior engineers, architects, and technical leaders responsible for turning agentic AI ideas into production decisions.

  • 2 days16 hours, hands-on
  • Live onlineIST
  • 10–25Experienced participants

See the full syllabus Ways to attend ↓

The workshop

  1. 1 Foundations Your first working agent
  2. 2 Core concepts Context engineering, RAG, MCP & A2A
  3. 3 Building agents Single-tool to multi-agent, in code
  4. 4 Evaluation & AgentOps Evals, observability, cost, security
  5. 5 Strategy Where agents belong, and under what operating model
  6. 6 Productize & capstone Package it; take the production decision

Your project, all the way through

Ends in a decision: ship · extend · buy · defer · stop

Hands-on throughout · shared core, role-specific depth · one framework deep. Full syllabus →

Why this is different

Your project, not our demo

Bring a real project: a product, an internal system, a workflow, or a new capability. We review your one-page Agent Opportunity Brief beforehand, then point every exercise and the capstone at it.

Build, then decide

The goal isn’t just an agent that works. It’s enough technical and business evidence to decide what should happen next.

The model is the least important part; the system is the product.

How your project is used

Before. You submit the Agent Opportunity Brief, a one-page brief on your project from “why agentic, not plain software” through build, buy, or defer. We review it and reply with suggestions before you arrive.

During. Every exercise is re-pointed at what you submitted. The first working agent is low-code, so the first build excludes no one; engineers rebuild it properly in code later.

End. The capstone is built against your project, and you leave with a reasoned decision about what to do with it.

You leave with

A working agent slice

Built against your own real project, not a sample app.

A production decision

Ship, extend, buy, defer, or stop, with the evidence behind it.

A reusable working kit

Decision aids, reference code, and a tracing, evaluation, and cost-control toolchain on your own accounts.

What two days can do. You won’t leave with a production system. You will leave with a working slice, the important failure modes exposed, and enough evidence to know what production would require. Production is the work that follows.

How it’s taught

One case, end to end. A legal-document agent grows from first capability through retrieval, hardening, and packaging.

Debug what breaks. ClauseBot v0 fails differently as the workshop progresses; you diagnose and repair it.

Applied, not quizzes. Debugging, architecture design, and code review.

Other cases span software engineering, support, incident response, fintech, healthcare, and education.

Samir Joshi

Led by

Samir Joshi

Systems architect, engineer, and former software engineering faculty member. Three decades building and leading production systems across India, the US, and Europe, including senior roles at Mastercard and Nokia/HERE, and long-term engagements for Fidelity and Pearson. His work now focuses on the architecture and judgement required to put AI systems into dependable production.

Attend

Join the public workshop

Two days · Live online · Public cohort

Prerequisites: coding fluency, working knowledge of system design, and experience on complex projects. Price shared when you register interest; no commitment.

Register interest →

Run it for your team

Private · Online, in person, or hybrid

The same two days on your company's own codebase, architecture, and use case, under a mutually agreed NDA. Modules lift out as standalone sessions, and AWS and Azure productionization tracks extend the base.

Talk about a private workshop →

Register your interest and we’ll send the details, including price, with no commitment.

We use these details only to reply about this workshop. We never share them with anyone else, and you can ask us to remove them at any time.

Before you commit

Bringing confidential work?

In a public workshop, bring a project you’re free to discuss. Proprietary data never leaves your control (bring-your-own-key or local models throughout), and sensitive implementation detail should be sanitized before it comes into the room. The room runs on a Chatham House norm: what’s said in the room stays there, what’s learned travels. That norm is a working convention, not a legal instrument.

In a private workshop for your company, your real codebase and internal architecture are in scope, under a mutually agreed NDA. Nothing to sanitize, and nobody from another company in the room.

Which frameworks and protocols?

LangGraph in depth, with eight-plus others mapped: LangChain, OpenAI Agents SDK, Google ADK, AWS Strands, CrewAI, AutoGen, LlamaIndex, and low-code tools. Everything is written against patterns, so your stack can swap in underneath. MCP and A2A are both covered. The full syllabus has the rest.

Bring your project. We'll tell you honestly if an agent belongs in it.

Register interest

Running it for a team? Talk about a private workshop