🤖 Live Workshop · Limited to 30 Seats

AI Agents Workshop

From Business Requirements to Production

Stop building demos. Start shipping agents that think, recover, and scale. Build a real multi-agent system — layer by layer — over 2 intensive days.

📅 25 Apr & 1 May 2026 · 10 AM–6 PM
🐍 LangGraph + Claude
☁️ AWS / Azure
Register Now — ₹15,000
10 modules · 10 live labs · 1 deployed system · Portfolio-ready by Day 2
10
Hands-on Labs
8
Failure Modes Covered
6
Multi-Agent Topologies
2
Days to Production-Ready

What You'll Learn

Six competencies. Every one of them directly employable.

🧠
Agent Architecture
Decompose any business problem into a perception-reasoning-action loop. Understand when agents are the right tool — and when a simpler approach would win.
🔁
Top 4 Agentic Patterns
Master Tool Use, ReAct, Reflection, and Planning — the four patterns covering 95% of real-world agents. Learn each as a design decision, not a recipe.
🛠️
Tool Design, MCP & LangGraph
Design tools with instructive errors. Build and consume MCP servers. Peel back create_agent to raw LangGraph — Subgraph, Command, Send, middleware.
🕸️
Multi-Agent + A2A + Frameworks
Six topologies. Agent-to-Agent protocol. Compare LangGraph, CrewAI, AutoGen, Google ADK, Microsoft Agent Framework, Claude Agent SDK, Strands. Dynamic Composition.
🛡️
Self-Healing Agents
Diagnose and recover from the 8 canonical failure modes. Implement circuit breakers, retry loops, escalation patterns, and prompt injection defences.
🚀
Production Deployment
Deploy to AWS and Azure with real security. Build LangSmith observability, LLM-as-judge evaluation suites, and a portfolio that gets you hired.
✨ The Golden Thread
One platform. Five agents. Ten layers of sophistication.
Every module builds on a single enterprise system — the Incident Intelligence Platform. Five specialist agents form a pipeline: 🔔 Alert Triage → 🔍 Investigation → 🧠 Root Cause → 🛠️ Resolution → 📋 Post-Mortem. It starts as a single triage agent on Day 1 morning. By Day 2 evening, it is a deployed, self-healing, multi-agent system with episodic memory, constitutional safety rules, an eval suite, and a live webhook trigger. Every engineer has lived through incidents — now you build the system that handles them.

The Curriculum

10 modules across 2 days. Concept → Demo → Lab in every session.

Day 1 — Design & Build
10:00 AM
M0
👋 Kickoff
Welcome, stack setup, smoke test, 2-day map. Every learner has API keys working and a green smoke test before M1 starts.
10:30 AM
M1
🧩 What Is an AI Agent? + First Agent Running
Traditional AI vs Agentic AI. The agent loop (Observe → Decide → Act). The six components (tools, memory, knowledge, reasoning, orchestration, planning). Where agents run. Lab: Run your first agent with create_agent. By 11:30 every learner has a working agent in their own Colab.
11:30 AM
M2
🔌 How LLMs Use Tools + Alert Triage Agent
The tool-use mechanic. Good tool design (name, schema, docstring, return). Structured output. 3-layer validation (schema, semantic, business-rule). Confidence calibration. Lab: Build the Alert Triage Agent — the first of 5 Incident Intelligence agents.
2:00 PM
M3
🌐 Interaction Surfaces + Tools Ecosystem
How humans and systems invoke agents — web chat, Slack, Telegram, mobile, API, webhooks, message queues. Multi-modal input (text, image, audio, video). Tools: REST APIs, databases, RAG, code execution, MCP. Lab: Build and run your own MCP server with 3 tools; consume it from your agent.
3:30 PM
M4
🛠️ LangGraph Intermediate
Peel back the curtain. What create_agent does under the hood. StateGraph, Nodes, Edges, Conditional Edges. Subgraph, Command, Send. Middleware (wrap_model_call, wrap_tool_call). Lab: Rebuild the Alert Triage Agent from raw LangGraph primitives. Compare traces.
4:30 PM
M5
🔁 Top 4 Agentic Patterns + Multi-Agent Preview
Tool Use, ReAct, Reflection, Planning. When each wins. How each fails. Six multi-agent topologies preview (deep dive Day 2). Lab: Build the Investigation Agent using ReAct. Wrap it with Reflection. Measure the quality delta.
6 Core Concepts Covered on Day 1
🧩
create_agent & the Agent Loop
LangChain 1.x high-level API. Observe-Decide-Act. Six components of every agent
🔌
Tools, Structured Output, MCP
Tool design, 3-layer validation, confidence calibration. Build your own MCP server
🌐
Interaction Surfaces
Slack, Telegram, mobile, webhooks, queues. Multi-modal: text, image, audio, video
🛠️
LangGraph Intermediate
StateGraph, nodes, conditional edges, SubGraph, Command, Send, middleware
🔁
Top 4 Agentic Patterns
Tool Use, ReAct, Reflection, Planning — when to use each and how they fail
🔎
LangSmith Tracing
Observability from minute one. Every lab traced. Debug with real data
Day 2 — Harden, Evaluate & Ship
10:00 AM
M6
🧠 Context Engineering + Memory
Context engineering as a craft: prompting, query augmentation, retrieval, tools as context, agents as context providers. 4-layer memory model. Durable checkpointing. HITL with interrupt(). Memory scaling in production. Lab: Build the Root Cause Agent. Add episodic memory so the system learns from past incidents.
11:30 AM
M7
🕸️ Multi-Agent Deep Dive + A2A + Frameworks
The centrepiece of Day 2 (2 hours). Six canonical topologies. A2A protocol. Framework comparison: LangGraph, CrewAI, AutoGen, Google ADK, Microsoft Agent Framework, Claude Agent SDK, Strands Agents. Dynamic Composition. Lab: Wire all 5 Incident Intelligence agents with a Supervisor topology. Add Dynamic Composition.
2:30 PM
M8
🛡️ Self-Healing + Constitutional + Metacognition
The 8 canonical failure modes. Circuit breakers, prompt injection defence, cascading failure prevention. Constitutional AI enforced as middleware. Metacognition with calibrated confidence. Agent autonomy levels (L1-L4). Operational risk management. Lab: Inject 3 failures; add 5 Constitution rules; add metacognitive gates.
4:00 PM
M9
📊 Observability + Evaluations
LangSmith traces, datasets, annotations. Golden datasets. LLM-as-judge with rubrics. Calibration measurement. Regression detection in CI. Lab: 10-case golden suite. 3 evaluators. Run baseline. Find a failure. Fix it. Prove the improvement with data.
5:00 PM
M10
🚀 Deployment + Road Ahead
Deployment landscape: AWS Lambda, AWS Bedrock AgentCore, Azure Functions, Vertex AI, Groq. Serverless vs containers. War stories from production. Interview prep. Lab: Deploy the Incident Intelligence Platform. Public URL. Live webhook. Production LangSmith traces.
7 Advanced Concepts Covered on Day 2
🧠
4-Layer Memory + Scaling
In-context, session, episodic, semantic. Pruning, sharding, hot/cold tiers in production
🕸️
Multi-Agent Topologies + A2A
6 topologies. Agent-to-Agent protocol. Handoff contracts. Dynamic composition
📚
Framework Landscape
LangGraph, CrewAI, AutoGen, Google ADK, Microsoft Agent Framework, Claude SDK, Strands
🛡️
8 Failure Modes + Agent Autonomy
Circuit breakers, prompt injection defence. L1-L4 autonomy. Operational risk management
🏛️
Constitutional AI + Metacognition
Rules enforced by middleware. Calibrated confidence. Agents that know when they don't know
📊
LLM-as-Judge Evals
Golden datasets. Automated scoring. Calibration measurement. Regression guard in CI
🚀
Production Deployment
AWS Lambda, AWS Bedrock, Azure, Vertex AI, Groq. Serverless vs containers. War stories

Patterns That Set You Apart

Day 2's advanced module covers what separates agent engineers from agent users.

🏛️
Constitutional AI
Agents that operate under explicit principles and self-audit every output. Essential for compliance and regulated industries.
🤔
Metacognition
Agents that know when they don't know — and hand off gracefully rather than fail silently. Below threshold: escalate, don't guess.
⚙️
Dynamic Composition
Orchestrators that assemble the right agents at runtime from a registry. The pattern for truly open-ended workloads.

Your Instructor

Built by someone who ships, not just teaches.

🧑‍💻
Sridhar Jammalamadaka
Founder, FutureProof India · AI Architect
  • 💼 16 years in IT — former Software Architect at Oracle, M.Tech from IIIT Bangalore
  • 🤖 Built 30+ AI agents and 50+ AI chatbots for enterprise clients across healthcare, finance & legal
  • 🎓 Trained 1,400+ professionals in Agentic AI, RAG, and LLM Engineering
  • 🏛️ Trainer at IIIT Bangalore Executive Education
  • 🌎 AI Consultant serving India, Dubai & USA
  • 📚 Curriculum aligned with Anthropic's hiring benchmark & Gulli's Agentic Design Patterns

Who Is This For

Two lab modes: Builder (write code) and Strategist (write the spec). Both produce real artefacts.

👨‍💻
Backend / Full-Stack Engineers
Ready to go beyond LLM wrappers and ship real agent systems that survive production.
🤖
AI/ML Practitioners
Already working with LLMs, want to master production agent architecture and deployment.
💼
Tech Leads & Architects
Need to design agent systems and evaluate technical proposals. The Strategist track is built for you.
🎓
Ambitious Builders
Want a portfolio that gets noticed at Anthropic, Google DeepMind, Microsoft AI.

What's Included

Everything you need to go from zero to deployed.

✅ 2 full days live instruction (10 AM – 6 PM)
✅ 10 hands-on labs with LangGraph + Claude
✅ LangSmith workspace with all traces
✅ Deployed 5-agent Incident Intelligence Platform on AWS or Azure
✅ Architecture Decision Record template
✅ Evaluation suite template (LLM-as-judge)
✅ Lifetime recording access
✅ Telegram community + 14-day practice challenge
✅ Portfolio review session
✅ Certificate of completion

Prerequisites

Lower bar than you think.

🐍
Python
Comfortable with functions and libraries. No ML needed.
🌐
REST APIs
Know what an API call is. Everything else covered from scratch.
💻
Laptop + Browser
Everything runs in the cloud. No complex local setup.
No prior agent experience needed. No LangGraph knowledge required. No ML background. If you've written a Python function and called an API, you're ready.

Secure Your Seat

30 seats. Once full, that's it.

Workshop Pass
₹15,000
per person · GST included
  • ✅ 2 full days of live instruction
  • ✅ 10 hands-on labs with LangGraph + Claude
  • ✅ Deployed 5-agent Incident Intelligence Platform on AWS/Azure
  • ✅ Architecture Decision Record + Eval templates
  • ✅ Lifetime recording access
  • ✅ Telegram community + 14-day practice
  • ✅ Portfolio review session
  • ✅ Certificate of completion
Register Now — Secure Your Seat
🔥 Only 30 seats available
Full refund available up to 48 hours before Day 1.

Frequently Asked Questions


Is this for beginners or experienced engineers?+
Both. Every lab has Builder mode (write LangGraph code) and Strategist mode (write the requirements spec). Beginners build confidence on Day 1, experts hit Constitutional AI, Metacognition, and Dynamic Composition on Day 2.
Do I need to know LangGraph before attending?+
No. We cover LangGraph from scratch in Module 1. If you know Python and have made an API call, you're ready. You'll have a working agent within 90 minutes.
How is this different from other AI agent courses?+
Three things: (1) One enterprise-grade golden-thread project — a 5-agent Incident Intelligence Platform — across all 10 modules. (2) Chaos engineering — deliberately break your agents and watch them recover. (3) Aligned with Anthropic's engineering hiring benchmark.
Will I actually deploy a real agent by the end?+
Yes. Module 10 is a deployment lab. You'll deploy the full 5-agent Incident Intelligence Platform to AWS or Azure, trigger a live incident via webhook, and watch all agents respond in LangSmith traces. You leave with a running URL, not a notebook.
What if I can't attend live?+
Lifetime recording access included. All labs have written instructions. Telegram community stays active. 14-day practice challenge keeps you on track.
What's the refund policy?+
Full refund if requested more than 48 hours before Day 1. No refunds after that, but lifetime recording access ensures full value.

Ready to Build Agents That Actually Work?

10 modules. 10 labs. One deployed system. Portfolio-ready by Day 2.

📅 25 Apr & 1 May 2026
⏰ 10:00 AM – 6:00 PM
🐍 LangGraph + Claude
🔥 30 Seats Only
Register Now — ₹15,000
📧 connect@futureproofindia.com · 💬 Telegram Community