Training

Hands-on GenAI training, taught by a practitioner.

Programs built from shipping AI to tens of thousands of engineers. Every session is practical, customised to your stack, and ends with something your team has actually built.

On-site in Bengaluru, or travel across India and abroad Live virtual cohorts across time zones Customised to your stack, tools and codebase Post-training office hours and follow-up clinics
Program 01

AI Coding Agents in Practice

Go beyond autocomplete. Engineers learn to delegate real work to Claude Code, Codex or Cursor — safely, reviewably and on your own codebase.

Software engineers, tech leads, QA and DevOps

1–2 days · hands-on · up to 30 per cohort

Participants will

  • Ship a real ticket end-to-end with an agent, in your repo
  • Write effective CLAUDE.md / AGENTS.md project context
  • Use skills, hooks, subagents and MCP tools responsibly
  • Know what not to send to a model, and why

Modules

  1. 01How coding agents actually work: context, tools, loops
  2. 02Context engineering and project memory files
  3. 03Test generation, refactoring and legacy-code workflows
  4. 04Agentic code review and PR hygiene
  5. 05Skills, hooks, subagents and MCP servers
  6. 06Security, sensitive data and supply-chain hygiene
  7. 07Measuring impact without vanity metrics
Program 02

Building Production RAG & Agents

The engineering behind assistants that answer correctly — and know when not to. Built from lessons shipping DeX across 70+ platforms.

ML, platform and backend engineers

3-day bootcamp · capstone project · up to 20 per cohort

Participants will

  • Design an ingestion and retrieval pipeline that stays fresh
  • Build an agentic flow with answerability and critique steps
  • Stand up an eval harness that gates every release
  • Operate it: observability, guardrails, cost

Modules

  1. 01Ingestion, chunking and metadata strategy
  2. 02Embeddings, hybrid search and reranking
  3. 03Agentic retrieval: rewrite, answerability, critique, summarise
  4. 04Evals: golden sets, LLM-as-judge, online feedback
  5. 05Guardrails and sensitive-data handling
  6. 06Observability with OpenTelemetry
  7. 07Model routing, caching and cost control
  8. 08Capstone: ship an assistant on your own docs
Program 03

GenAI for Engineering Leaders

What actually changes in your org when AI writes and reviews code — and how to lead it with numbers, not hype.

CTOs, VPs, Directors and engineering managers

Half-day workshop · in person or virtual

Participants will

  • A 90-day adoption plan for your organisation
  • A metrics framework your CFO will accept
  • Clarity on build vs. buy and vendor lock-in
  • A working model with Risk, Cyber and Legal

Modules

  1. 01The 2026 landscape: agents, coding tools, platforms
  2. 02Where ROI shows up — and where it doesn't
  3. 03Adoption playbooks and change management
  4. 04Governance and risk partnership models
  5. 05Team design and skills for the agentic era
Program 04

Secure & Governed GenAI

Threat-model LLM apps and agents, instrument them for audit, and rehearse your first AI incident before it happens.

Security, GRC, platform and risk teams

1 day · workshop + tabletop exercise

Participants will

  • A threat model for your AI estate
  • Logging and detection patterns for AI usage
  • An AI incident-response runbook
  • A mapping to ISO 42001, NIST AI RMF and DPDP

Modules

  1. 01Prompt injection, data leakage and tool abuse
  2. 02MCP and agent supply-chain risk
  3. 03Identity, RBAC and non-human access
  4. 04Cyber logging, attribution and SOC detections
  5. 05Regulatory landscape: EU AI Act, DPDP, sector rules
  6. 06Tabletop: an agent goes wrong
Work with me

Plan a training for your team.

Tell me who's attending, what tools you use and what you want them to do differently afterwards. I'll send an outline and a fixed quote.

Book a call er.kushbatra@gmail.com WhatsApp LinkedIn