I ship agentic AI to production. Then I teach your team to.
Four ways to move from talking about AI to shipping it.
Corporate training
Intensive, 80%-hands-on programs that take dev teams from AI-assisted coding to shipping production multi-agent systems. Working code every session.
See the programs 02Agentic AI consulting
Design and build your first production agent system — architecture, implementation, and a clean handoff to your team.
How it works 03Enterprise solutions
Reusable agentic patterns mapped to real business outcomes: support triage, document automation, internal copilots, and more.
Browse solutions 04Daily AI updates
What shipped in agentic AI today — curated and condensed with implementation notes for builders. One email on Thursdays.
Read the latest
Built and taught by someone who ran the transformation himself.
Not theory from a slide deck — patterns proven in production at Wan Buffer and on real client stacks.
- Trains development teams and consults with IT companies on production agentic AI
- Every engagement is customised to your tech stack and ships working deliverables
- Runs Wan Buffer — 20 people plus 150 agents in production
- Speaks on agentic AI for software CEOs, founders, and engineering teams
Invite Jigar to speak at your event.
Keynotes and hands-on workshops on agentic AI for engineering teams, software CEOs, and founder communities. Practical, demo-driven, and tailored to your audience, not generic AI hype.
Field notes from production agentic AI.
Agentic transformation is an operating-model problem, not a model problem
Microsoft published a 6-step playbook for rolling agents out across an enterprise, and the line that matters is "you do not need a bigger model, you need a better operating model." That matches what I see in consulting: the pilots that die do not die on model quality, they die on ownership, evals, and governance. Here is how I read the playbook for IT services teams, and the operating-model gaps that actually stall agent rollouts.
ReadThe anatomy of an AI agent: memory, tools, the loop, and guardrails
Strip the hype off an AI agent and four parts are left: a memory, a set of tools, a loop that decides what to do next, and a guardrail that vets every action before it runs. Here is what each part is for, the order they fail in, and where I have written about fixing each one.
ReadYour coding agent has amnesia. Persistent memory is the fix.
Claude Code forgets your architecture, your decisions, and why you ruled things out the moment a session ends. The reliability tax is not tokens, it is re-establishing context every morning. Here is what persistent agent memory actually is, how an open-source engine like Cortex implements it, and how to evaluate a memory layer for your own agents.
ReadCommon questions about agentic AI consulting and training.
What is agentic AI consulting?
It is hands-on help designing and shipping AI systems that take actions, not just answer questions. In practice that means scoping the right workflow, building the agent with reliable tools, evals, and guardrails, and handing your team a system they can run. I work mostly with IT services teams putting their first or second agent into production.
What does a corporate agentic AI training program cover?
A practical path from prompt to production agent: the agent loop, tool design, the Model Context Protocol, multi-agent orchestration, evals, and observability. Teams build real agents during the program rather than watching slides. Format and length are tailored to your team, from a focused two-day workshop to a multi-week cohort.
Which frameworks and tools do you build agents with?
Whatever fits the job, but the stack I reach for most is the Claude API, the Model Context Protocol for tools, Python and FastAPI, pgvector for retrieval, and an observability layer like Langfuse or OpenTelemetry. The point is matching the tool to the problem, not standardising on a framework for its own sake.
How long does it take to get an agent into production?
For a bounded, well-scoped workflow, a working agent in front of real users in about 90 days is realistic, with the agent and its operating layer of evals, observability, and guardrails built together. What stretches timelines is rarely the model. It is unclear scope, messy data, and a security review that arrives late.
Do you work with teams outside India?
Yes. I am based in Ahmedabad and work with teams across India and remotely worldwide. Consulting and training are delivered in person or remotely depending on what suits your team.
Let’s build with agentic AI.
Tell me about your team and what you want to ship. Or email [email protected].