Monday 30 June – Tuesday 1 July 2026 · Ahmedabad
Agentic AI Foundation Program — Essentials
Program 01 · 2-day corporate cohort
View recap21 Oct 2026 · Anthropic opens a Claude Duet research preview: a proactive agent with a background VM and approval gates
21 Oct 2026 · Google Cloud adds GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Luna to Model Garden in private preview
20 Oct 2026 · DeepSeek open-sources DeepInfer: Apache 2.0 offline inference for Flash-1017 on SM100 and Ascend 950
20 Oct 2026 · llm-d 1.0 ships agent-aware distributed inference: session routing, multi-tenant QoS, and a v1 config API
20 Oct 2026 · DHS publishes a FASCSA order excluding DeepSeek products from US federal civilian IT and procurement
19 Oct 2026 · MiniMax ships M3.1 Flash: cheaper, faster agent and computer-use inference at $0.15 / $0.60 per million tokens
19 Oct 2026 · GitHub Copilot retires Gemini 3.7 Flash, GPT-5.x, and Grok 4.5 across chat, agent, and completions
21 Oct 2026 · GitHub CLI adds opt-in expiring OAuth tokens
21 Oct 2026 · GitHub details architecture for agent-scale Git infrastructure
20 Oct 2026 · Google expands Gemini capabilities for Android Auto and small business
Guide · MiniMax M3.1 Flash: a cheaper agent and computer-use worker lane
Guide · Claude Duet: Anthropic’s proactive agent for professionals, with approval still in the loop
Daily agentic AI updates in the WhatsApp community. Join from /card
21 Oct 2026 · Anthropic opens a Claude Duet research preview: a proactive agent with a background VM and approval gates
21 Oct 2026 · Google Cloud adds GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Luna to Model Garden in private preview
20 Oct 2026 · DeepSeek open-sources DeepInfer: Apache 2.0 offline inference for Flash-1017 on SM100 and Ascend 950
20 Oct 2026 · llm-d 1.0 ships agent-aware distributed inference: session routing, multi-tenant QoS, and a v1 config API
20 Oct 2026 · DHS publishes a FASCSA order excluding DeepSeek products from US federal civilian IT and procurement
19 Oct 2026 · MiniMax ships M3.1 Flash: cheaper, faster agent and computer-use inference at $0.15 / $0.60 per million tokens
19 Oct 2026 · GitHub Copilot retires Gemini 3.7 Flash, GPT-5.x, and Grok 4.5 across chat, agent, and completions
21 Oct 2026 · GitHub CLI adds opt-in expiring OAuth tokens
21 Oct 2026 · GitHub details architecture for agent-scale Git infrastructure
20 Oct 2026 · Google expands Gemini capabilities for Android Auto and small business
Guide · MiniMax M3.1 Flash: a cheaper agent and computer-use worker lane
Guide · Claude Duet: Anthropic’s proactive agent for professionals, with approval still in the loop
Daily agentic AI updates in the WhatsApp community. Join from /card
Agentic AI architect · Trainer · Builder
I ship agentic AI to production. Then I teach your team to.
Jigar Joshi
15+ years · 150+ agents in productionWork with me How I help teams
Four ways to move from talking about AI to shipping it.
01
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
About Jigar
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
15+
years in software, ERP & AI
8+
IT services teams trained
150+
agents in production
40%
faster delivery after training
Keynotes & workshops
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.
From the blog
Field notes from production agentic AI.
MiniMax M3.1 Flash: a cheaper agent and computer-use worker lane
On October 19, 2026 MiniMax launched M3.1 Flash on its API, M Plan, and MiniMax Code with $0.15 / $0.60 list prices, vendor claims of 70% lower agent-task cost, and stronger coding and computer-use scores. This guide covers what shipped, what remains closed-weight, and how to re-bench the cheap worker lane.
ReadClaude Duet: Anthropic’s proactive agent for professionals, with approval still in the loop
On October 21, 2026 Anthropic opened a Claude Duet research preview for US Pro and Max subscribers. Duet is a proactive Opus 5.5 agent with a background VM, Marketplace connectors, and hard approval gates on send, pay, sign, and delete. This guide covers what it is, what it is not, and how enterprise teams should trial it.
ReadAgent-Scale Git: Why Your Repository Architecture Breaks Under Autonomous Load
GitHub's new engineering deep dive reveals how traditional Git infrastructure fails under the high-frequency, small-commit patterns of autonomous agents. Here is what builders need to know about repository integrity at scale.
ReadFAQ
Common 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 jigar@wanbuffer.com.
Or get the weekly agentic AI brief