Insights & Essays.
Field notes for CTOs and principal engineers: what shipped, what failed, and how to staff the next AI program. Depth first — no vendor recap.
Latest Articles
TanStack Start 1.0 Is Stable: What You Commit To (Vite 8, Validators, Sessions)
TanStack Start 1.0 is officially stable. Explore the production architecture: Vite 8 Environment API, Standard Schema validators, BYO session pipelines, and the Next.js 16 decision matrix.
Angular 20 Security Support Ends 28 Nov 2026: The Upgrade Path to 22
Angular 20 security support officially ends on 28 November 2026. Follow this production runbook to execute safe sequential hops to Angular 21 and 22, resolve breaking changes, and protect compliance.
Vectorless RAG: Let the Model Read the Table of Contents Before It Searches
An in-depth technical analysis of vectorless RAG, PageIndex, and MarkIndex. Discover why hierarchical document trees beat cosine similarity for structured enterprise knowledge.
VMO vs PMO: Turning Delivery Offices into Value Management Engines
Discover why traditional RAG dashboards are dying and how leading enterprises replace delivery-focused PMOs with Value Management Offices (VMOs) to govern…
The Brief as Machine-Routable Work Unit: Replacing Tickets with Verification-Driven Outcomes
Discover why traditional Jira and Linear tickets fail autonomous AI agents, and how modern PM 3.0 product organizations replace activity tracking with…
Google Antigravity: Read the Plan, Then the Rules Budget
A deep technical analysis of Google Antigravity v2.17.0 and v2.18.1. Explore /plan review policies, the 20,000-token rules budget, Customizations plugins tab, and .gemini/config.json.
Contextual Embeddings That Retrieve the Evidence, Not Just the Answer: Perplexity's Late-Chunking Architecture, pplx-embed-v2-context-9b-preview, and Multi-Evidence Synthesis
An in-depth architectural breakdown of Perplexity's pplx-embed-v2-context-9b-preview, late chunking across 32k tokens, 1024-d int8 vectors, and empirical…
Kiro Workflows: Graphs of Agents, Not Another Spec File
A deep technical analysis of Kiro Workflows launched Sep 30, 2026.
AG-UI 1.0: The Open Event Protocol That Connects Any AI Agent to Any Application Interface
An in-depth technical analysis of CopilotKit's AG-UI 1.0 protocol specification, JSON Schema event streams, multimodal tool results, and the MCP-A2A-AGUI triad.
What is the Vatsal Shah blog about?
Long-form articles on agentic AI, production LLM architecture, cloud engineering, delivery and technical leadership, written by Vatsal Shah. Each article has its own title, publish date and canonical URL, and links to related case studies, frameworks and playbooks on this site.
Are the articles free to read?
Yes. Every article is free to read with no paywall and no sign-up. The weekly newsletter is optional for readers who want new articles and an India lens on AI regulation by email.
How is the blog organized?
Articles are grouped by category and tag, and each one links to related reading so a topic can be followed from an explainer to a framework, a playbook or a case study.
Can I quote or republish an article?
You may link to any article and quote short excerpts with attribution to Vatsal Shah and shahvatsal.com. Republishing substantial content or scraping the blog requires written permission under the terms of use.
How can I discuss an article with the author?
Use the contact form at /contact and say which article you mean. Choose the focus that fits: consulting, a software or application project, hiring, or a speaking session. Replies usually arrive within 24 to 48 hours.
External Standards & Publications
Our engineering publications follow industry standards for software architecture and agentic AI systems. Read more about technical specifications at the IEEE Standards Association and general web engineering principles at the World Wide Web Consortium (W3C).
What is “AG-UI 1.0” about?
An in-depth technical analysis of CopilotKit's AG-UI 1.0 protocol specification, JSON Schema event streams, multimodal tool results, and the MCP-A2A-AGUI triad.
Who wrote this article and when was it published?
Written by Vatsal Shah, an AI Leader and Solution Architect based in Ahmedabad, India, and published on September 30, 2026. Reading time is 18 min read. It is filed under AI & Engineering Practices.
How can I apply this in my own organization?
Use the sections of this article as a working checklist, adapt each step to your platform and risk profile, and record the decisions you make. To discuss AG-UI 1.0 for your team, request a briefing at https://shahvatsal.com/contact.