
AI and Automation
AI agents, MCP, AI-native products, Claude and Anthropic stack, automation pipelines.


Vetting third-party MCP servers: 7 checks before production
The official MCP Registry listed 53,756 active servers on 2 November 2026 and scans none of them. Seven checks to run before one reaches production.
AI-native studio vs traditional agency: cost and speed in 2026
AI made one coding task 55.8% faster and slowed experienced developers 19% on mature code. Where an AI-native studio costs less and ships faster than an agency.
Claude Partner Network tiers: what Select and Preferred prove
Select asks for 10 active certified people and 2 customers in production, Preferred for 100 and 15. What each Claude partner tier proves and what it leaves out.
Embedding AI agents in SaaS: 6 product decisions for 2026
Gartner expects 40% of enterprise apps to embed task-specific AI agents by end of 2026. Six product decisions separate agents that ship from agents that stall.
A2A protocol: how to design an agent API other agents can call
A2A v1.0 shipped in March 2026. Six design steps for an A2A server: Agent Card, outcome skills, eight task states, bindings, per-call auth, versions.
Agentic web design: what to change when agents do the buying
Gartner puts 90% of B2B buying through AI agents by 2028, over $15 trillion. Here is what changes in a product's data, feed and checkout.
WebMCP in 2026: the browser API that lets agents use your SaaS UI
WebMCP lets a web page register tools that browser AI agents call directly. Chrome 149 runs it as an origin trial. What it changes for SaaS interfaces.
Context engineering: what it is and how to do it for AI agents
Context engineering decides what fills a model's context window. Get it wrong and accuracy drops 39% across multi-turn tasks, whatever the prompt says.
MCP governance in 2026: what the Linux Foundation handoff changed
Anthropic donated MCP to the Linux Foundation in December 2025. Who decides the spec now, what the 2026-07-28 release removed, and what to check.
AI feature token cost: budget it before it eats your margin
Traditional SaaS runs 80% gross margin; AI-native products sit near 52%. The gap is token cost. Here is how we budget AI features so margins hold.