Top story · Daily AI intelligence
OpenAI published Agent Plugins 1.0, an open format that bundles Agent Skills and MCP servers into portable plugins any compatible client can discover and load. A steering committee of OpenAI, Amazon, Microsoft, Cursor, and Vercel backs it, Google joined as a core maintainer, and ChatGPT, Codex, Cursor, GitHub Copilot, and VS Code support it at launch.
01 / Insights
Daily AI analysis
What we're reading and thinking about. Refreshed daily.
OpenAI releases LifeSciBench, a 750-task life-science research benchmark
LifeSciBench was authored and reviewed by 173 working scientists across seven research workflows. Tasks are free-response and even the strongest model passes only about one in three.
read →OpenAI and Molecule.one demo a near-autonomous AI chemist on GPT-5.4
The agent improved a hard medicinal-chemistry reaction, a concrete look at AI agents running real lab R&D rather than just suggesting steps.
read →Google publishes the Agentic Resource Discovery open specification
ARD is an Apache-2.0 standard for publishing, discovering and verifying AI capabilities across the web, built on the Linux Foundation AI Catalog data model.
read →Google details A2UI plus MCP Apps patterns for agent front-ends
Three architectural patterns let agents serve native, brand-consistent UIs directly over MCP servers or embed stateful iframe apps inside declarative views.
read →Databricks Agent Bricks becomes a full governed agent platform with multi-agent Supervisor
At Data + AI Summit, Databricks expanded Agent Bricks into a comprehensive platform spanning model choice, context, and control, adding a Supervisor Agent for multi-agent orchestration, MCP in Unity Catalog, Lakebase-backed agent memory, and any-harness support. Over 100k agents have been built on it.
read →Microsoft Work IQ APIs reach general availability
Microsoft makes its workplace intelligence layer for agents generally available, exposing M365 people, email, meetings and files via Chat, Context, Tools and Workspaces plus A2A, a remote MCP server and a REST API, billed on consumption through Copilot Credits.
read →02 / Weekly Deep Dive
How agents actually ship
One researched edition a week: real deployments, the stacks behind them, and the honest counter-facts.
Caylent builds its own agent orchestrator and cuts a 2,600-hour migration to 220
Instead of buying a migration tool, Caylent built a multi-agent orchestrator on the Claude Agent SDK that runs inside the customer's own cloud and cut one engagement from 2,600 engineering hours to about 220.
Eve makes the buy-a-vertical-vendor case for small plaintiff law firms
Plaintiff firms with no in-house ML team buy their agents off the shelf, and Eve customers report large jumps in lead conversion, case value, and drafting speed.
Suzano puts a natural-language-to-SQL agent in front of 50,000 staff
A Brazilian pulp-and-paper maker built a Gemini agent that turns plain-language questions into SQL, which Google Cloud says cut query time by about 95 percent for 50,000 employees.
03 / Latest project
MomMe, a lifestyle community, web & iOS
A full lifestyle community platform, web portal and native iOS app, taken end to end, with an AI moderation flow keeping the community safe at scale.
- MomMe web portal + iOS application
- Full lifestyle community with 3,000+ registered users
- AI moderation flow
04 / Contact
Get in touch
Questions, ideas, or a project in mind? Send us a note and we'll get back to you, usually within a day.
hello@kmmt.ai