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.
Databricks Document Intelligence functions reach GA
In-platform PDF and document processing functions are now generally available, and Databricks Agent Tools agentic search is benchmarked 3x faster.
read →OpenClaw graduates v2026.6.8 to stable
OpenClaw promoted its recent beta line to a stable v2026.6.8 release.
read →Arcade.dev raises $60M Series A for agent action layer
Arcade.dev raises a $60M Series A for its secure action layer that gives production AI agents scoped user-level authorization and a full audit trail of every action they take.
read →Microsoft taps AWS for GitHub capacity as AI coding surges
After AI-driven traffic outran Azure and triggered repeated outages, Microsoft adds AWS capacity for GitHub, which is now processing 275M commits per week, on pace for 14B in 2026 versus 1B in all of 2025.
read →OpenClaw ships v2026.6.8-beta.2
OpenClaw v2026.6.8-beta.2 brings richer Telegram and WhatsApp delivery with structured rich text, tables and ACP bindings, plus sharper agent and gateway recovery for media completions and auto-reply final sends.
read →Anthropic Agent SDK billing split goes live, ending flat-rate subsidised automation
From June 15, programmatic Claude usage (Agent SDK, claude -p, Claude Code GitHub Actions, third-party frameworks like OpenClaw) moves off the Pro/Max subscription into a separate capped credit pool ($20/$100/$200 by plan) metered at full API rates with no rollover. Automated requests stop when it runs out unless overflow billing is enabled.
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