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.
Thoughtworks launches Agent/works to govern enterprise agent fleets across any cloud
Agent/works gives enterprises a single multi-cloud control plane and governed runtime for AI agents, replacing human access controls with capability-based, scope-bound, time-limited permissions plus pre-execution compliance checks.
read →Databricks Unity AI Gateway adds SQL-defined governance for AI agents
The Unity AI Gateway brings agent traces and monitoring via LakeWatch and lets enterprises express contextual security policies for agents directly in SQL.
read →Databricks introduces LTAP, unifying transactional and analytical data for agents
Lake Transactional/Analytical Processing keeps operational and analytical workloads on one data copy, while Lakebase gains git-style branching, cross-cloud disaster recovery, and autonomous database operations for agents.
read →Databricks partners with SpaceX to put Grok natively on the platform, adds Kimi
Databricks will make xAI Grok models natively available through a SpaceX partnership and added Moonshot Kimi support alongside OpenAI, Anthropic, Gemini, and Qwen.
read →OpenAI launches Partner Network with $150M commitment
OpenAI commits $150M to a new global Partner Network and targets 300,000 certified consultants by end of 2026, betting that implementation and integration win enterprise deals over raw model power.
read →Lakebase Search brings agent-native hybrid retrieval into Postgres
Lakebase Search combines vector and full-text retrieval in one SQL query via reciprocal rank fusion, reporting 95.5% recall@10 at 30ms P99 on 100M vectors with instant indexing for the agent read/write loop.
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