Perf detail from README: outlook_batch_triage uses Graph's /$batch endpoint, not per-message calls. 10-20× faster on bulk ops! When your agent is processing 50 newsletters or triaging an overnight inbox, this is the difference between "wait for it" and "done."
Agent builders: outlook-mcp v1.5.2 — 54 typed Graph tools (mail, calendar, contacts, tasks, drafts, attachments).
Still the only first-class MCP server in the personal-Outlook space. Everything else is bash scripts the agent has to parse stdout from.
https://t.co/mv7R242zDp
Thanks @OmarShahine and @BradGroux! It's also published on https://t.co/X0oVc86eIi
Personal accounts only. Currently 52 tools across mail and calendar. My agent has been using it and doing super helpful things with it.
Not affiliated, endorsed, or supported by MSFT. ;)
🦞 TL;DR: New Job at Microsoft. Bringing OpenClaw + personal agents to Microsoft 365!
My goal is to help usher in a new generation of workplace proactive assistants, ones that lighten your load by taking on tasks end-to-end, and that can also step in proactively when they can help.
As part of this mission, I’ll be partnering with the @OpenClaw + M365 community to bring the energy of this work to our customers. We’ve already hit the ground running with a fully integrated Teams plugin for OpenClaw, and I can’t wait to help usher in the era of personal agents at work.
"if a picture is worth a thousand words, a prototype is worth, well, at least millions."
I've used this statement almost verbatim in recent months within the @Outlook team. We've had several PMs show super impressive examples of this being the new reality.
Track costs across 12 platforms via Claude Code. Ask one question, get your burn rate.
I kept logging into a bunch of different dashboards just to figure out what I spent. Built an MCP to fix it. It's called burnmeter. 🔥
Free, open source.
/btw wait did we write any tests
Claude: “You said TDD was non-negotiable at the start of this conversation. We have written zero tests.”
Built different. Ouch.
This has never been more true. AI doesn’t replace the doing — it just makes starting cheaper.
The people actually building right now have never learned faster. 🧠
The reality is openclaw has been for the innovators at the bleeding edge on the adoption curve.
Not surprising we're seeing companies consumer-fying the claw-like agent setup. Very cool.
Introducing Base44 Superagents.
AI agents built with managed infrastructure, secured by default, one-click integrations, and 24/7 execution from the start.
Everything is taken care of so you can focus on what your agent does, not how to get it running.
That means no API keys to juggle, no config files, no security setup, and no maintenance. We handle all of it.
Your Superagent connects to all the tools you already use in one click, runs on schedules and triggers, remembers context across sessions, acts proactively on your behalf, and keeps working around the clock.
All from wherever you already are, WhatsApp, Telegram, Slack, or your browser.
The AI agent everyone's been waiting for, with everything you need already built in.
We're excited to get this into your hands, so we're giving free credits to everyone who comments and reposts in the next 24 hours.
We're experiencing issues with Claude Code and https://t.co/6PWRu97AJ0 where some users may not be able to log in & others may experience slower than usual performance.
We're on it and working hard to bring service back to normal, thanks for bearing with us.