Think inside your AI world.
Microsoft Teams through Unl
Teams will hand back every message in the channel, in order, replies included. Whether one of those messages was an actual decision or just someone thinking out loud is a distinction Teams doesn't draw.
Microsoft Teams through Unl reads channel messages, threads and members against the decision-recorded criterion you have ratified, so 'did we actually agree on this' comes back fit-or-flag with the condition the thread hasn't met.
What Microsoft Teams holds
Naked, Microsoft Teams through Unl reads real messages, not a meeting summary:
- List messages in a channel, with replies expanded
- List the channels in a team
- Retrieve a chat or a channel message by ID
- List the members of a channel or chat
- List chats and their messages for the signed-in user
What the naked read gives you
Ask Microsoft Teams through Unl what was said in the #pricing channel this week and it returns every message in order, replies threaded underneath. That's an honest transcript. It doesn't know that your team only treats a message as a decision when it comes from the deal lead and gets a thumbs-up reply from finance - Teams reads the words, not which ones were binding.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when Microsoft Teams is read measured
Say you run deal desk, and you have ratified in Unl that a pricing decision counts as recorded only when the deal lead posts the number in #pricing and finance replies with an explicit thumbs-up or 'confirmed' in the same thread - after a discount got treated as approved from a comment that was actually a question.
'Did we agree the 15% discount for the client?' returns, measured: unmet - the deal lead's message proposing 15% sits in the thread, but finance's reply reads 'let's discuss Monday', not a confirmation, so the condition isn't met. Teams supplied the message and the reply; the ratified rule supplied the confirmation condition that turns a thread into a verdict.
And back again
When finance posts the confirming reply on Monday, you log the outcome in Unl, and the next 'did we agree the discount' question for that deal returns a met verdict instead of re-reading the same thread.
The answer comes back measured against what you already decided, and why.
The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Questions people ask
What makes a Teams message a 'decision' rather than a comment?
The confirmation condition your team ratified, not the message's tone. Here, a proposal only counts as decided once the deal lead posts it and finance replies with an explicit confirmation in the same thread - Teams shows the messages, the ratified rule decides which exchange counts as binding.
How do I connect Microsoft Teams to Claude?
Microsoft's Work IQ Teams MCP server, part of Microsoft Agent 365 (currently in preview), exposes Teams chats, channels and messages via the Graph API. Connect through your tenant's Agent 365 endpoint, authenticate with your Microsoft 365 account, then link that connection into Unl so channel reads run against your ratified rule.
Does Unl post messages or change anything in Teams?
Unl reads through Microsoft Teams, and can write back on your explicit gesture — it never acts as a side effect of a read.
What this is
Think inside your AI world — you stay in command
Save the thoughts, decisions and targets worth keeping, each with its reasoning, carried into every AI session the moment they matter. A new unit of exchange between you and your AI: the Settled Why with standing that travels. Unprompted.
Your whole AI world. What you decided at the epicentre. It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector — quick to connect, in a couple of steps.
MCP native·Human settled·Model agnostic·Your data
Measured Context
Connect Unl to bring the right information into the moment.
Your sources, read against the criteria you set.
The full product, open. Free at launch.