Think inside your AI world.
Outlook through Unl
Outlook will find the email, open it, and show you what was sent in reply. Whether that reply actually locked in a commitment or just acknowledged the question is a line Outlook doesn't draw for you.
Outlook through Unl reads messages and sent items against the written-commitment criterion you have ratified, so 'did we confirm this in writing' comes back verdict-shaped with the reply that fell short.
What Outlook holds
Naked, Outlook through Unl reads real mailbox content, not a paraphrase:
- Search Outlook messages by keyword across subject, body and attachments
- Retrieve a message by ID, including full HTML body
- List messages in sent items, filtered and sorted
- Read message properties - subject, categories, importance
- Follow a thread across an original message and its replies
What the naked read gives you
Ask Outlook through Unl to find the thread with a client about the September start date and it will surface the inbound request and every reply sent back, full text included. That's a faithful record of the mailbox. It doesn't know that your team only counts a start date as confirmed when the reply contains the words 'confirmed for' followed by a date - Outlook reads what was sent, not whether it counted as a commitment.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when Outlook is read measured
Say you run client onboarding, and you have ratified in Unl that a start date counts as confirmed only when a sent reply contains the phrase 'confirmed for' immediately followed by a date, sent from the account owner - after a client took 'sounds good, let's aim for September' as a locked date.
'Did we confirm the client's September start in writing?' returns, measured: unmet - the sent reply reads 'sounds good, let's aim for September', which lacks the 'confirmed for' phrase the rule requires, so it reads as a soft acknowledgement, not a commitment. Outlook supplied the sent message and its text; the ratified rule supplied the phrasing condition that turns a reply into a verdict.
And back again
Once you send the properly worded confirmation and log it in Unl, the next 'did we confirm this in writing' question for the client returns a met verdict instead of re-reading the same soft reply.
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 an email reply a 'confirmation' rather than an acknowledgement?
The exact wording condition your team ratified, not the friendliness of the reply. Here, only a sent message containing 'confirmed for' plus a date, from the account owner, counts - Outlook shows what was sent, the ratified rule decides if the wording locks it in.
How do I connect Outlook to Claude?
Microsoft's Work IQ Mail MCP server, part of Microsoft Agent 365 (currently in preview), exposes Outlook mail tools including message search, retrieval and sent-items listing via the Graph API. Connect through your tenant's Agent 365 endpoint, authenticate with your Microsoft 365 account, then link it into Unl so mailbox reads run against your ratified rule.
Does Unl send emails or change anything in Outlook?
Unl reads through Outlook, 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.