Get your team on the same page so you can move faster

Execution is no longer the bottleneck. Shared understanding is. Mention integrates your docs, transcripts, and chats, pushes the knowledge your team needs, and verifies it landed.

Start now No credit card required

The sources

Refund policyNotion

Refunds over $200 require manager approval…

#supportSlack

"heads up: new refund threshold starts today"

Weekly support syncGoogle Meet

Transcript · 34 min

The contents

1Refund policyReference
2Escalation rulesHow-to
3Enterprise accountsExplanation

The report

RefundsEscalationEnterprise
Ana
Ben
Chloe

Ben is stuck on Escalation rules.

You explained it. Did it land?

Most teams run on write-and-pray: document it, share the link, hope. Nothing tells you whether it was read, understood, or already out of date.

The status quo

With Mention

Docs are written once, read never

You know the page shipped; you don't know it landed. The gap surfaces weeks later, inside a decision built on a stale assumption.

With Mention

✓Pushed, then verified

Every member gets the path, and knowledge checks confirm it landed. Nothing ships into silence.

You are the search engine

The same questions arrive on repeat: in DMs, in standups, in onboarding. Every answer you give by hand reaches one person.

With Mention

✓Answered once, for everyone

Grounded Q&A answers from your sources, with citations. Repeated questions become curated FAQs instead of repeated DMs.

Misalignment is silent

People quietly operate on slightly different understandings of processes and concepts, acquired from different sources. That's fine until it isn't.

With Mention

✓Drift gets caught

When sources disagree, Mention surfaces the conflict and asks you to decide. Everyone, including your agents, sees the same answer.

Your scattered sources become shared understanding

Not a wiki that waits to be searched. Mention distills your existing sources into short lessons and pushes them to every member: kept current, no authoring required.

Curate

You write the brief. Mention writes the rest.

Create an audience and Mention drafts its table of contents from what your sources actually cover, titles and briefs already filled in. Add your own entries as a short brief: Mention writes each article, composes its lesson, and keeps both current as content rolls in.

  • A starting table of contents drafted from your sources
  • Entries added with a short brief. No documents to author
  • Commission research reports to pull in scheduled public-web context
  • Rewrites whenever out-of-date information is detected
Support hires need to learn how we handle refunds and escalations.
Drafted for this audienceMention
✓Refund policyAdded
✓Escalation rulesAdded
Legacy ticketingSkipped

Ask anything

Between lessons, a patient senior teammate.

Anyone can ask in plain language and get answers grounded in your actual sources, with citations. When the system is uncertain, it says so. Repeated questions become FAQs, a live map of what your team is still unsure about.

Can I refund an annual plan after 30 days?

Yes, pro-rated to the unused months. Anything over $500 needs manager approval first.

Refund policy · Notion#support · Slack

You see who understands what

Reading is not understanding. Mention verifies every step and puts the result on one screen: mastery, not vibes.

Verify, don't assume

Every article ends in a knowledge check.

A few quick questions confirm the main points actually landed. Wrong answers route people back to the relevant section instead of letting them skip ahead. Completion means understanding, not exposure.

Knowledge checkRefund policy

A customer asks for a $700 refund. What does it need?

Manager approval✓
Nothing, it's under the limit
A new invoice

Correct. Refund policy marked mastered.

One screen

The whole team, on one screen.

The adoption dashboard shows per-member mastery across every article, measured by knowledge checks passed rather than pages viewed. Spot who's stuck while it's still cheap to help.

  • Per-member breakdown across every article and lesson
  • Sort by progress, drill into any member
  • FAQs surface what the whole team is missing
AdoptionSupport team
RefundsEscalationEnterprise
Ana
Ben
Chloe
Dev

Ben hasn't passed Escalation rules in two weeks. Worth a check-in.

And it knows when it needs you

Your company changes weekly: new policies, new thresholds, new tools. Mention absorbs routine changes on its own. When a change takes judgment, it brings you the question instead of guessing.

Refine

When sources conflict, you settle it once.

When Notion disagrees with the latest Slack conversation, no refresh can settle which is right. Mention surfaces the conflict and asks you to decide. Or investigate its answers yourself and correct them inline. Either way, it never repeats the stale answer to your team again.

  • Sources re-sync on a schedule; changes flow into the next regeneration
  • Inline corrections that propagate to every member
  • When material changes, members are routed back through exactly what changed
Refund policyNotion · 3 months ago

Refunds over $200 require manager approval.

#supportSlack · yesterday

"New approval threshold is $500, effective today."

Use $500Resolved by you

Every member and every agent now sees $500.

Your agents need shared understanding too

AI made execution fast and cheap, but not necessarily consistent or correct.
Mention gives your AI-driven execution layer verifiable consistency.

Draft a reply to this customer: they want a refund on an annual plan, four months in.
Your agentMention MCP

ask · "What is our refund policy for annual plans?"

read_sop · Escalation rules

Drafted. Four months in means a pro-rated refund for the eight unused months: $960. That's over your $500 threshold, so the draft requests manager approval first.

In practice

Your agent asks Mention before it acts.

Connect ChatGPT, Claude, Cursor, or your own agent over MCP. It signs in with scoped, revocable access and pulls the same curated knowledge your team learns from, at the moment it needs it.

6.2×

faster answers

63%

lower token cost

Benchmarked against the same agent answering from raw sources.

Works with the tools you already use

Connect once. Knowledge stays current as sources change.

What you can do on day one

1

Create an audience for your team

2

Connect one or two knowledge sources

3

Review the starting contents drafted from your sources

4

Invite team members; they start learning immediately

No documentation written. No manual updates. Just make steering adjustments.

Ready to get started?

Push knowledge to your team this week

Start now

No credit card required to start.

Frequently Asked Questions

A wiki waits to be searched, and it can't tell you whether anyone read a page, understood it, or is working from last quarter's version. Mention inverts both halves: it composes short lessons from the same source material and pushes them to every member, then verifies understanding with knowledge checks and shows you the results per member. Your wiki stays where it is. Mention connects to it as a source.

Yes. Mention exposes your company's knowledge through a Model Context Protocol (MCP) server. Any AI agent or workflow that supports MCP can connect and immediately access your structured, curated domain knowledge. The same knowledge your team learns from is what your agents act on: conflicts resolved, answers corrected, always current. This is what makes AI automation at your company reliable rather than approximate. It's also dramatically cheaper: in our benchmark, the same agent answered the same questions 6.2× faster at 63% lower token cost with the Mention MCP than by digging through raw sources.

A generic chatbot retrieves a chunk of text and hopes it was the right one. Mention does something different: it curates your team's knowledge into articles and lessons, verifies understanding with knowledge checks, and tracks per-member progress. Answers are constrained to your team's vocabulary. When sources conflict, you decide which is correct; when an answer is wrong, you correct it inline and the change propagates to everyone.

You correct it inline, and the correction propagates to every member immediately. The old answer is gone. When sources disagree, Mention surfaces the conflict and asks you to decide rather than picking arbitrarily.

We don't train models on your content. We store structured analyses tied to concepts (what each source says about a given idea), and we do not retain your raw documents.

One focused working session for the first audience: connect a source, review the starting contents Mention drafts, invite your team. Members can start working through lessons the same day, at their own pace. Adding more audiences later is faster because sources are already connected and the glossary builds on what's already there.

Sources refresh on a schedule, so updated docs flow into rewrites automatically. Edit an entry's brief any time to change what it covers, or add and remove entries; articles are rewritten and lessons recomposed on their own. Switching tools means disconnecting the old source and connecting the new one; your audiences, articles, and glossaries aren't tied to a specific integration.