Knowledge that maintains itself

Your team's knowledge is scattered across Notion documents, Slack conversations, and the quick call you hopped on in Teams. Mention turns it into structured learning material that stays current as your team evolves.

You curatethe terminology and processes they need to know
Admin reviewing the generated playbook for a learning audience
They learnfrom an interactive tutor
Learner working through an ordered lesson with a knowledge check

What you do

Setup is a conversation. Refinement is automatic. You curate, the AI does the writing.

Admin shaping a learning audience through a chat conversation

Curate

Build the playbook once, by describing its goals.

Describe what team members do and what they need to learn. Mention proposes processes and concepts to teach. You make tweaks, then never have to update it manually again: it keeps itself up to date as content rolls in.

  • AI-proposed processes from your existing sources
  • Click-to-accept curation. No documents to author
  • Regular updates whenever out-of-date information is detected
Admin refining an answer and resolving conflicts between sources

Refine

Your sources will conflict. Resolve conflicts quickly and easily.

When Notion disagrees with the latest Slack conversation, Mention surfaces the conflict and asks you to pick a side. Or, investigate its answers yourself and correct it inline. Either way, it never repeats the stale answer to your team members again.

  • Inline corrections that propagate to every learner
  • Source-conflict resolution with a clear audit trail
  • Admin-as-learner mode to see what your team sees
Adoption tab showing per-member progress across processes and concepts

Track

Quickly identify struggling team members.

Adoption is measured by knowledge checks passed and concepts mastered. Sort by progress, drill into any member, see exactly which processes and concepts they've completed.

  • Per-member breakdown across processes and concepts
  • Completion based on understanding, not just exposure
  • FAQs surface gaps in your team's understanding

What your team sees

A structured learning path with knowledge checks and grounded Q&A.

Prerequisite gate suggesting foundational concepts to learn first

No gaps

Concepts build understanding in a logical order.

When a learner reaches for a concept they're not ready for, Mention stops them and suggests what to master first. Just like a teacher would.

Article with a knowledge check quiz on the right side

Verify, don't assume

Knowledge checks verify understanding.

After each article, a quiz verifies the learner actually got the main points. Wrong answers route them back to the relevant section instead of letting them skip ahead.

Learner asking a question and getting an AI answer grounded in the team's knowledge

Ask anything

A patient "senior teammate" answers questions 24/7.

Learners ask questions in plain language and get answers grounded in your team's actual sources. When the system is uncertain, it says so, and points to where it would look.

Works with the tools you already use

Connect once. Knowledge stays current as sources change.

  • Notion
  • Confluence
  • Dropbox
  • Box
  • GitHub
  • Slack
  • Google
  • Microsoft 365
  • Zoom
  • YouTube
  • Public Internet
  • Other integrations available on request.

    Get in touch

What you can do on day one

1

Create an audience for your team

2

Connect one or two knowledge sources

3

Review AI-suggested concepts and processes

4

Invite team members; they start learning immediately

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

Ready to get started?

Start building your knowledge base today

Start now

No credit card required to start.

Frequently asked questions

A generic chatbot retrieves a chunk of text and hopes it was the right one. Mention does something different: it builds a curated, dependency-ordered learning path with knowledge checks and per-member progress tracking. 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.

No. You curate, the AI writes. You describe an audience in a chat about what they do and what they need to learn, and the AI proposes processes and concepts pulled from your existing docs, meetings, and chats. You accept, rename, or skip. Articles are generated on demand from the latest source material, so they don't go stale the moment you ship them.

You correct it inline, and the correction propagates to every learner 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, run through the curation conversation, invite your team. Learners can start working through processes 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 the next article generation automatically. Reopen the curation chat any time to add, rename, or remove processes, and the playbook reflects the change immediately. Switching tools means disconnecting the old source and connecting the new one; your audiences, playbooks, and glossaries aren't tied to a specific integration.