Where the team's intelligence lives.
Know is the function with the most documents and the least findability. It's the difference between a team that knows things and a team that can find things. Knowledge base, internal wiki, the institutional memory of the operation.
v 02 · live
What Know means.
Know is the work of making the team's intelligence accessible. Not the work of writing documentation. Not the work of maintaining a wiki. The work of designing the knowledge layer so that the right answer is findable in seconds, by the person who needs it, when they need it, and stays current as the work changes.
Most CX teams have two knowledge bases. The official one: out of date, hard to search, written for compliance. And the real one: Slack messages, agent notes, screenshots in DMs, a shared doc someone made in 2023. The official KB is theatre. The real KB is invisible institutional memory.
That's the gap Know names. Knowledge exists; it's just not where the team looks for it. The KB exists; it's just not what the team trusts. Senior agents become walking knowledge bases because the actual one isn't usable. When they leave, the knowledge leaves with them.
"Our KB had 1,400 articles. The team's actual answer to "how do I handle this?" was Slack-search. The KB was the org's pretend operation. Slack was the real one. When my best agent quit, three months of his knowledge left with him."
Haven's Know module starts with the findability audit. What gets searched. What gets found. What gets used. What the team is actually using as knowledge (Slack, docs, notes), surfaced and consolidated.
The KB becomes the place the team actually goes. Articles get retired more than added. Senior agents stop being load-bearing. Knowledge becomes a system, not a person.
The progression. Four levels.
The KB is theatre. The team uses Slack, DMs, and senior agents instead. Most articles are stale. Search rarely returns the answer the team needs.
- KB is theatre
- Real knowledge in Slack/DMs
- Stale articles
- Senior agents are load-bearing
Some articles are trusted. Heavy users have their bookmarks. The rest of the team avoids the KB. New articles get added; nothing gets retired. Volume grows; usefulness doesn't.
- Trusted bookmarks
- Avoidance among team
- Article growth
- No retirement
The KB is owned and pruned. Findability is measured. Stale articles are retired. The team uses the KB before Slack. Senior agents stop being the knowledge layer.
- Owned KB
- Findability metrics
- Routine retirement
- KB beats Slack as first port of call
The KB is a self-improving system. Search misses trigger article creation. Unused articles auto-flag for retirement. The team's intelligence compounds rather than scattering.
- Self-improving KB
- Auto-flagged stale content
- Search-miss → article
- Compounding intelligence
What Know builds.
The findability audit
What gets searched. What gets found. What gets used. The gap between them is the real KB roadmap.
- Search → found → used funnel
- Top 50 unfound queries surfaced
- Article-to-volume coverage gaps
- Owner per coverage gap
The article lifecycle
Each article has an owner, a review date, and a retirement criterion. The KB shrinks as it improves.
- Owner & review date per article
- Retirement criteria named upfront
- Drift alerts on every product release
- Usage telemetry on every article
The knowledge capture ritual
A weekly or fortnightly cadence where senior agent knowledge gets surfaced and turned into shared articles. No more single points of failure.
- Senior-agent knowledge surfaced live
- Converted into shared articles
- No more single points of failure
- Rolling backlog of next topics