Customer Retention · Keep

Knowledge concierge.

Answers the internal questions your team asks all day from your own documentation, and tells you which answers are missing or stale.

Operational lens−40% internal tickets modeled targets · not client results
.crft/Knowledge concierge

internal tickets

to the Scan's evidence — before any scope

4–10 wks

to a system in production, not a pilot

modeled targets · not client results · timings are CRFT's standard engagement

The work, today.

The answer exists, in a document, that nobody can find. So people ask a person — the same person, the same five questions — and that person becomes a lookup service instead of doing their job. Meanwhile the documentation rots, because nothing tells anyone which page went wrong.

Where the Scan startsWith your docs, the questions people actually ask and where the answers go stale.

What the system is.

Four lines, the same four on every system we build. Where they fall is what makes this one different from the last one.

Your documentation, wherever it lives, including the parts out of date
The questions actually being asked, in tickets and in chat
Who answers what today, and how long it takes them
Which documents are current and which have not been touched in a year
01

What it reads

The signals it works from. Typically connects to Document storage, Chat, Support desk and Intranet.

01What the question is really asking
02Which source answers it, and how confident that is
03When it does not know — and says so rather than inventing
04Which gaps and contradictions in the documentation are costing the most
02

What it decides

The calls it makes on its own, unattended, every time it runs.

An answer in the tool people already ask in, with the source linked
A gap report — the questions it could not answer, ranked by frequency
A staleness flag on documents its answers keep getting corrected on
03

What it writes back

Into the tools the work already lives in.

04

Where the human stays

Anything it is not confident about goes to the person who owns that area, and the answer they give becomes documentation. Refusing to answer is a designed behavior, not a failure mode — a confident wrong answer about policy is worse than no answer.

How we set it up.

The same four legs as every CRFT engagement — written for this system rather than in general.

  1. 01
    Scan48 hrs · evidence before scope

    We categorize a month of real internal questions. The distribution decides the build — a long tail needs different treatment from twenty questions asked constantly.

  2. 02
    Scope1 week · the report is the scope

    Scope is set by source sprawl. Documentation in four systems with three conflicting versions is a content problem before it is an AI problem, and we will say so.

  3. 03
    Build4–10 wks · production, not a pilot

    Confidence thresholds and source citation ship on day one. It is allowed to be less useful in order to be trustworthy.

  4. 04
    Compoundongoing · it reports, then improves

    The gap report is the compounding part: it turns the questions it fails into the documentation it needs, so the corpus improves because the system is running.

What we hold it to

Internal tickets deflected, answer accuracy on a sampled review, and documentation gaps closed.

Get CRFT

Build the intelligence your company compounds on.

Five inputs, a published price, a report in 48 hours. Decide with numbers — then own what gets built.

Or just send us a note
What kind of system? Pick any that apply