Every unanswered question becomes a drafted answer, waiting for your review

Kelu watches which questions the assistant can't answer well, ranks them by volume, drafts the missing answer from your own content, and hands the draft to your team. AI proposes; humans review and publish. It's the loop that turns a chatbot from a support tool into an editorial system for your docs.

How Doc Proposals work

Gap analytics identify the missing knowledge; a scan drafts the missing answer; your team accepts or dismisses each draft

01
Ranked by real question volume

Gap Discovery

  • Every unanswered or down-voted question is logged
  • Gap report ranks missing knowledge by volume
  • Groups similar questions so you don't chase 40 versions of the same topic
  • Per-knowledge-base view so DevRel and Ops can each own their gap list
  • CSV export and copy-as-markdown let you pipe them to Linear / Jira / Notion
02
A starting point, not the final answer

AI-Drafted Answers

  • POST to /doc-proposals/scan and the top gaps become drafted answers
  • Drafts use only your own content; missing facts are marked NEEDS INPUT
  • Each draft carries the questions it would answer and the sources it drew from
  • Each draft marked grounded or partial, so the team sees what needs input
03
AI proposes, humans publish

Human Review

  • Accept or dismiss each draft from the dashboard
  • Edit in-place before accepting — the AI is a first draft, not final copy
  • Accepted drafts become Q&A answers, used right away
  • Dismissed drafts stay dismissed until you restore them
  • Re-run scans as your gap list evolves after each docs release
Close the loop the industry doesn't close

The docs backlog writes itself

Most AI chatbots surface unanswered questions and leave it there — 'here's a report, good luck writing the docs'. Doc Proposals goes further: it drafts the answer. Every question the AI couldn't answer becomes evidence of a missing doc, evidence becomes a draft, and the draft goes to a human editor for review. Over a quarter, the flywheel is what turns 'we shipped an AI' into 'our docs are measurably better'.

  • Unanswered questions become the docs backlog — ranked by volume
  • AI drafts the answer from your existing content
  • Human review keeps final judgement with the editor, not the model
  • Accepted drafts go live as Q&A answers
  • Re-runs after each docs update track whether the gap actually closed
Why teams trust the answers

Answers you can check, from a system that won't guess

It stays in sync on its own

Each source re-syncs on its own schedule, from every 5 minutes for tickets to daily for websites. Unchanged pages are skipped.

A bad sync can't empty it

If one sync would remove more than 45% of a source's pages, Kelu holds the removals until a person approves them.

Every answer from your docs shows its sources

Numbered links point to the page and section each part of the answer came from, so anyone can check it in one click.

Got questions?

Frequently Asked Questions

Common questions about Doc Proposals

Turn unanswered questions into a docs backlog

Run your first Doc Proposals scan and see which gaps come back as drafts ready for your editor.

Free to start · No credit card required