All articles
AI & AutomationMay 15, 2026·8 min read

Spot the real holes in your knowledge base, not the ones you imagine

Your support team thinks it knows which articles are missing. The data says otherwise. A method to systematically surface the gaps that actually cost you.

JG
Jérôme Gambiez
Founder, ResponZ

Asking a support team which articles are missing always yields the same list: 5 to 10 highly visible topics, seen the previous week. The real list is longer, flatter and more expensive.

The classic gap: recurring topic, no article

A topic is a gap when it returns regularly and consistently triggers a long conversation. Simple 3-dimensional criterion:

  • Frequency:> 5 conversations / month over 3 consecutive months.
  • Cost:average resolution time > global median × 1.3.
  • Auto-resolution: 0 articles cited in agent or FIN replies.

The silent gap: article exists but is unfindable

Subtler and more frequent. The article exists, but it's poorly titled, poorly indexed, or buried in the wrong section. Symptom: agents reply with a paraphrase instead of pasting the link. The rate at which an article is cited by its own team is the best discoverability indicator.

Honest metric

Citation rate = number of times the article appears in a reply / conversations on that topic. Below 30%, the article is invisible. Above 60%, it's doing its job.

The ghost gap: stale topic

Article that exists, is findable, but describes a UX from two versions ago. Detection: reopen rate of conversations that cite it. A cited article whose conversation reopens within 48h two out of three times is an article that lies.

Monthly method, 90 minutes

  1. Extract recurring topics not covered in the last 90 days.
  2. For each existing article, compute citation rate + reopen rate.
  3. Rank by estimated total cost (volume × average resolution time).
  4. Decide: create / rewrite / deprecate. Five decisions per month max, otherwise nothing ships.

A KB isn't a project, it's a monthly discipline. Teams that invest 90 minutes a month on this loop systematically out-perform those who rewrite 30 articles in one go every 9 months.

Read next