Pitchbar's self-improvement loop watches every conversation and flags questions your agent could not answer confidently. Those questions cluster into content gaps at /app/analytics/content-gaps. Treat the page as a prioritised backlog of what to teach your bot next.

How a gap is detected

After every visitor turn, DetectGapJob queues asynchronously (off the hot path) with the user message, the agent id, and the confidence score the retriever produced. The job:

1. Normalises the question (lowercase + collapse whitespace) and hashes it.
2. Looks up an existing gap with the same hash for this agent; if found, increments occurrences and refreshes last_seen_at.
3. Otherwise inserts a new row in content_gaps with status=open.

The job is single-attempt — duplicating a gap row is harmless, but retrying after a transient DB hiccup would over-inflate occurrences.

What the UI shows

• Agent picker — narrow to one bot when you have several.
• Status — Open (default), Answered (someone added a curated answer / source), Ignored (won't fix).
• Window — last 7 / 30 / 90 days, or all time.

Each row carries the question text, the count of times it has been asked, the last time it was asked, and the agent it belongs to.

Actions

• Curated answer — jumps to the curated-answers editor for that agent with the question pre-filled. Once you save the curated answer, the next visitor who asks that question gets a direct response without going through retrieval.
• Resolve — marks the gap as answered (the source / curated answer that addresses it is live).
• Ignore — marks ignored (out of scope for this bot, e.g. visitor asked about a product the workspace doesn't sell).

Who can do what

Why this matters

Most chatbots silently degrade — a question never gets answered, the visitor bounces, no one notices. Pitchbar turns those silent failures into a triage queue. Working the gap queue weekly is the fastest path to a high-quality agent.