Skip to content

AI Triage

DeskFork’s AI virtual agent automatically answers common questions using your knowledge base. When the agent is uncertain, it routes the ticket to a human immediately — it never guesses.

  1. Customer message arrives → DeskFork embeds the message with Workers AI
  2. Vectorize semantic cache searched (cosine similarity threshold: 0.95)
  3. Cache hit (similarity ≥ 0.95): cached answer returned instantly, no LLM call
  4. Cache miss: LLM called via AI Gateway with your knowledge base as context
  5. Response stored in Vectorize cache for future similar questions
  6. AI response sent to customer via WebSocket (async, non-blocking)

The AI will never generate an answer it is not confident about. If:

  • Similarity is below 0.95 and no relevant KB article is found
  • The question matches a payment/refund/legal keyword
  • Negative sentiment exceeds the configured threshold
  • The same customer asked 2 follow-up questions in a row without resolution

…the ticket is immediately routed to a human agent with the reason logged in the ticket timeline.

Once a human agent sends a reply, the bot is permanently disabled for that ticket until an agent explicitly re-enables it via “Route to bot” in the ticket sidebar. This prevents the bot from interfering with ongoing human conversations.

Go to Settings → AI → Virtual Agent.

SettingDescription
EnabledToggle AI on/off per inbox
Similarity thresholdDefault 0.95; lower = more cache hits but higher error risk
Sentiment thresholdNegative sentiment score that triggers escalation (0–1)
Escalation keywordsPayment, refund, legal, etc. — triggers immediate handoff
Follow-up limitNumber of unanswered follow-ups before escalation (default: 2)

The AI uses articles from your knowledge base as its source of truth. Go to Knowledge Base → Articles to:

  • Create articles (Markdown supported)
  • Organise into collections
  • Publish/unpublish articles
  • Review AI citation accuracy

Reports → AI shows:

  • Cache hit rate
  • Escalation rate by reason
  • Average similarity score on cache misses
  • Top escalated topics (for KB gap analysis)