AI that answers the tickets it can, and hands the rest to your team
Kelu reads incoming tickets in Zendesk, Intercom, Freshdesk, Front, and Linear, answers the ones it has grounded evidence for, and hands the rest to your team with your escalation tag — nothing is posted on them. Draft only mode turns confident answers into private notes for an agent to send (not on Linear, where a note is a public comment). Deflection, triage, and copilot in one place.
What Support Ticket AI does
Grounded ticket answers, agent drafts, and safe deflection — measured with simulations before you enable it
Grounded Ticket Resolution
- Reads new tickets in the groups and inboxes you pick and retrieves from your indexed knowledge
- Responds directly only when confidence clears the threshold
- Cites the exact source pages behind every response
- Falls back to a human agent when evidence is thin — never invents policy
- Works alongside your existing macros and automations
Agent Copilot Drafts
- Draft only mode leaves replies as private notes in Zendesk, Intercom, Freshdesk, and Front
- Grounded in your knowledge base's public documents
- In Zendesk, a sidebar drafts on request — the agent stays in control
- Tracks which sources produced each draft, for audit
- Per-knowledge-base persona and tone applied consistently
Triage & Routing
- Auto-tag tickets with a category, a priority and topic tags
- Usage counts deflected tickets
Safe Rollout with Simulations
- Simulate the AI against up to 100 of your most recent resolved tickets
- Human-review queue for every simulated response
- Confidence score for every simulated answer
- Enable auto-response gradually — group by group or inbox by inbox
- Traces record the question and answer for every real reply
Before the ticket, in the ticket, after the ticket
Support Ticket AI is deliberately end-to-end. Answer the question in the support form before a ticket is filed (form deflector). Resolve or draft when it is (helpdesk integrations and copilot). Find the gaps and route each one into a doc proposal for your team to publish (gap analytics). Every step runs on the same knowledge base and the same retrieval pipeline as the widget and bots — improve your docs once, and every surface gets better.
- Form deflection stops repeat questions from becoming tickets
- Copilot drafts land in the Zendesk agent sidebar
- Auto-resolution runs on confident, grounded answers only
- Weak-answer traces feed doc proposals that fix the underlying gap
Before the ticket
Kelu
Open Settings → API keys and click Rotate. 1Sources: 1 API keys
No ticket filed
In the ticket
Internal note86%
Yes, under Billing → Currency, before your next invoice. 1Draft for the agent
After the ticket
Exporting audit logs
asked 14 times
Knowledge Maintenance
ProposedReview & addGap becomes an answer
Answers you can check, from a system that won't guess
It says "I don't know"
When your content does not cover a question, Kelu does not guess. In a helpdesk it posts nothing and tags the ticket for your team.
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.
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.
Got questions?
Frequently Asked Questions
Common questions about Support Ticket AI
Native helpdesk AIs are built around their own helpdesk and price per resolution or session. Kelu indexes your docs, wikis, code repos, and connector sources, plus solved Zendesk tickets — and surfaces the same knowledge base to the widget, bots, and MCP endpoint on flat pricing. One knowledge base, every surface, and you keep the choice of helpdesk.
Every answer carries a confidence score. Above the threshold you set, the AI responds directly, or leaves a draft for the agent in Draft only mode; below it, nothing is posted and the ticket gets your escalation tag. Simulations let you calibrate that threshold on historical tickets before enabling anything customer-facing.
Answers are generated only from retrieved chunks of your indexed content, the prompt enforces grounding in those sources, and the abstention gate blocks posting below the confidence threshold. Every reply cites the sources it used, and traces record each question and answer.
As monthly AI questions, the same unit that covers the widget, bots, and MCP. Flat pricing (Free / Pro / Enterprise) with clear included quotas — not per-ticket metering — so a busy support week never surprises your invoice.
Zendesk, Intercom, Freshdesk, Front, and Linear for tickets, plus Freshchat for live chat. Zendesk Messaging is coming soon. Solved Zendesk tickets can also be indexed as a source, so past resolutions inform future answers.
Turn your ticket queue into an AI-assisted workflow
Connect your helpdesk, run a simulation on your most recent resolved tickets, and review every answer before you enable anything customer-facing.
Free to start · No credit card required