Support Desk Manager
An AI-native support desk that resolves the tickets
Runs your support desk — resolves tickets from your own help docs, escalates the exceptions.
$0.69 per resolution, or from $149/mo
50 free resolutions in 30 days, no card
Support desk · Sample
23 tickets resolved this week, 3 escalated to your team
Last 7 days · example data
Resolution rate
88%
23 resolved · 3 escalated
Deflection
85%
17 of 20 deflected
Avg. time to resolve
41s
per ticket
QA score · 30 d
94%
Predicted CSAT
Replies sent vs. escalated — last 14 days
Replies sentEscalated
Control: A second, stronger AI model reviews every reply before it can send on its own
It runs your support desk: it answers each inbound ticket from your own help docs, every claim cited to the article it came from, and escalates the rest. A second, stronger AI model checks every reply before it can send on its own. You review and one-click send from day one; autonomy is earned per topic and opt-in. Run it instead of a helpdesk, or alongside the one you have — you pay per resolved ticket, not per seat.
Trained on
your help-centre articles + your refund and escalation policy + the customer's recent tickets with your desk (last 14 days)
Methods
- Every factual claim cited to the help-docs article it came from
- A second, stronger AI model reviews every reply before it can send on its own
- Refunds, credits, and billing decisions escalated to your team, never resolved by the desk
- A ticket that tries to instruct the AI never sends automatically — it waits for your team
- A reply that would repeat an email, card or phone number is redacted and held for your team
Who it's for
Support teams and founders who want an AI-native desk that resolves the routine tickets and escalates only the exceptions — standalone, or alongside the helpdesk you already run.
How it works
From signup to the first finished piece of work.
Forward your support email in about five minutes, or connect your help desk — then point us at your help-centre articles and refund policy.
Each inbound ticket loads the customer's recent tickets with your desk (last 14 days), then the desk resolves it with an answer cited to your docs.
A second, stronger AI model checks every reply before any automatic send; trusted topics that clear the calibration bar send, everything else escalates to your team.
Trusted topics resolve automatically. On Zendesk, Intercom, Freshdesk or Front, drafts land on the ticket as an internal note (Front: a draft reply) — your team approves them in the helpdesk it already uses; in Zendesk, Intercom and Freshdesk the agent copies the note into the reply. Email and chat drafts wait in your queue for one-click review.
Capability matrix
Does well, with review, won't do.
Out-of-scope tasks escalate · they don't hallucinate
Does well
- A resolved reply within minutes of an inbound ticket
- Every claim cited to a help-docs article
- A second, stronger AI model checks every reply before an automatic send
- A reply that would repeat an email, card or phone number is redacted and held for your team
- Cancellation requests always go to your team
With review
- Trusted topics resolve automatically once they clear the calibration bar; everything else escalates to your team for one-click review
- Low-confidence answers go to your team's queue
- Refund, billing, and policy questions wait for your decision
Won't do
- Never promises a refund or credit
- Never admits fault or liability
- Never answers from facts your docs don't support
Connections
Per tool: why we need it, what we do, how it's audited.
Connect what you need, when you need it. The assistant only reads tools you explicitly link — never the rest of your stack.
- Your support content — forward your support@ email (about five minutes) and drop the chat widget on your site. Moving off Zendesk, Freshdesk or Intercom? Import your help-center articles in a few clicks (and your macros, from Zendesk).
- Your help-centre articles — the source every answer is cited to.
- Optional: your refund and escalation policy — so the line on refunds is yours, not a guess.
- We retrieve the right help-docs article for each ticket and cite it in the answer.
- We run a second, stronger AI model as reviewer. A ticket that tries to instruct the AI never sends automatically, and a reply that would repeat an email, card or phone number is redacted and held for your team.
- We escalate refunds, billing, and policy calls to your named owner with the policy section quoted.
What it reads on every task
Your data. Not the public internet.
Loaded fresh per task — change a doc, the next task picks it up. No retraining, no week-long fine-tune, no stale snapshot.
- Your knowledge base and help-centre articles — the only source an answer is allowed to cite
- Your refund and escalation policy — so the desk never invents a policy you don't have
- The customer's recent tickets with your desk (last 14 days) — loaded before any reply is drafted
Guardrails
When it stops and asks you.
- Refunds, credits, billing disputes, or contract changes — escalated to your team with the policy quoted, never promised
- A question your help docs don't cover — escalated for a human decision instead of a confident guess
- A reply that would repeat an email, card or phone number — redacted and held for your team
- An answer the second-AI reviewer scored low-confidence — held for your team's review
Plans
Pay per resolution
$0.69
Per resolved ticket. Pay only for what the desk resolves — no subscription, $0 when a ticket escalates.
Choose Pay per resolutionA resolution is billed only when the reply went out — automatically or with your one click — and the customer did not write back on that conversation within 72 hours. Escalated tickets, replies the customer came back on, and replies your team rewrote (more than half changed) are never billed.
Try the sample, or start with your own data.