Salesforce MVP Hall of Fame (Shivanath Devinarayanan) · Founded 2022
Support ticket routing
Every ticket to the right queue in one call. The unsure ones go to a person, not a guess. The assessment is free: a short read of the org and a written note. If you go ahead, the first build week is a fixed AED/SAR 14,900 (about USD 4,050), credited in full when you sign the build within 60 days.
Founded 2022 · Founder in the Salesforce MVP Hall of Fame · Dubai HQ · Kochi studio
- 01Models · Claude, Gemini, OpenAI, Bedrock
- 02Agentic systems · Agentforce, CrewAI, ADK, A2A
- 03Agentic memory · Neo4j, Cognee, IndyKite
- 04Automation and voice · n8n, Retell
- 05Deployment and governance · identity, evals, policy, audit
The stack
How we would assemble it.
The honest no: if the work is a software factory with a named delivery date, we are the wrong partner.
The decision
The decision, drawn.
Choice over 5-50 queues + Noul 'needs a human now' in one call; auto-route above 0.9 confidence
Jev · Choice+Noul
Which queue should this ticket go to, and does it need a person now?
- billing
- technical
- account
- other
Charged twice this month. Payouts failing since Monday.
- billing0.87
- technical0.12
- account0.01
- other0.00
Noul · escalate 0.95
The flow
One ticket, from inbox to queue.
Arrives
A ticket lands in Service Cloud
Email, chat or the web form. Nobody has read it yet.
Jev decides
Queue and urgency, one call
Billing, technical, account or other, and whether a person needs it now.
Above the line
Routed on arrival
The ticket sits in its queue. Claude or Gemini drafts the reply after routing.
Below the line
A team lead picks the queue
Tickets Jev is unsure of wait for a person, not a guess.
The job
What has to be true.
Act at 0.90 confidence or higher. Below that, a person or a larger model. Act at 0.85 or higher. Block at 0.15 or lower. Between 0.35 and 0.65, a person decides.
The figure
Builder's figure. Not reproduced by us.
40 tickets across 9 desks for about $0.0016; TypeSafe eval: customer service 76.0 vs 78.3 best comparator
apimodels.app/jev-use-casesWrite your house rules into the request. When rules were left out, Jev got 5 of 24 right with high confidence (Huryn). Validate thresholds on labelled samples.
Who runs it
Who would run this, and what changes.
Example
Head of customer service, Dubai property developer
Today: Handover snags, service charge questions and payment plan requests share one inbox. A coordinator sorts the pile every morning before anyone replies.
After: Each ticket reaches its queue as it arrives. The coordinator sees only the ones Jev is unsure of.
Property management teamsExample
Support lead, Riyadh software company
Today: Billing complaints sit in the technical queue for a day before someone moves them. Customers write again to ask why.
After: Billing, technical and account tickets split on arrival. The same call flags the urgent ones for a person.
Software companiesExample
Service desk manager, Abu Dhabi facilities firm
Today: Tenants email one address for everything from AC faults to invoice copies. Agents forward and re-forward.
After: The queue list you wrote decides where each email goes. A person checks anything under your confidence line.
Tickets and SLAs in Mindcat Desk
The brief
Name the decision your team makes a thousand times a day.
We read the process and write down where Jev fits, where it does not, and where the line sits.