CUSTOMERS

What one pilot team found.

Case study

An L1 enterprise software support queue

An L1 support queue at a global enterprise software provider piloted a Claude agent against live Salesforce cases for seven days. The agent read each case thread, internal notes and prior resolutions, then drafted a reply for a specialist to review — never sending anything itself.

4.4×

less specialist review time per case

89%

of the queue was diagnostic work the agent could assist

21

drafts prepared across 16 live cases

0

drafts reached a customer without human review

L1 Support Lead · Global enterprise software provider

Work out what it saves your team.

The diagnostic share (89%) and precedent share (39%) are measured from a 16-case pilot at one client. The minutes saved and the hourly rate are estimates, so replace them with your own team's figures. Set how many analysts work the queue.

L1 analysts on the queueEvery analyst earns the savings below on their own caseload.

4

Cases per analyst, per monthQueue volume — sets how many times every saving below is earned.

23

Diagnostic shareThe portion the agent can research and draft. Provisioning and access requests are excluded — they save nothing.

89%

Of those, share with usable precedentCases with a prior resolution on record. These earn the bonus saving below on top of the base.

39%

Minutes saved on a diagnostic caseReading the thread and internal notes, working out who owes the next reply, and writing the draft — saved whether or not precedent exists. Estimate — adjust to your team.

34

Extra minutes when precedent existsThe precedent search itself — finding and reading prior cases on the same question, which is the slowest part by hand. Estimate — adjust to your team.

18

Fully-loaded hourly rateSalary plus overheads — converts the hours returned into money returned. Your figure — set it to your team's real cost.

£60

Time returned

56.0 h

saved per month

672 h

saved per year

90

working days a year, at 7.5 h

37 min

average across every case, including the ones it barely touches

Money returned

£40,305

specialist time returned per year

£3,359

specialist time returned per month

Time saved is modelled, not observed end to end. The pilot was 16 cases at one client, so your results will vary. Assumes every draft passes a human reviewer.