Skip to content

A support triage agent that drafts the first reply.

Client
Regional logistics company
Role
Strategy, design and build
Timeline
[N] weeks
Type
AgentsRAG
−[XX]%ticket handling time
[XX]%of drafts sent with light edits
[N] wksfrom kickoff to production
[N]ktickets handled per month

The problem

[FILL IN: What was broken or slow, who felt it and what it cost. For example: a four-person support team answered the same shipment questions all day, and response times slipped every peak season.]

[What had been tried before, and why it didn’t work.]

The approach

[How we scoped it: which workflows we looked at, what we chose not to automate, and how success was measured.]

  1. 01Shadowed the team and labelled [N] real tickets
  2. 02Built an eval set before writing a single prompt
  3. 03Shipped a draft-only version to two agents in week [N]

What we built

[The system in plain language: what comes in, what the AI does, where a human stays in the loop, and what goes out.]

[Diagram, screenshot or short video of the system]
[Caption]

Results

[What changed, with the numbers from the outcomes row and how they were measured. Include one human detail: what the team does with the time now.]

Stack used

  • Claude
  • Python
  • Postgres + pgvector
  • [Helpdesk tool]
  • Vercel
  • [Eval tooling]
“[Optional pull-quote from the client about the result.]”
[Name], [Title], [Company]