Agent Sightings Real agent use cases

Dust enables agents to go deeper at lower cost with Claude

Dust saved $10k a day on model spend after optimizing prompt caching. It gives companies a shared workspace where teams can build, deploy, and manage model-agnostic AI agents connected to their company knowledge, tools, and workflows. “The new Claude models didn’t just answer the question; it proactively explored adjacent information and synthesized across sources.” Stanislas Polu Co-founder and CTO of Dust The outcome $10K a day saved, and agents that run deeper The caching work paid off first on the bill.

Agent or tool
Claude Code
Topic
Customer Support
Reported on
Case study (Anthropic)
Added
2026-11-11

Why it matters

Support is repetitive and time-sensitive. Agents can draft answers, look things up and handle simple requests, so people can focus on the tricky ones. It is one of 554 sightings filed under Customer Support on Agent Sightings (number 147 by interest), and one of 255 involving Claude Code.

How you could try it

Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Claude Code or any similar agent and adjust the details to your situation.

I want an agent to handle routine customer questions end to end, and pass anything unclear to a person. The tool in the source case was Claude Code.

Saved

Tip: Start small: run it once on a low-stakes example, read what the agent did, and only then let it run on real work.

Source

Read the original first-hand account on Case study (Anthropic): https://claude.com/customers/dust. Our summary is a paraphrase; details are in the source.

Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.

Browse more like this

More in Customer Support · more with Claude Code · all browse pages · industry guides

Related sightings

← All 2754 use cases