Agent Sightings Real agent use cases

How Perplexity put its support team in control of its AI agent

How Perplexity put its support team in control of its AI agent. wasn't simply handling more questions. Putting support operators in control of the AI experience Perplexity chose Decagon with a specific operating model in mind: the people closest to customers should be able to shape how the AI agent behaves. As Perplexity has grown, so has the scale and complexity of supporting its users, with average daily support volume increasing 269% from last year. Over the last 30 days, the team has achieved a 78% deflection rate while supporting 70+ user intents.

Agent or tool
Decagon
Topic
Finance
Reported on
Case study (Decagon)
Added
2026-11-12

Why it matters

Money tasks are tedious but high-stakes, which is exactly where a careful agent helps: it does the checking and paperwork while a person keeps the final say. It is one of 156 sightings filed under Finance on Agent Sightings (number 80 by interest), and one of 20 involving Decagon.

How you could try it

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

I want an agent to gather the figures and draft the work, but I will approve any payment or account change myself. The tool in the source case was Decagon.

Saved

Tip: Keep the agent in 'propose, don't pay' mode: let it gather numbers and draft messages, and approve any payment or account change yourself.

Source

Read the original first-hand account on Case study (Decagon): https://decagon.ai/case-studies/perplexity. 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 Finance · more with Decagon · all browse pages · industry guides

Related sightings

← All 2754 use cases