Agent Sightings Real agent use cases

Test API endpoints in Postman and report results

Real-world thread: user supplied Comet with context on the API payloads and details, then let it handle testing in Postman. Comet generated multiple test payloads, executed the endpoint tests itself, and produced a final report after the run. Comet completed the tests and delivered the report with no further input required.

Agent or tool
Perplexity Comet
Topic
Software Development
Reported on
X
Added
2026-10-15

Why it matters

Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 106 sightings filed under Software Development on Agent Sightings (number 86 by interest), and one of 10 involving Perplexity Comet.

How you could try it

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

In this repo, test API endpoints in Postman and report results. Read relevant code, apply a minimal patch, run available checks, and summarize the diff. Stop before merge or deploy.

The prompt breaks down into 3 steps you can check as the agent works:

  1. In this repo, test API endpoints in Postman and report results.
  2. Read relevant code, apply a minimal patch, run available checks, and summarize the diff.
  3. Stop before merge or deploy.

Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.

Source

Read the original first-hand account on X: https://x.com/ai_for_success/status/1995164144509784334. Our summary is a paraphrase; details are in the source.

Related sightings

← All 991 use cases