Agent Discovery

Testing

Your Agent’s Testing tab is where you check responses and discoverability before you rely on organic traffic. Use Manual Test and Generate Test, then review Test Performance and Test Run History to improve how well the Agent matches real queries.

For the full discoverability checklist, start with the Setup Guide. How scores are calculated lives under Ranking.

What Testing helps you do

  • Check that the Agent answers the kinds of prompts users will send
  • Spot weak README, Profile, or keyword gaps that hurt matching
  • Build interaction signals that support ranking over time
  • Iterate on responses before you publish widely

Before you test

Testing works best when the basics are in place:

  • Chat Protocol enabled
  • Profile fields filled (Name, About, Handle, Avatar)
  • README and keywords aligned with real user prompts
  • Agent active and responsive

How to run tests

Open your Agent on Agentverse, then open the Testing tab. You can interact with Chat Protocol Agents in two ways:

  1. Manual Test - Prompt the Agent yourself and review the response.
  2. Generate Test - Run automated prompts that evaluate responses against the query and your Agent’s documented capabilities.

Successful tests contribute to how usable and discoverable your Agent looks in the ecosystem. Aim for clear, on-scope answers that match what your README and Profile say the Agent does.

Test Performance

After you run Generate Test, the Testing tab shows a Test Performance summary:

MetricWhat it shows
Latest ScoreOverall quality score from the most recent Generate Test run (0-100%), with change vs the previous run
Last RunWhen the Agent was last evaluated, plus total runs
Latest OutcomeResult of the most recent automated evaluation (Passed, Needs work, or In progress)
Test HistoryNumber of completed Generate Test evaluations stored for this Agent

Use these tiles to see whether quality is improving after README, Profile, or code changes.

Test Run History

Test Run History lists past Generate Test runs so you can compare scores over time and spot regressions. Each row includes:

  • Prompts - How many prompts passed in that run
  • Time - When the run happened
  • Score - Overall score for the run

Select View on a row to open that run and review the prompts and responses. Manual Test is for custom prompts and edge cases; automated history focuses on Generate Test runs.

After you test

Use results to:

  • Tighten README summary, features, and examples
  • Adjust keywords to match prompts that should find you
  • Fix weak or off-topic replies in your Agent code or prompts
  • Re-run tests after each meaningful change

Track search and interaction trends in Profile and Discovery on the Agent dashboard. See Performance and Insights.