Urgent.News

What's breaking now, across thousands of outlets.

Tech

My test agent scored 12/100 on Agentverse. Five profile fixes got it to 72

Got a uAgent on Agentverse that nobody chats with? Check the profile before the code. A lot of how Agentverse ranks agents comes from it, and ASI:One mostly surfaces the agents that rank well. To see how much it matters, I set up a test agent with nothing on it. No README, no handle, no avatar, no description, and it wasn't running. Then I scored it against the factors in the Agentverse ranking…

A test agent on Agentverse received a low score of 12/100 due to several factors, which were later addressed to improve its ranking. Only active agents are considered for ranking, and inactive agents are deprioritized. To fix this, the agent had to be hosted on Agentverse or run as a mailbox agent on a continuously running service like a VPS with a watchdog.

The Chat Protocol was also crucial, as the test agent already had it, which contributed to the initial score. Further improvements included writing a comprehensive README with six sections, including a summary, key features, usage instructions, use cases, limitations, and metadata. The handle, avatar, and description were also optimized to enhance discoverability and ranking.

After these changes, the test agent scored 72/100. Additional points came from having at least 10 interactions with the agent, verifying the website, and providing starter prompts for new users. The author created a free agent named "Agent Doctor" to help other users assess and improve their own agents using this checklist.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Building Zero-Latency Real-Time Audio & Vision Agents in Pure Python: Sub-10ms VAD, Instant Barge-In & Full-Duplex WebSockets

In 2026, artificial intelligence underwent a fundamental architectural shift: models transitioned from turn-based text request-response interfaces to full-duplex, streaming multimodal perceptual…

  • Sub-10ms voice activity detection (VAD) achieved in pure Python
  • Instant barge-in interrupt stops AI speech output
  • Vision processing uses keyframe sampling and perceptual hash deltas

How I Built a Boston Common Shadow Study From a Single Map Selection

The setup Last month I wanted a shadow study of Boston Common without downloading LiDAR, learning a full GIS stack, or asking anyone for a license.

  • Defined question focused on Boston Common's southwest lawn shade at 3 pm in December
  • Chose rectangular bounding box encompassing Common plus two blocks in every direction
  • Used stationary elevated camera for consistent comparisons at 9 am, noon, and 3 pm

More from Tuesday 3 November →