VQV Signal

DEVELOPING WATCH PRACTICAL

Sierra introduces Poppy, a way for companies to set rules for visiting AI agents

According to a post on X by @SierraPlatform, Sierra has introduced Poppy, a way for companies to set rules for AI agents that visit their sites. Sierra says personal agents today either pass themselves off as the user or get blocked. Under Poppy, an agent connecting to a company for the first time reads that company's poppy.json file, identifies itself, and starts a signed-out session. The company therefore decides how visiting agents can interact with it.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-10-26T21:55:00+00:00 Detected 2026-10-27T09:17:43+00:00
View original source

According to a post on X by @SierraPlatform, Sierra has introduced Poppy, a way for companies to set rules for AI agents that visit their sites. Sierra says personal agents today either pass themselves off as the user or get blocked. Under Poppy, an agent connecting to a company for the first time reads that company's poppy.json file, identifies itself, and starts a signed-out session. The company therefore decides how visiting agents can interact with it.

AI-assisted summary based on the listed source.

Sierra says personal agents today either pass themselves off as the user or get blocked. With Poppy, an agent that connects to a company for the first time reads the company's poppy.json file, identifies itself and starts a signed-out session, so the company decides how agents can interact with it. Original post...

Site operators could use the poppy.json file to set the terms for agents that visit, instead of relying on agents to disguise themselves or being blocked outright. Builders of personal agents would need to follow these rules to interact with companies that adopt the approach. The source does not give details on adoption, supported platforms or the file format, so the next thing to watch is whether Sierra publishes documentation and other companies use it.

Signal Strength 86% Technical label WATCH Public Interest 40 Category DEVELOPING Reader Depth PRACTICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 0 Practical Impact Score 56 Novelty Interest Score 94 Consequence Score 18 Curiosity Score 16 Shareability Score 55

VQV surfaced this signal because it is recent, relevant to AI Agents, connected to Scobleizer News Pulse (X).