VQV Signal

AI AT WORK WATCH TECHNICAL

Fetch.ai's ASI:One adds stateful /v1/responses API for continuing conversation threads

According to a post on X by @Fetch_ai, its ASI:One platform has added a stateful /v1/responses API. Developers can create a response, save its ID, and continue the thread by passing previous_response_id instead of resending the whole conversation. The same ID can be used to retrieve, cancel or delete a response, and output arrives as typed items such as reasoning, messages and tool calls. The snippet is partial, so other details are not covered here.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-21T14:30:00+00:00 Detected 2026-11-21T22:04:00+00:00
View original source

According to a post on X by @Fetch_ai, its ASI:One platform has added a stateful /v1/responses API. Developers can create a response, save its ID, and continue the thread by passing previous_response_id instead of resending the whole conversation. The same ID can be used to retrieve, cancel or delete a response, and output arrives as typed items such as reasoning, messages and tool calls. The snippet is partial, so other details are not covered here.

AI-assisted summary based on the listed source.

Developers can now create a response with ASI:One, save its id, and continue the thread by passing previous_response_id instead of resending the whole conversation. The id can also be used to retrieve, cancel or delete a response, and output arrives as typed items such as reasoning, messages and tool calls. Why it...

Developers building chat or agent applications on ASI:One could keep conversation state on the server instead of resending the full history with each request. The post says this reduces token overhead and simplifies application building, though this claim has not been independently tested here. Teams should check the official documentation for details on how stored responses are handled.

Teams using AI at work may want to compare this against current productivity and review workflows.

Signal Strength 78% Technical label WATCH Public Interest 42 Category AI AT WORK Reader Depth TECHNICAL

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 74 Novelty Interest Score 70 Consequence Score 38 Curiosity Score 16 Shareability Score 54

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