Unverified50% confidenceFactExact time
Decision Models work via local HTTP requests, with the text to be evaluated placed in State and the questions placed in Questions, and the local model answers all questions in a single request.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedAsk mode is a question-and-answer interaction, better suited for solving specific localized problems on top of existing projects.73% similarUnverifiedExplicitly asking the model to search online for the latest information when posing a question can leverage instruction-following capabilities to force real-time retrieval.72% similarUnverifiedThe actual number of tokens consumed by a single user request includes the entire input context (including conversation history, system prompts, tool definitions, etc.) as well as the response content generated by the model.69% similarUnverifiedAuto Mode's decision process first runs the user's deny, ask, and allow rules, then performs a tiered check to determine which actions are sent to the classifier.69% similarUnverifiedThe minimal pipeline of a large model Q&A system is: the user sends parameters from the frontend to the WebApp, which forwards them to the backend API via HTTP request, and the backend calls the large model for processing and renders the result back to the frontend.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984289API
curl https://kongchang.com/api/v1/knowledge/claims/984289MCP
get_claim(id=984289)