Unverified50% confidenceFactExact time
When an Agent runs, it typically reads multiple layers of System Prompts, divided into a global layer (effective for all projects) and a project layer (effective for the current project).
1
Sources
50%
Confidence
Long-term
Relevance
9/5/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn a multi-Agent architecture, each Agent can have independent System Prompts and toolsets, focusing on specific domains to improve output quality and task completion rates.77% similarVerifiedThe project adopts a multi-agent collaborative architecture, decomposing job-seeking tasks into independent agents with different responsibilities.75% similarUnverifiedThe Agent's workflow can be summarized as: receive user instructions → decompose complex tasks into multiple sub-steps → sequentially invoke corresponding tools to execute → aggregate results and output.75% similarUnverifiedIn a Multi-Agent architecture, the Orchestrator Agent is responsible for task decomposition and progress tracking, while Worker Agents each have their own role (e.g., Search Agent for retrieval, Critic Agent for validation, Writer Agent for output merging).75% similarUnverifiedAgent采用感知层、思考层、行动层三层架构协同运作74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/861827API
curl https://kongchang.com/api/v1/knowledge/claims/861827MCP
get_claim(id=861827)