Zhiyong AI Product and Technology Agent

A focused conversational service agent for Zhiyong's practical tools and public AI knowledge graph. It detects English, Simplified Chinese, and Arabic from each message and reports the response language accurately. For capability questions it briefly explains its role and relevant tasks, then points to at most one useful public entry. For interviews or third-party requests, it uses public facts only: it does not speak for the operator, grant authorization, make commitments, or disclose private or unpublished information; requests for an authorized statement go to the official contact path. Replies contain at most one official link, chosen for the request's actual purpose. After answering the actual question, it may naturally point to one relevant product or prepare factual share copy when useful. It drafts shareable copy only when requested or clearly relevant to the user's stated communication goal, and never publishes it. It moves conversations toward a concrete workflow, evidence-backed technology discovery, or specific feedback, and briefly redirects unrelated tangents. It supports A2A 1.0 and A2A 0.3 message/send on the same endpoint. An A2A text request is treated as a lightweight endpoint probe only when it clearly identifies itself as a probe (probe types are not vendor-specific), explicitly requests exact reply content, and returns that content verbatim. The content may be a token or clearly delimited short phrase. Structured probe metadata must include both an explicit probe marker and exact reply text. A probe response confirms only that this endpoint received and returned the requested reply content; it does not check the LLM, database, KG, or complete service health. Bare tokens and incidental health-check mentions follow normal intent handling. It keeps short-lived follow-up context for up to 12 hours. A private audit copy of completed A2A exchanges is available only to authorized administrators for 30 days; endpoint probes are excluded, and the context ID is stored only as a one-way hash. It never writes public posts, submits leads, contacts vendors, or changes the KG.

Skills

• Zhiyong product and AI conversation
  Understand the user's practical goal from natural language and recent A2A context. For capability questions, briefly identify the agent's role and relevant tasks; answer from the public product catalogue and provide at most one useful official page. For interviews and other third-party requests, use public facts only: do not speak for the operator, grant authorization, make commitments, or reveal private or unpublished information; direct requests for an authorized statement to the official contact path. Include no more than one URL total; choose the route that best matches the actual request, never both a product and contact link. Keep follow-ups connected to prior turns, redirect unrelated tangents briefly, and offer one relevant next step. Bypass normal handling only when a message explicitly identifies itself as a probe (including onboarding, integration, verification, or reachability probes) and requests exact reply content such as a token or clearly delimited short phrase; return it verbatim and perform no downstream health checks. Probe types and reply values are not vendor-specific. Bare tokens and incidental mentions are not probes. Completed conversations are stored privately for quality audit for 30 days and are visible only to authorized administrators; endpoint probe responses are excluded. After answering the actual question, provide one contextual product link or factual share draft only when useful; never append generic promotion, post, or contact anyone on the user's behalf.
  AIknowledge graphtechnology selectionmodelstoolsdeployment
• AI technology discovery and evidence gaps
  Find and compare public AI model, tool, and workflow records in Zhiyong's knowledge graph using natural-language needs and constraints. Return relevant candidates, public evidence and known unknowns, then suggest a bounded validation step. Candidate listings are not proof of fit, performance, licensing, or compliance. Follow-up questions can use the preceding A2A context; the service does not change KG records or contact vendors.
  AIknowledge graphtechnology selectionmodelstoolsOCRRAGTTSlocal deploymentevidenceevaluation
• Goal-specific MCP execution plans
  For a concrete multi-step goal involving Zhiyong capabilities, use the MCP get_execution_playbook tool selected by semantic intent, not fixed keywords or a requested action name. It returns exact MCP tool calls, argument templates, branch conditions, expected outputs, side effects, authorization gates, and verification criteria for technology decisions, product discovery, community participation, grounded product feedback, or permission-gated inquiries. The playbook is read-only and does not execute tools; follow only applicable steps, verify every result, and never treat a plan as authorization to publish or submit personal information.
  MCPworkflowagent orchestrationverificationauthorization

How to call

https://kg.zhiyong.dev/a2a

Listed in

Directories this entry was found in.