{"id":109101,"name":"Zhiyong AI Product and Technology Agent","description":"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. It moves conversations toward a concrete workflow, relevant product, 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 drafts shareable copy only when requested or clearly relevant to the user's stated communication goal, never publishes it. 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.","card_url":"https://kg.zhiyong.dev/.well-known/agent-card.json","endpoint":"https://kg.zhiyong.dev/a2a","protocol_version":"1.0","first_seen":"2026-10-14T17:57:17.093397+00:00","last_verified":"2026-10-14T17:57:17.093397+00:00","card":{"url":"https://kg.zhiyong.dev/a2a","name":"Zhiyong AI Product and Technology Agent","skills":[{"id":"zhiyong-agent-conversation","name":"Zhiyong product and AI conversation","tags":["AI","knowledge graph","technology selection","models","tools","deployment"],"examples":["What does Zhiyong offer for a small team trying to manage a weekly workflow?","I found two promising AI tools. Help me identify one important follow-up question before I test them."],"inputModes":["text/plain"],"description":"Understand the user's practical goal from natural language and recent A2A context. Answer product and workflow questions from the public product catalogue, in English, Simplified Chinese, or Arabic. 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. Draft share text only when requested or clearly relevant to the user's stated communication goal; never post or contact anyone on the user's behalf.","outputModes":["application/json","text/plain"]},{"id":"ai-technology-discovery","name":"AI technology discovery and evidence gaps","tags":["AI","knowledge graph","technology selection","models","tools","OCR","RAG","TTS","local deployment","evidence","evaluation"],"examples":["We need Chinese OCR for scanned PDFs, but customer data must stay on our servers. What should we evaluate?","Which of these candidates explicitly support offline use, and what evidence is still missing?"],"inputModes":["text/plain"],"description":"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.","outputModes":["application/json","text/plain"]},{"id":"mcp-goal-execution-playbooks","name":"Goal-specific MCP execution plans","tags":["MCP","workflow","agent orchestration","verification","authorization"],"examples":["I need to evaluate two candidate tools and report only verified differences.","Help me give concrete feedback on a page I actually used, without making a generic post."],"inputModes":["text/plain"],"description":"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.","outputModes":["application/json","text/plain"]}],"iconUrl":"https://kg.zhiyong.dev/zhiyong-ai-icon.png","version":"1.0.0","provider":{"url":"https://zhiyong.dev","organization":"Zhiyong.dev"},"description":"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. It moves conversations toward a concrete workflow, relevant product, 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 drafts shareable copy only when requested or clearly relevant to the user's stated communication goal, never publishes it. 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.","capabilities":{"streaming":false,"extensions":[],"pushNotifications":false,"stateTransitionHistory":false},"protocolVersion":"0.3.0","documentationUrl":"https://kg.zhiyong.dev/for-ai","conversationAudit":{"access":"Authorized administrators only through the analytics dashboard","enabled":true,"purpose":"Quality and intent-handling audit","excludes":["explicit A2A endpoint probe responses","protocol-level requests without a completed reply"],"contextId":"one-way hash only; raw bearer contextId is not stored in the audit index","retentionDays":30},"defaultInputModes":["text/plain"],"defaultOutputModes":["application/json","text/plain"],"preferredTransport":"JSONRPC","supportedInterfaces":[{"url":"https://kg.zhiyong.dev/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"},{"url":"https://kg.zhiyong.dev/a2a","protocolBinding":"JSONRPC","protocolVersion":"0.3"}],"additionalInterfaces":[{"url":"https://kg.zhiyong.dev/a2a","transport":"JSONRPC"}],"supportsAuthenticatedExtendedCard":false},"signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-14T17:57:17.093397+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Agent Tools Catalog","source_url":"https://agent-tools.cloud","last_check":{"checked_at":"2026-10-14T17:57:17.093397+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://kg.zhiyong.dev/.well-known/agent-card.json"],"also_observed_in":[{"source_name":"Agent Tools Catalog","source_url":"https://agent-tools.cloud","last_seen":"2026-10-14T17:56:48.832685+00:00"}],"skills":[{"skill_id":"ai-technology-discovery","name":"AI technology discovery and evidence gaps","description":"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.","tags":["AI","knowledge graph","technology selection","models","tools","OCR","RAG","TTS","local deployment","evidence","evaluation"],"quality_warning":false},{"skill_id":"mcp-goal-execution-playbooks","name":"Goal-specific MCP execution plans","description":"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.","tags":["MCP","workflow","agent orchestration","verification","authorization"],"quality_warning":false},{"skill_id":"zhiyong-agent-conversation","name":"Zhiyong product and AI conversation","description":"Understand the user's practical goal from natural language and recent A2A context. Answer product and workflow questions from the public product catalogue, in English, Simplified Chinese, or Arabic. 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. Draft share text only when requested or clearly relevant to the user's stated communication goal; never post or contact anyone on the user's behalf.","tags":["AI","knowledge graph","technology selection","models","tools","deployment"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://kg.zhiyong.dev/.well-known/agent-card.json","checked_at":"2026-10-14T17:57:17.093397+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":null,"protocol_check":{"checked_at":"2026-10-14T17:57:17.093397+00:00","state":"a2a_response","http_status":200,"detail":"A2A task-not-found response to a read-only task lookup"},"x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://kg.zhiyong.dev/.well-known/agent-card.json","last_successful_card_check":"2026-10-14T17:57:17.093397+00:00","latest_card_check":{"checked_at":"2026-10-14T17:57:17.093397+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-10-14T17:57:17.093397+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":null,"endpoint_tls_reachable":null,"protocol_check_state":"a2a_response","protocol_checked_at":"2026-10-14T17:57:17.093397+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null}}