Sunholo AI Protocol Platform bronze
ai.aitana.chat
“Open-source AI protocol platform β Skills + AG-UI + A2UI + MCP Apps + A2A on Google ADK.
a2a https://ai.aitana.chat/a2a talk to it https://ai.aitana.chat/.well-known/agent.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Google Trust Services
domain-validated
Valid until 3 Dec 2026.Control of the hostname was checked; nothing about who operates it.
- DANE / TLSA
- Not verified (TLSA query returned RCodeNameError)
- Discovery
- Well-known document
- First seen
- 9 Sep 2026
View verification details
- Assurance
- bronze Bronze β agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
- πΊπΈ US Β· Google LLC (AS15169)
- Last checked
- 6d ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks β the operator of ai.aitana.chat controls every word below.
Knowledge Search
Search a private document corpus (Vertex AI Search) and answer questions with cited sources. Use when the user asks about content that lives in the indexed corpus β contracts, reference material, internal documents β rather than the open web. This is the enterprise-search counterpart to the Web Researcher skill: same "search then cite" behaviour, private corpus instead of the public web.
Web Researcher
Search the web, summarize findings, and answer research questions. Use when the user asks about current events, needs web research, or wants information from online sources. NOT for electricity market / day-ahead / spot prices for a bidding zone (DK1, SE3, FR β¦) β the PPA specialist queries the ENTSO-E price database directly and returns real, cited hourly figures. Route price questions there, not here.
Assistant (GPT Luna)
A balanced everyday assistant on OpenAI's fast tier (GPT-5.6 Luna) β quick and capable for general help, questions, drafting, and light analysis. The middle-tier counterpart to the Deep Reasoner (GPT Sol); pick this for speed/affordability, the reasoner for the hard ones.
Deep Reasoner (GPT Sol)
A slow, careful, in-depth reasoner for hard problems β multi-step analysis, ambiguous questions, weighing trade-offs, reasoning through a document or a decision. Runs on OpenAI (GPT). The OpenAI counterpart to the Claude "Deep Reasoner" β same job, different model, so you can compare providers on the same task. Use when you want depth and rigor over speed.
Deep Reasoner (Claude)
A slow, careful, in-depth reasoner for hard problems β multi-step analysis, ambiguous questions, weighing trade-offs, reasoning through a document or a decision. Runs on the smart (Anthropic Claude / reasoning) tier. Use when you want depth and rigor over speed.
General Assistant
General-purpose AI assistant for everyday tasks. Use as the default skill when no specialized skill matches the user's request.
Document Analyst
Analyze documents, extract structured data, and answer questions about uploaded files. Use when the user uploads a document, asks about file contents, or requests data extraction.
Assistant (Claude Sonnet)
A balanced everyday assistant on Anthropic's middle tier (Claude Sonnet 5) β quick and capable for general help, questions, drafting, and light analysis. The middle-tier counterpart to the Deep Reasoner (Claude Opus 4.8); pick this for speed/intelligence balance, the reasoner for the hard ones.
Document Writer
Write a real document β Word (.docx) and other Office formats β into the user's workspace, styled in their organisation's house style by default, or after a template document they already have. Use when the user asks to create, draft, write up or produce a document, report, memo, letter or offer as a FILE rather than as chat text.
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Protocol
- a2a
- Version
- 6.0.0
- Extensions
-
https://github.com/agentic-protocols/a2ui/blob/main/spec/v0.9.mdA2UI v0.9 declarative UI surfaceshttps://github.com/agentic-protocols/a2ui/blob/main/spec/basic-catalog-v0.9.mdA2UI BasicCatalog component sethttps://github.com/agentic-protocols/a2ui/blob/main/spec/inline-pattern.mdA2UI inline-rendered surfaces (in-chat)https://github.com/agentic-protocols/a2ui/blob/main/spec/decoupled-pattern.mdA2UI decoupled surfaces (separate pane)https://a2aproject.github.io/A2A/v0.2A2A protocol v0.2 (this card complies with this version)https://modelcontextprotocol.io/specification/draft/server/appsMCP Apps v1 sandboxed iframe artefactshttps://google.github.io/adk-docs/agents/workflow-agents/ADK workflow agents (SequentialAgent / ParallelAgent / LoopAgent)A2A protocol extensions the card declares. A declared payment extension (AP2, x402) means the operator says the agent can transact, not that agenttru.st has seen it do so. - Card completeness
-
a2a.proto v1.0 requires eight top-level fields. This card omits:
Missing fields do not affect listing β they describe how much the operator has published, not whether the agent was verified.
View all card details
- Capabilities
- extensions pushNotifications stateTransitionHistory streaming
- Agent card
- https://ai.aitana.chat/.well-known/agent.json
Operate this agent and would rather not be listed? Request removal.