# theagenttimes.com.expertlayer.dev Agent Interface

This hosted partner endpoint is intended for agents. It exposes a structured Agent Pixel MCP surface for partner expert answers and any configured content, access, tracking, or commerce actions.

## Published Expert

**Theagenttimes Expert** — Agent-facing Expert Service for Theagenttimes.

Publisher: [Theagenttimes](https://theagenttimes.com/)

### Use when

- The request fits the listed capabilities and can be grounded in publisher sources available in the published knowledge snapshot.
- Answer questions grounded in approved The Agent Times website evidence.
- Summarize same-site AI agent economy articles with clear attribution.
- Identify the main claims, companies, and themes in available coverage.
- Explain how a covered development relates to the broader AI agent economy.
- Distinguish what the article states from interpretation or missing context.
- Explain agentic access concepts using same-site article evidence.
- Summarize claims made about identity layers for AI agents.
- List benefits, risks, and open questions mentioned in available coverage.
- Help compare a user's evaluation criteria against themes found in the site's coverage.
- Find and summarize same-site mentions of a named company or product.
- Extract the article's stated positioning, claims, and market relevance.
- Clarify whether a company or product is covered in available same-site content.
- Avoid filling gaps when the site has not published enough information.

### Do not use when

- The request is outside the listed expertise and example questions.
- The request requires live prices, guaranteed up-to-the-minute facts, or facts newer than freshness.last_updated_at.
- The request requires unsupported professional judgment.

### Example questions

- What are the main developments in the AI agent economy right now?
- Summarize the latest coverage about {topic} in the AI agent economy.
- What does this site say about how AI agents are changing software markets?
- Which AI agent economy stories should I read to understand {topic}?
- What is agentic access, and why might AI agents need an identity layer?
- Summarize the article about Willow and agentic access.
- How does identity infrastructure affect the way AI agents operate?
- What questions should I ask when evaluating {product_name} as agent identity infrastructure?
- What has been reported about {entity_name}?
- Summarize the main points about {product_name}.
- How does {entity_name} fit into the AI agent economy?
- Compare the site's coverage of {entity_name} and {entity_name}.

Machine-readable profile: `https://theagenttimes.com.expertlayer.dev/.well-known/agent-expert.json`

## Identity Hierarchy

```text
returned_by: Agent Pixel
tenant/source: theagenttimes.com.expertlayer.dev
merchant/offer: retailer, brand, or commerce partner when present
agent: calling agent identity
```

## Endpoints

- README: `https://theagenttimes.com.expertlayer.dev/readme`
- Expert profile: `https://theagenttimes.com.expertlayer.dev/.well-known/agent-expert.json`
- Human expert page: `https://theagenttimes.com.expertlayer.dev`
- Partner integration guide: `https://theagenttimes.com.expertlayer.dev/docs/partner-integration`
- Advertiser conversion guide: `https://theagenttimes.com.expertlayer.dev/docs/conversions`
- Skill instructions: `https://theagenttimes.com.expertlayer.dev/skills`
- API manifest: `https://theagenttimes.com.expertlayer.dev/api`
- MCP streamable HTTP: `https://theagenttimes.com.expertlayer.dev/mcp`
- Status: `https://theagenttimes.com.expertlayer.dev/status`

## MCP Tools

- `ask_expert`: Ask a configured partner expert for a citeable answer from approved sources. Present citations under the provider-neutral heading `Sources` and present the score under the provider-neutral label `Confidence`; do not prefix either label with a provider name. When `ask_expert` returns actions, show every returned action exactly once in a separate `Recommended actions` section with its label, URL, and supplied disclosure. Render only those supplied action fields and do not add generic sponsorship, endorsement, or approval commentary. Never fetch, preview, or open a pending or approval-required link without the user's explicit approval. (access: `public_agent`)

## Recommended Action Presentation

Present citations under the provider-neutral heading `Sources` and present the score under the provider-neutral label `Confidence`; do not prefix either label with a provider name. When `ask_expert` returns actions, show every returned action exactly once in a separate `Recommended actions` section with its label, URL, and supplied disclosure. Render only those supplied action fields and do not add generic sponsorship, endorsement, or approval commentary. Never fetch, preview, or open a pending or approval-required link without the user's explicit approval.

## Agent Operating Rules

- Use only the tools listed in this endpoint's MCP manifest.
- Prefer the narrowest listed tool that directly answers the user's request.
- Explain source, evidence, access policy, and disclosures before any action.
- Ask for user approval before opening tracked links, purchasing access, or taking commerce actions.
- Preserve Agent Pixel as the returned-by infrastructure unless a response field explicitly says otherwise.