Response Fields

This page explains the data returned by the LLM Scraper. Each field is briefly described, with an example where relevant, so teams can quickly understand and integrate the response.

Top-Level Fields

Field	Description	Example
traceID	Unique identifier for the request. Used for debugging, support, and internal tracking.	"traceID": "a1b2c3d4-e5f6-7a8b-9c0d-e1f2a3b4c5d6"
timestamp	ISO-8601 timestamp indicating when the request was processed.	"timestamp": "2026-04-16T10:56:56.252Z"
request_duration	End-to-end request duration in seconds (from request received to response returned).	"request_duration": 14.28
process_duration	Total internal processing time in seconds. This includes the full request lifecycle.	"process_duration": 14.28
scraper	Scraper name by LLM Engine	"scraper": "Copilot"

Note request_duration is included within process_duration. For example, if request_duration is 14.28 and process_duration is 14.28, the overall time experienced by the client is 14.28 seconds.

---

Response Object

The main parsed output from the LLM.

---

prompt

The original prompt sent to the LLM for this request. This field is always returned as part of the response for traceability and debugging.

Example

"prompt": "what are the leading SEO tips in 2026"

---

text_markdown

Markdown-formatted version of the response, preserving structure such as headings, lists, emphasis, and inline citations.

This field represents the primary readable output of the LLM, including formatting and citation markers as returned by the model.

Example

"text_markdown": "**The leading SEO tips for 2026 center on AI-readiness, entity-based optimization, technical excellence, and delivering deeply useful, intent-matched content.**\n\n### 1. Optimize for AI-Driven Search & LLM Discovery\n- Build **topic clusters** and **entity relationships** instead of isolated keyword pages.\n- Use **structured data** and schema to make content easy for AI to cite."

---

text (plain text)

Plain-text version of the response with formatting removed. Useful for storage, indexing, or systems that don't support Markdown.

Example

"text": "The leading SEO tips for 2026 center on AI-readiness, entity-based optimization, technical excellence, and delivering deeply useful, intent-matched content."

---

citations_found

Boolean indicating whether the model output included citations.

Example

"citations_found": true

---

citations

Flat list of citation objects extracted from Copilot.

Each citation includes:

• id

• title

• url

• section: "citations" or "more"

Example

"citations": [
  {
    "id": 1,
    "url": "https://moz.com/blog/top-seo-tips-2026-whiteboard-friday",
    "title": "Top SEO Tips For 2026 - Moz",
    "section": "citations"
  },
  {
    "id": 2,
    "url": "https://sitebulb.com/resources/guides/seo-in-2026-17-expert-tips-predictions/",
    "title": "SEO in 2026: 17 Expert Tips & Predictions - Sitebulb",
    "section": "citations"
  }
]

---

inline_citations

Structured citations extracted directly from the main response text.

Each inline citation represents a specific source tied to an exact text span (anchor) in the generated answer.

Unlike citations, which are a flat list of sources, inline_citations show where and how each source is used inside the content.

Each inline citation includes:

• id

• title

• url

• text_anchor

Example

"inline_citations": [
  {
    "id": 1,
    "url": "https://moz.com/blog/top-seo-tips-2026-whiteboard-friday",
    "title": "Top SEO Tips For 2026 - Moz",
    "text_anchor": "Build topic clusters and entity relationships instead of isolated keyword pages. Use structured data and schema to make content easy for AI to cite."
  },
  {
    "id": 2,
    "url": "https://sitebulb.com/resources/guides/seo-in-2026-17-expert-tips-predictions/",
    "title": "SEO in 2026: 17 Expert Tips & Predictions - Sitebulb",
    "text_anchor": "Improve crawlability, internal linking, and site architecture. Demonstrate E-E-A-T to become a trusted source for both humans and AI."
  }
]

Notes

• A single text span may have multiple inline citations

• id corresponds to the same source in the citations array

---

tables

Structured tables extracted from the Copilot response.

Each table includes a title, table_columns array, and table_rows array where each cell is represented as an object with a value key.

Example

"tables": [
  {
    "title": "Quick Comparison: What Matters Most in 2026",
    "table_columns": ["Priority", "Why It Matters"],
    "table_rows": [
      [{"value": "AI & Entity Optimization"}, {"value": "AI search relies on semantic understanding"}],
      [{"value": "Technical SEO"}, {"value": "Crawlability + speed directly impact rankings"}]
    ]
  }
]