​
Personalized Response Styles

Cortex doesn’t just answer — it learns how you like your answers.

Over time, the system adapts to each user’s preferences by observing their behavior, past queries, and feedback loops. This includes:

  • Preferred formats (e.g. tables, bullet points, summaries)
  • Preferred tone (e.g. concise, friendly, formal)
  • Preferred depth (e.g. quick summary vs detailed explanation)
  • Specific content types (e.g. Excel files, slide decks, contracts)

You can also allow users to explicitly specify how they want answers — for example:

"I prefer comparisons in a markdown table."
"I like summaries with bullets, not long paragraphs."

This creates a highly tailored experience where answers feel personalized, not generic.

​
Smart Clarifications

When users ask vague or ambiguous questions, Cortex’s intelligent search agent recognizes this and asks for clarification instead of performing a poor-quality search.

Rather than returning irrelevant or incomplete results from unclear queries, and just plain ChatGPT answers, the system:

  • Detects ambiguous language in user questions
  • Identifies missing context that would improve search quality
  • Generates targeted clarification questions to gather more specific information
  • Waits for user input before proceeding with the search

This happens automatically when the AI determines a query is too broad, unclear, or lacks sufficient context to provide meaningful results.

Example interaction:

{
  "question": "Tell me about the contract",
  "response": {
    "clarification_needed": true,
    "clarification_question": "I found several contracts in your documents. Could you specify which contract you're interested in, or what specific aspect you'd like to know about (e.g., terms, pricing, termination clauses)?"
  }
}

You can use these clarification questions in your frontend to prompt users for more details, ensuring they get high-quality, relevant answers rather than generic responses. This creates a more conversational experience and significantly improves result accuracy.

​
Grounded with Citations

Every response can be grounded in source material using Cortex’s built-in citation system.

When a user asks a question, the answer is generated using documents, web data, or memory — and the system:

  • Returns the exact chunks of source text used to build the answer
  • Provides source IDs, titles, page numbers, and optionally bounding box coordinates for PDFs
  • Allows the frontend to show inline citations, source previews, or even highlight regions in original files

Example output:

{
  "answer": "The contract allows termination with a 30-day notice after 12 months.",
  "sources": [
    {
      "source_id": "doc-123",
      "title": "contract.pdf",
      "page": 3
    }
  ],
  "chunks": [
    {
      "text": "The contract specifies a 12-month term...",
      "bounding_box": {
        "x": 120, "y": 320, "width": 180, "height": 40
      }
    }
  ]
}

This keeps responses auditable, explainable, and trustworthy — especially useful in enterprise, legal, and compliance settings.

​
Filter by Metadata

You can restrict the context used for answering questions by providing tenant_metadata and document_metadata parameters in upload API calls. This allows you to filter sources by source_title or source_type.

"tenant_metadata": {"source_title": "contract.pdf"},
"document_metadata": {"source_title": "contract.pdf"}

Only sources matching the provided metadata will be used for context.

​
Creative Mode

Sometimes, users want answers that go beyond their knowledge base. Creative mode allows your app to let LLMs generate responses without solely relying on the retrieved context. It’s like interfacing directly with ChatGPT.

With creative_mode enabled, Cortex shifts from strictly grounded retrieval to imaginative generation, allowing it to:

  • Suggest new ideas or concepts
  • Generate content beyond the original sources
  • Expand on partial context using LLM capabilities

Use this when you want the AI to help with:

  • Brainstorming things outside of the context
  • Writing summaries with flair
  • Exploring hypothetical ideas
  • Rewriting answers for tone and creativity

You can toggle this mode using the search_mode: ["creative"] parameter in the /search/qna API call.

{
  "question": "Give me 5 fun blog title ideas about data privacy",
  "search_mode": ["creative"]
}

​
Combine All Modes

Cortex’s strength is in combining these capabilities into one flexible response system:

  • Retrieval + Generation: Factual answers grounded in sources
  • Memory + Personalization: Responses that evolve to match each user
  • Creativity + Control: Creative responses when needed, factual when not

Whether you’re building a research assistant, support bot, or content co-pilot — Cortex helps your AI speak with intelligence and personality.