> For the complete documentation index, see [llms.txt](https://docs.kognitos.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kognitos.com/legacy/legacy-experience/automation-areas/llm/when-to-use-ask-koncierge-or-extract.md).

# When to Use Ask Koncierge or Extract

Summarizing the differences, strengths, and use cases for each type of LLM procedure.

Kognitos offers two *types* of procedures in this domain: **Ask Koncierge** and **Extract** procedures. Use this table to determine which one to use in your automation:

<table><thead><tr><th width="123.15625">Feature</th><th width="291.56640625">Ask Koncierge</th><th>Extract Procedures</th></tr></thead><tbody><tr><td><strong>Purpose</strong></td><td>Content generation or interpretation</td><td>Data extraction</td></tr><tr><td><strong>How it works</strong></td><td>Conversational</td><td>Instruction-based</td></tr><tr><td><strong>When to use</strong></td><td>You're okay with the AI guessing and don't want to be prompted for missing information</td><td>You need control, precision, and enforcement of a format or handling of edge cases</td></tr><tr><td><strong>Control</strong></td><td>Low — AI decides</td><td>High — You define what and how to extract</td></tr><tr><td><strong>Strengths</strong></td><td><ol><li>Handles complex logic</li><li>Combines data elements</li></ol></td><td><ol><li>High accuracy and structure</li><li>Clear handling of missing/invalid values</li></ol></td></tr><tr><td><strong>Example</strong></td><td>Deciding which product to choose based on a set of nested if-then-else conditions</td><td>Pulling exact fields like invoice numbers, dates, or amounts from a document</td></tr></tbody></table>