What are the different prompt types in Playbooks and when should I use them?

Quick Answer

Jylo offers five prompt types: Yes/No (binary decisions), List of values (multiple categories), Range of values (numerical results), Text (short answers with evidence), and Generative (long-form outputs). The first three can both analyse content and prompt documents, while Text and Generative are for analysis only. Choose your prompt type based on the information you need and how you plan to use it in your workflow.

Detailed Explanation

Prompts are the foundation of Playbooks in Jylo. Each type serves a specific purpose and produces distinct outputs:

Filtering-Capable Types

These prompt types can both analyse content and filter documents in Flows:

1. Yes/No
   • Output: Binary true/false decisions
   • Interface: Checkbox in the Flows filter panel
   • Best for: Clear binary questions (e.g., "Does this document contain confidentiality clauses?")
   • When to use: When you need to quickly separate documents into two categories
   • Example use case: Identifying which contracts contain specific provisions
2. List of values
   • Output: Multiple categorical items
   • Interface: Set of checkboxes in the Flows filter panel
   • Best for: Identifying multiple discrete elements (e.g., "Which parties are mentioned in this agreement?")
   • When to use: When documents should be grouped by categories or entities
   • Example use case: Extracting and filtering by company names, jurisdictions, or document types
3. Range of values
   • Output: Numerical results within a defined range
   • Interface: Slider control in the Flows filter panel
   • Best for: Numerical data that has meaningful minimum/maximum values
   • When to use: When you need to filter documents based on quantities or measurements
   • Example use case: Filtering contracts by value, duration, or ratings

Analysis-Only Types

These prompt types can analyse information but cannot filter documents:

4. Text
   • Output: Short string response with evidence links to source text
   • Interface: Text with "Evidence" buttons that highlight supporting content in the document
   • Best for: Extracting specific information that needs verification
   • When to use: When accuracy and source verification are critical
   • Example use case: Extracting specific clauses, terms, or definitions with evidence links
5. Generative
   • Output: Long-form text without citation links
   • Interface: Expanded text output without evidence buttons
   • Best for: Creating comprehensive analyses or summaries
   • When to use: When you need synthesised information rather than exact extractions
   • Example use case: Document summaries, explanations of complex concepts, or recommendations

All prompts are programmed to return evidence where possible other that Generative which is influenced by your instruction only.

Common Questions

When should I use Text vs. Generative prompt types?

Use Text prompts when you need concise answers with direct evidence from the document that users can verify. Choose Generative prompts when you need comprehensive analyses, summaries, or explanations where specific word-by-word citations aren't necessary.

Can I use Conditional Logic with all prompt types?

Yes, all prompt types except Generative can trigger conditions for other prompts. This means Yes/No, List of values, Range of values, and Text prompts can all be used to create dynamic workflows where certain questions only appear based on previous answers.

How do I handle unexpected or incorrect prompt responses?

During verification, you can edit AI responses for all prompt types. For List of values, you can remove incorrect items with the trash icon or add new categories. For Yes/No, you can toggle the correct answer. For Range of values, you can adjust the numerical value directly.

If You're Still Stuck...

If you're unsure which prompt type to use:

1. Consider the format of the answer you need (yes/no, categories, numbers, text)
2. Determine if you'll need to filter documents based on the response
3. Create a test Playbook with different prompt types to see which produces the most useful results

Still need help? Contact us via Zendesk.

Related Articles

• How do I create and use Flows?
• Understanding Playbooks 
• How do I set up conditional logic in Playbooks?
• How do I use the hash-linking system in Playbooks?