This document explains the Ask AI node, which lets you interact with AI models to process text and generate responses.

​
Node Inputs

​
Required Fields

  • Prompt: Main instruction or question for the AI. It should be clear and detailed to guide the AI to give you the best possible answer. When connected to other nodes, you can drag outputs from those nodes directly into your prompt from the side menu.
New UI Note: With Gumloop’s updated interface, when you connect nodes together, you can access data from previous nodes by dragging the output badges from the side menu directly into your prompt field. This eliminates the need for separate Combine Text nodes.

​
More Options

  • Choose AI Model: Select the AI model you want to use
  • Temperature: Controls response creativity (0-1). Default temperature is ‘1’
    • 0: More focused, consistent
    • 1: More creative, varied
  • Maximum Tokens: Limits response length
  • Cache Response: Save responses for reuse (only works when inputs and prompts remain constant)
  • Thinking Tokens (for Claude 3.7 Sonnet Thinking only): Set a budget for extended thinking mode
    • Minimum: 1024 tokens
    • Must be less than Maximum Tokens
    • Larger budgets improve reasoning quality for complex tasks

​
Show As Input

The node allows you to configure certain parameters as dynamic inputs. You can enable these in the “Configure Inputs” section:
  • prompt: String
    • The main instruction/prompt for the AI
    • Example: “Summarize this article”
  • model_preference: String
    • Name of the AI model to use
    • Accepted values: “Claude 3.7 Sonnet”, “Claude 3.7 Sonnet - Thinking”, “Claude 3.5 Haiku”, “GPT-4.1”, “GPT-4.1 Mini”, etc.
  • Use Function?: Boolean
    • true/false to enable/disable function calling
    • Only works with OpenAI models
  • Cache Response: Boolean
    • true/false to enable/disable response caching
    • Helps reduce API calls for identical inputs
  • Temperature: Number
    • Value between 0 and 1
  • Maximum Tokens: Number
    • Positive integer for maximum response length
    • Example: 2000
  • Thinking Tokens: Number (for Claude 3.7 Sonnet Thinking only)
    • Number of tokens allocated for extended thinking
    • Minimum: 1024 tokens
    • Example: 4000
When enabled as inputs, these parameters can be dynamically set by previous nodes in your workflow. If not enabled, the values set in the node configuration will be used.

​
Using Connected Node Data

With Gumloop’s new interface, adding data from connected nodes to your prompt is simple:
  1. First, connect nodes by dragging a connection line between them
  2. When configuring the Ask AI node, you’ll see available outputs from connected nodes in the side menu
  3. To use these outputs in your prompt, simply drag the output badge from the side menu and drop it into your prompt field
  4. You can format your prompt around these dynamic values
For example, to analyze website content: 
Analyze this website content and provide a one-page summary:

[drag Website Scraper badge here]
Alt text

​
Claude 3.7 Sonnet vs. Claude 3.7 Sonnet Thinking

Claude 3.7 Sonnet is available in two distinct modes that serve different use cases:
  1. Claude 3.7 Sonnet (Standard Mode):
    • Provides direct responses without extended internal reasoning
    • Quick response time suitable for most everyday tasks
    • Excellent for creative content, analysis, and general queries
    • More efficient for straightforward tasks where deep reasoning isn’t required
  2. Claude 3.7 Sonnet Thinking (Extended Thinking Mode):
    • Performs additional internal reasoning before delivering the final answer
    • Takes longer to respond but provides higher quality answers for complex problems
    • Especially valuable for tasks requiring:
      • Complex problem-solving with multi-step logic
      • Math calculations and derivations
      • Detailed code writing and debugging
      • Analytical tasks that benefit from thorough consideration
    • While the model performs more extensive thinking internally, only the final response is shown in Gumloop (the thinking process itself is not visible)
    • The model determines how much of the thinking tokens to use based on the task complexity
You can learn more about Claude 3.7 Sonnet here.

​
Thinking Tokens vs. Maximum Tokens

  1. Thinking Tokens (Claude 3.7 Sonnet Thinking only):
    • Budget for the model’s internal reasoning process
    • Must be less than Maximum Tokens
    • Minimum: 1024 tokens
    • Recommended: 4,000-16,000 for complex tasks
    • Larger budgets improve reasoning but increase cost and response time
  2. Maximum Tokens:
    • Total limit for the entire response (includes thinking + final answer)
    • Must be greater than Thinking Tokens
    • Sets the upper bound for response length

​
Node Output

  • Response: AI’s generated answer or output

​
Node Functionality

The Ask AI node connects to various AI models to:
  • Generate text responses
  • Process/analyze content
  • Answer questions
  • Summarize information
  • Convert data formats
  • Perform step-by-step reasoning (with thinking-enabled models)

​
Available AI Models

  • Claude 3.7 Sonnet
  • Claude 3.7 Sonnet Thinking (extended reasoning capabilities)
  • Claude 3.5 Haiku
  • OpenAI o3
  • OpenAI o3 Deep Research
  • OpenAI o4-mini
  • OpenAI o4-mini Deep Research
  • GPT-4.1
  • Grok 4
  • GPT-4.1 Mini
  • DeepSeek V3
  • DeepSeek R1
  • Perplexity Sonar Reasoning
  • Perplexity Sonar Reasoning Pro
  • Gemini 2.5 Pro
  • Gemini 2.5 Flash
  • Grok 3
  • Grok 3 Mini
  • Azure OpenAI
  • And more

​
Deep Research Support

The Ask AI node now supports Deep Research for:
  • OpenAI O3
  • OpenAI O4 Mini
Deep Research enables more comprehensive, multi-step reasoning and retrieval for complex queries that require thorough investigation and analysis.

​
AI Model Selection Guide

When choosing an AI model for your task, consider these key factors:
Model TypeIdeal Use CasesConsiderations
Standard ModelsGeneral content creation, basic Q&A, simple analysisLower cost, faster response time, good for most everyday tasks
Advanced ModelsComplex analysis, nuanced content, specialized knowledge domainsBetter quality but higher cost, good balance of performance and efficiency
Expert & Thinking-Enabled ModelsComplex reasoning, step-by-step problem-solving, coding, detailed analysis, math problems, technical contentHighest quality but most expensive, best for complex and long-form tasks, longer response time
Note: Auto-Select uses a third-party model routing service and automatically chooses the appropriate model for cost, performance, and availability. Not ideal if consistent model behavior is needed.
Additional selection factors:
  • Task complexity and required accuracy
  • Response time requirements
  • Cost considerations
  • Consistency needs across runs
  • Specialized knowledge requirements
For more detailed information on AI models with advanced reasoning capabilities, you can refer to:

​
Common Use Cases

  1. Content Creation:
Prompt: "Write a blog post about [drag Topic input badge here]"
  1. Data Analysis:
Prompt: "Analyze these sales figures and provide key insights:
[drag Sales Data input badge here]"
  1. Customer Support:
Prompt: "Answer this customer question professionally according to our company policies:
Customer Question: [drag Customer Query input badge here]"
  1. Step-by-step Problem Solving (with Thinking):
Prompt: "Solve this complex pricing optimization problem with the following constraints:
[drag Business Problem input badge here]"
Thinking Tokens: 8000

​
Loop Mode Pattern

  1. Batch Processing: 
    Input: List of articles
Prompt: "Analyze and find key patterns in this article: [drag Current Article output badge here]"
Result: Analysis for each article

​
Understanding Cache Response

The Cache Response option can significantly speed up your workflows when using the same inputs repeatedly:
  • When enabled, identical inputs will retrieve previous results instead of making new API calls
  • For caching to work, all of these must be identical:
    • Prompt text (including any inserted input badges)
    • Model selection
    • Temperature setting
    • Maximum tokens setting
    • Thinking tokens (if applicable)
  • Even small changes to any input will trigger a new API call
  • Perfect for testing workflows or handling repeated queries

​
Important Considerations

  1. Credit Costs:
    • Expert models (OpenAI o3, Claude 3.7 Thinking): 30 credits
    • Advanced models (GPT-4.1 & Claude 3.7): 20 credits
    • Standard models: 2 credits per run
    • With API key: 1 credit (configure in credentials page)
  2. Function Calling:
  3. Model Selection:
    • Consider task complexity when selecting models
    • For reasoning-heavy tasks, consider thinking-enabled or reasoning models
  4. Connected Nodes:
    • Remember to drag output badges from the side menu into your prompt
    • You can format text around the output badges for better prompting
    • Multiple connected nodes make all their outputs available in the side menu
  5. Ask AI Node is Text Based Only:
In summary, the Ask AI node is your interface to AI models, helping you automate text processing and generation tasks with customizable control over the output style and format. With Gumloop’s improved UI, you can easily incorporate data from connected nodes directly into your prompts without needing separate Combine Text nodes. For complex problems requiring step-by-step analysis, consider using advanced or expert AI models.