Thinkeo Documentation
HomeWebsiteAPI DocumentationThinkeo Platform
HomeWebsiteAPI DocumentationThinkeo Platform
  1. Best practices
  • ๐Ÿš€ Discovering the Thinkeo Platform
  • Get started
    • ๐Ÿš€ The Basics: Introduction
    • ๐Ÿงฉ The Basics: Blocks
    • ๐Ÿง™โ€โ™‚๏ธ The Basics: The Wizard
    • ๐Ÿท๏ธ The Basics: Attributes
    • 1๏ธโƒฃ Hands-on Practice - App and Attributes
    • 2๏ธโƒฃ Hands-on Practice - Blocks
    • 3๏ธโƒฃ Hands-on Practice - The AI Block
    • 4๏ธโƒฃ Hands-on Practice - The Wizard
    • 5๏ธโƒฃ Hands-on Practice - Block Execution
    • 6๏ธโƒฃ Hands-on Practice - Testing Your App
  • Apps
    • ๐Ÿ“ฑ Publication Interface
    • ๐Ÿ—๏ธ Studio
  • Blocks
    • ๐Ÿ“ File Block
    • โšก Block Execution
    • ๐Ÿค– AI Block
    • ๐Ÿงฉ Group Block
    • ๐Ÿ“ Paragraph Block
    • ๐Ÿ” Condition Block
    • ๐ŸŽฒ Choice Block
    • ๐Ÿ” Search Block
    • ๐Ÿ”— API Call Block
    • ๐Ÿ“„ Word Export Block
    • ๐Ÿ“Š PPT Block
    • ๐Ÿ‘๏ธ Filtered Views
  • Attributes
    • ๐Ÿท๏ธ Attributes
    • โš™๏ธ Attribute Editor
  • Best practices
    • ๐Ÿ“ Writing Effective Prompts
  • Admin
    • ๐Ÿ’ณ Thinkeo Credits
    • ๐Ÿ‘ฅ Team Management
    • โš™๏ธ Settings
  • Release notes
    • ๐Ÿš€ Thinkeo v1.2 Release Notes
    • ๐Ÿš€ Thinkeo v1.0 Release Notes
    • ๐Ÿš€ Thinkeo v0.10 Release Notes
    • ๐Ÿš€ Thinkeo v0.8 Release Notes
    • ๐Ÿš€ Thinkeo v0.7 Release Notes
    • ๐Ÿš€ Thinkeo v0.6 Release Notes
  1. Best practices

๐Ÿ“ Writing Effective Prompts

To create AI Applications that consistently produce quality content, you will need to write effective prompts.
AI is a tool, not black magic. It must be guided through precise instructions and fed with relevant information to write satisfactory responses.

๐ŸŽฏ Key Elements#

There are a multitude of prompting techniques with advantages and disadvantages, which will be more or less adapted to your needs.
We can nevertheless identify common points across different methods:
๐ŸŽญ Role and Context
The importance of role and context: The more you give AI a reference framework, the better it will be able to understand what is expected of it, the positioning it must adopt, and the interpretation it will have of your directives.
๐ŸŽฏ Precision of Terms
Precision of terms used: Be factual, precise, avoid words that can be subject to interpretation. For example, for AI to write a "good" text means nothing without criteria to determine what you consider "good", asking for "many" words is also not quantifiable.
๐Ÿ“š Use of References
Use of references: Give it material it can rely on, examples of expected content by explaining what the provided excerpt represents.
๐Ÿ—‚๏ธ Use of Structure
Use of structure: See the section below on this page, AI is much more relevant when we explicitly distinguish each element it must take into account and an order is established for the logic to follow. You can even go so far as to explicitly indicate the different thinking steps it must follow before writing its content.
1
โš ๏ธ Optimal Prompt Length
A prompt that is too short will lack information to be properly interpreted by AI, and a prompt that is too long risks confusing it with too much information to understand. To avoid lengthy prompts, break them down into subtasks.
2
๐ŸŽฏ Single-Purpose Design
Take advantage of Thinkeo and AI blocks. AI is most effective when we break down what it needs to do into several subtasks, so consider that a Prompt is intended for a single objective.
3
๐Ÿ”— Thinkeo Block Chaining
Take advantage of Thinkeo's features to create cascading reasoning. Use interconnected AI blocks to break down complex tasks into simpler subtasks. Share blocks to reuse the same references, contexts, or prompt sections from one prompt to another. Nest AI blocks within others to leverage content generated by your other AI blocks, thus unifying the result of your subtasks to accomplish a larger one.

โœจ Additional Best Practices#

๐ŸŽฏ Testing & Examples#

1.
Use concrete examples: Provide specific examples of the type of response you expect. This helps AI better understand your expectations and calibrate its response accordingly.
2.
Test your prompts: Before finalizing a prompt for an application, test it with different input variations to ensure it produces consistent and quality results in various situations.
3.
Iterate and refine: After testing your prompt, don't hesitate to adjust it. Sometimes, small changes in wording can have a significant impact on response quality.

๐Ÿง  Advanced Techniques#

4.
Use the "AI as expert" technique: Ask AI to adopt the viewpoint of a specific expert in the relevant field. For example, "As a digital marketing expert with 20 years of experience, how would you approach...". This approach can help obtain more nuanced and professional responses.
5.
Incorporate creative constraints: Sometimes, adding unusual constraints can stimulate more original and insightful responses. For example, "Explain this concept as if you were talking to a 10-year-old" or "Describe this strategy using only culinary metaphors". These constraints can lead to clearer explanations or unique perspectives.
Thinkeo Pro Tip
๐Ÿ’ก Use shared blocks in Thinkeo to avoid repeating the same information in your prompts. A Choice Block for Tone can be nested in all your AI blocks, conditional blocks with certain other instructions as well, use blocks for content given as "provided information", etc.
Consult the AI Block page to see an illustration.

๐Ÿ—๏ธ AI Block Architecture in Thinkeo#

Understanding how AI blocks work in Thinkeo is essential for creating effective prompts. In Thinkeo, all nested blocks within an AI block constitute the complete prompt that will be sent to the AI.

๐Ÿ”ง How Prompt Assembly Works#

1
๐Ÿ“ Block Concatenation
When an AI block executes, Thinkeo automatically assembles all its nested blocks from top to bottom to create the final prompt. Each nested block adds its content to the complete prompt.
2
๐Ÿ“ Automatic Content Injection
File blocks automatically extract and inject document content into the prompt - no special syntax needed. The AI receives the extracted text as part of the assembled prompt.
3
๐Ÿ”„ Child Block Execution
All nested blocks (File, Search, Paragraph, etc.) execute first and generate their content before the parent AI block receives the complete assembled prompt.

๐ŸŽฏ Practical Example#

AI Block: "Document Analysis"
โ”œโ”€โ”€ ๐Ÿ“ Paragraph Block: "You are a financial expert. Analyze the document below:"
โ”œโ”€โ”€ ๐Ÿ“ File Block: [Automatically extracts: "Q3 Revenue Report... $2.3M increase..."]
โ””โ”€โ”€ ๐Ÿ“ Paragraph Block: "Provide 3 key insights in numbered format."
The AI receives this complete prompt:
You are a financial expert. Analyze the document below:

Q3 Revenue Report... $2.3M increase... [full extracted content]

Provide 3 key insights in numbered format.

๐Ÿ”— Nested AI Block Workflows#

You can create sophisticated workflows by nesting AI blocks within other AI blocks:
1
๐Ÿ” Child AI Generates Content
The nested AI block executes first, generates its response, and this response becomes visible content for the parent AI block.
2
๐Ÿ“Š Parent AI Uses Child Results
The parent AI block can then use, synthesize, or build upon the content generated by its child AI blocks.
Example Workflow:
Parent AI Block: "Executive Summary"
โ”œโ”€โ”€ ๐Ÿ“ Instructions: "Create an executive summary based on the analysis below:"
โ”œโ”€โ”€ ๐Ÿค– Child AI Block: "Financial Analysis" 
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ Instructions: "Analyze financial data and identify 3 key trends"
โ”‚   โ””โ”€โ”€ ๐Ÿ“ File Block: [Financial reports]
โ””โ”€โ”€ ๐Ÿ“ Final Instructions: "Format as 200-word executive summary"

๐Ÿ”ง Variables and Dynamic Content#

๐Ÿ“ Text Variables in Thinkeo#

Only text attributes can be used as variables within paragraph blocks using the @@ syntax.
1
๐ŸŽฏ Variable Insertion
Type @@ to open a search window and select your desired text attribute. Once inserted, the attribute appears as a colored button-like element in your block showing the attribute name.
2
๐Ÿ“ Visual Representation
In your blocks, variables appear as: [industry_sector] (colored button-style elements), not as @@industry_sector@@. The @@ syntax is only used during insertion.
3
โœ… Runtime Replacement
During block execution, these colored attribute buttons are replaced with their actual values assigned during the user's publication journey.

๐Ÿ“ File Attributes Usage#

File attributes cannot be used directly with @@ syntax. Instead:
File attributes are assigned to File Blocks or Search Blocks in their parameters
These blocks automatically extract and process file content
The processed content becomes part of the prompt assembly

๐Ÿ’ก Best Practices for Variables#

๐Ÿ“‹ Descriptive Naming
Use clear, descriptive names for your attributes: [client_company], [project_deadline], [industry_sector] (displayed as colored buttons)
๐Ÿ”„ Fallback Instructions
Include instructions for empty variables: "If company name is not provided, use 'the organization'"
๐ŸŽฏ Strategic Placement
Place variables strategically in your prompt structure for maximum impact and clarity
๐Ÿงช Test Different Values
Use the Studio's Attributes tab to test your prompts with different variable values

๐Ÿ—๏ธ Structure#

An effective prompt needs structure to organize information, provide context, and guide AI understanding for each instruction. It's not necessary to always have the same one; however, having a basic foundation that you use recurrently will help you build your prompts and adapt them to each need.

๐Ÿ“‹ Recommended Basic Structure#

We recommend a basic structure that has proven itself on Thinkeo Apps and that we adapt to uses. You can use it, be inspired by it, or start with something completely different - this is a proposal to help you get started.
1
๐ŸŽญ Role
Role: AI's role, we essentially indicate the Position it occupies and in what context or company. This role is generally common across the entire App.
Example: "You are a B2B marketing expert specializing in the [industry_sector] industry with 15 years of experience." (where [industry_sector] appears as a colored button)
2
๐ŸŽฏ Objective
Objective: Detailed instruction that will specify to AI what we expect from it. Here we will specify the context if needed, indicate how to interpret the content we provide, explain what it must produce and the objective of what will be written.
Example: "Analyze the provided document to create a competitive analysis of 300 words that identifies 3 key differentiating advantages and 2 potential market opportunities."
3
๐Ÿ“„ Provided Information
Provided information: The context we will give to AI and the references it can rely on. This can be words, sentences, or paragraphs. This is where we can share content to feed several prompts in parallel, or feed an AI block with content generated by another, notably.
Example: "Variables used: Company: [client_company], Competitor: [main_competitor]. Document to analyze:" (variables appear as colored buttons)
4
๐ŸŽจ Tone
Tone: Structured in three distinct points: Language level / Editorial style / Tone
Example: "Professional and analytical tone. Use business terminology. Be precise and factual."
5
๐Ÿ“ Length
Length: The number of words or sentences not to exceed and the expected structure, like X sentences or X paragraphs.
Example: "300 words maximum, structured in 3 numbered sections with bold headings."
6
๐Ÿ—ฃ๏ธ Language
Language: Here we specify specific rules like mandatory formal address, inclusive writing, particular words to avoid or reformulate.
Example: "Use formal address throughout. Avoid jargon. Replace technical terms with accessible explanations."
7
๐Ÿšซ Prohibitions
Prohibitions: AI handles prohibitions poorly, it's much more effective to give precise instructions on all other points; here it's about adding a complementary directive on specific elements.
Example: "Do not make recommendations about pricing or budget allocation."
๐Ÿ’ก Bonus tip: The instruction "Let's think step by step." can help when placed between "Role" and "Objective", AI then takes each instruction as a step, which often allows obtaining more qualitative results.

๐Ÿ”„ Alternative Structures#

Here are other proven structures you can use or adapt according to your needs:

๐Ÿ“ Classic Alternative Structure#

1.
Role
2.
Context
3.
Objective (mandatory)
4.
Rules
5.
Language (tone is part of language)
6.
Length
7.
Prohibitions
8.
Provided information

๐ŸŽฏ STAR Method Structure#

Particularly effective for analysis tasks:
1.
Situation - Context and background
2.
Task - What needs to be accomplished
3.
Action - How to approach the task
4.
Result - Expected output format

๐Ÿ“Š CRISP Structure#

For structured analytical work:
1.
Context - Business/domain context
2.
Requirements - Specific needs and constraints
3.
Input - Data and information provided
4.
Scope - Boundaries and limitations
5.
Process - Step-by-step methodology

๐Ÿ”ง Complex Task Structure#

For detailed analysis requiring high precision:
1.
Role
2.
Context
3.
Document structure
4.
Instructions
5.
Objective
6.
Content to include
7.
Tone
8.
Length
9.
Structure
10.
Specific rules
11.
Provided information

๐Ÿš€ Rapid Response Structure#

For simple, fast tasks:
1.
Role - Brief expert definition
2.
Task - One clear objective
3.
Format - Output specification
4.
Data - Input information

๐Ÿ”„ Iterative Refinement Structure#

For multi-step improvement tasks:
1.
Initial Role - Starting position
2.
Analysis Phase - First assessment
3.
Refinement Criteria - Improvement guidelines
4.
Final Output - Polished result format

๐ŸŽฏ Practical Use Cases and Examples#

๐Ÿ“Š Marketing Content Creation#

Scenario: Creating personalized marketing content based on client industry
AI Block Structure:
โ”œโ”€โ”€ ๐Ÿ“ "You are a marketing expert specializing in [client_industry]"
โ”œโ”€โ”€ ๐Ÿ“ "Create a compelling value proposition for [client_company]"
โ”œโ”€โ”€ ๐Ÿ“ File Block (client brief document)
โ””โ”€โ”€ ๐Ÿ“ "Format as 3 bullet points with impact metrics"
(Variables appear as colored buttons: [client_industry], [client_company])

๐Ÿ“‹ Document Analysis Workflow#

Scenario: Multi-stage document analysis with specialized AI agents
Parent AI Block: "Executive Summary"
โ”œโ”€โ”€ ๐Ÿ“ "Synthesize the following analyses into an executive summary:"
โ”œโ”€โ”€ ๐Ÿค– Child AI: "Financial Analysis"
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ "Analyze financial data and identify trends"
โ”‚   โ””โ”€โ”€ ๐Ÿ“ Financial reports
โ”œโ”€โ”€ ๐Ÿค– Child AI: "Risk Assessment" 
โ”‚   โ”œโ”€โ”€ ๐Ÿ“ "Identify potential risks and mitigation strategies"
โ”‚   โ””โ”€โ”€ ๐Ÿ“ Same financial reports
โ””โ”€โ”€ ๐Ÿ“ "Present findings in 250 words with clear recommendations"

โœ… Prompt Quality Checklist#

Before finalizing any prompt, verify:
๐ŸŽฏ Clear Objective
Role is specific and relevant
Task is clearly defined
Expected output format is specified
๐Ÿ“ Complete Information
All necessary variables are included
File blocks are properly configured
Context is sufficient for the task
๐Ÿ”ง Technical Setup
Variables use correct @@ syntax
Block hierarchy is logical
Execution order makes sense
๐Ÿงช Testing Ready
Test values assigned in Attributes tab
Individual blocks execute correctly
Complete workflow produces expected results

๐Ÿงช Testing and Debugging Your Prompts#

๐Ÿ”ฌ Using Studio's Debug Features#

1
๐Ÿท๏ธ Attributes Tab Testing
Navigate to the Attributes tab in Studio to assign test values to your text attributes. This allows you to simulate different scenarios without creating actual publications.
2
โ–ถ๏ธ Individual Block Testing
Use the "play" button next to block parameters to execute individual blocks and verify their output before testing the complete workflow.
3
๐Ÿ‘๏ธ Output Visualization
Toggle "show output" to see execution results directly in Studio, helping you identify issues and verify expected behavior.
4
๐Ÿ”„ Iterative Refinement
Test one modification at a time, compare results, and refine systematically rather than making multiple changes simultaneously.

๐Ÿšจ Common Issues and Solutions#

๐Ÿ”ด Variables Not Replacing
Symptoms: Variable buttons still show attribute names instead of values
Solution: Verify attribute exists, check spelling, ensure it's assigned in wizard step
๐Ÿ”ด Inconsistent Responses
Symptoms: AI generates different styles/formats
Solution: Add more specific formatting instructions, include examples, adjust temperature parameter
๐Ÿ”ด Missing File Content
Symptoms: AI doesn't reference document content
Solution: Check file block configuration, verify file attribute assignment, test with different file formats
๐Ÿ”ด Prompt Too Long
Symptoms: Truncated responses, high costs
Solution: Break into smaller AI blocks, use child/parent structure, choose model with larger context

๐Ÿ“Š Diagnostic Questions#

When a prompt isn't working effectively, ask yourself:
1.
๐ŸŽฏ Is the role specific enough? Generic roles produce generic results
2.
๐Ÿ“‹ Are instructions actionable? Avoid vague terms like "good" or "professional"
3.
๐Ÿ”— Is the block hierarchy logical? Check execution order and dependencies
4.
๐Ÿ“ Are length constraints realistic? Match expectations with model capabilities
5.
๐Ÿงช Have I tested edge cases? Try with different variable values and file types

๐Ÿค– Choosing the Right Model for Your Prompt#

๐ŸŽฏ Model Selection Strategy#

The complexity and requirements of your prompt should guide your model choice:
1
๐Ÿ“ Simple Content Generation
Use Case: Basic content creation, simple analysis, straightforward formatting
Recommended Models: GPT-4.1 Mini, Claude 3.5 Haiku, Mistral Small
Why: Cost-effective for simple tasks, fast execution, sufficient quality
2
๐Ÿง  Complex Analysis & Reasoning
Use Case: Multi-step analysis, complex reasoning, sophisticated synthesis
Recommended Models: GPT-4.1, Claude Sonnet 4, o3 Mini (with reasoning)
Why: Better reasoning capabilities, handle complex instructions, maintain consistency
3
๐Ÿ“Š Large Document Processing
Use Case: Processing very large documents, extensive context analysis
Recommended Models: Gemini 2.5 Pro (2M tokens), GPT-4.1 (1M tokens)
Why: Massive context windows, efficient large document handling
4
๐Ÿ” Research & Web Integration
Use Case: Tasks requiring current information, fact-checking, web research
Recommended Models: Perplexity Sonar Pro, Perplexity Deep Research
Why: Integrated web search capabilities, up-to-date information access

๐Ÿ’ฐ Cost Optimization Guidelines#

๐Ÿ’ก Efficiency Strategies
Start with smaller models for testing and refinement
Use GPT-4.1 for best quality/price ratio on complex tasks
Reserve premium models (Gemini 2.5 Pro) for truly large documents
Consider open-source options for less critical applications
๐Ÿ“ˆ Performance Indicators
If responses are inconsistent โ†’ Try more powerful model
If costs are too high โ†’ Test with smaller model or break into subtasks
If processing is too slow โ†’ Consider faster alternatives
If context is truncated โ†’ Upgrade to larger context model

๐Ÿ”„ A/B Testing Models#

To find the optimal model for your use case:
1.
๐Ÿ“‹ Define Success Metrics: Quality, consistency, speed, cost
2.
๐Ÿงช Test with Representative Data: Use typical inputs and scenarios
3.
๐Ÿ“Š Compare Results: Document differences in output quality and characteristics
4.
๐Ÿ’ฐ Calculate ROI: Balance quality improvements against cost increases
5.
๐ŸŽฏ Make Informed Decision: Choose based on your specific requirements and budget

๐ŸŒก๏ธ Mastering Temperature for Better Results#

Temperature is one of the most powerful and underutilized parameters in prompting. Understanding its impact can dramatically improve your results.

๐ŸŽ›๏ธ Understanding Temperature#

Temperature controls the "creativity" vs "predictability" balance of AI responses:
โ„๏ธ Low Temperature (0.3-0.5)
Consistent & Professional
Reliable for business content and analysis
Natural language without being robotic
Good balance of consistency and readability
Recommended baseline for most Thinkeo Apps
๐Ÿ”ฅ Higher Temperature (0.6-0.9)
Creative & Varied
More diverse and creative outputs
Better for brainstorming, marketing copy, storytelling
Each generation will be more unique
Use when you specifically need originality

๐ŸŽฏ Practical Temperature Guidelines#

1
๐Ÿ“Š For Analysis & Data (Temperature: 0.3-0.4)
When processing documents, extracting information, or creating structured analyses. You want consistency and accuracy while maintaining some natural variation.
Example: "Extract 5 key financial metrics from this quarterly report"
2
โœ๏ธ For Content Creation (Temperature: 0.4-0.6)
For writing marketing content, proposals, or explanations where you want balanced creativity with maintained coherence. This is the sweet spot for most business content.
Example: "Write a compelling value proposition for [product_name]"
3
๐Ÿ’ก For Brainstorming (Temperature: 0.6-0.8)
When you want innovative ideas, creative solutions, or diverse perspectives on a problem while maintaining practicality.
Example: "Generate 10 innovative marketing campaign ideas for [industry_sector]"
4
๐ŸŽจ For Creative Writing (Temperature: 0.7-1.0)
For storytelling, creative descriptions, or when you want maximum originality and unique perspectives.
Example: "Write a creative product description that stands out from competitors"

โš™๏ธ Temperature Best Practices#

๐Ÿ”ง Pro Tips:
Start with 0.3-0.4 and adjust: Begin with a moderate temperature and increase for more creativity
Test systematically: Try the same prompt with different temperatures to see the impact
Match temperature to task: Analysis = 0.3-0.4, business content = 0.4-0.6, creativity = 0.6+
Use App-level settings: Set a baseline temperature for your entire App, then adjust individual blocks as needed

๐Ÿงช Temperature Testing Example#

Try this same prompt with different temperatures to see the difference:
Prompt: "Describe the benefits of remote work for companies"
Temperature 0.3: "Remote work reduces office costs, increases talent pool access, and improves employee satisfaction through flexible scheduling..."
Temperature 0.7: "Picture this: your company becomes a borderless ecosystem where talent flourishes from kitchen tables to mountain cabins, cutting costs while boosting creativity..."
The same prompt, completely different tone and approach!

๐Ÿš€ Going Further#

The Prompt Engineering guide proposed by OpenAI is a good foundation for discovering different approaches and best practices to implement in Prompts addressed to OpenAI models.
๐Ÿ“š External Resource: OpenAI Platform
Keep in mind that iterating and adjusting your prompts based on your usage remains the best practice for understanding and seeing what works best for your needs. The recommendations you'll find for OpenAI models also apply to other AIs (like Mistral for example), so once you've found your bearings and designed a standard structure that brings you satisfaction, reuse it.

Modified atย 2025-08-19 16:01:11
Previous
โš™๏ธ Attribute Editor
Next
๐Ÿ’ณ Thinkeo Credits
Built with