AI Fluency Series #2: Description

How to Communicate Tasks Effectively to LLMs

AI Fluency Series #2: Description – How to Communicate Tasks Effectively to LLMs

In our previous post , we explored delegation —understanding the problem, selecting the right LLM, and deciding which tasks are human-led versus AI-led. Now, we shift focus to description : how to effectively communicate the tasks you've delegated to an LLM, ensuring clarity, precision, and actionable results.

Consider a scenario: a colleague asks, “Can you help me generate report using AI?” At first glance, it seems simple. But without a clear description, the AI might produce irrelevant or low-quality outputs.

To avoid this, we break description into three distinct layers:

1️⃣ Product Description: Defining the Desired Output

Purpose: Clearly articulate what you want the AI to produce.

Key Elements: Format, audience, style & tone, content details.

Example: "I am a technical lead that want to generate a market analysis of observability and monitoring tools for software development services to present to a technical audience. It should include a comparison table of features."

2️⃣ Process Description: Guiding the AI's Approach

Purpose: Instruct the AI on how to tackle the task.

Key Elements: Methodology, reasoning style, interaction style.

Example: "Build the report around the Weighted Scoring Model framework, evaluating tools based on criteria like ease of use, integration capabilities, scalability, and cost-effectiveness. Start with an executive summary, followed by detailed sections for each tool, and conclude with a recommendation."

3️⃣ Performance Description: Defining AI Behavior

Purpose: Set expectations for how the AI should behave while performing the task.

Key Elements: Level of detail, perspective, engagement style.

Example: "Provide a detailed, supportive explanation with a focus on inclusivity and clarity. when I ask questions be challenging against my assumptions to help me think more deeply about the topic."

🔄 Integrating the Descriptions

To delegate effectively, ensure all three layers are addressed:

  • Product Description: What exactly do you want?
  • Process Description: How should the AI approach it?
  • Performance Description: How should the AI behave?

🚀 Actionable Takeaways

  • Define the Problem Clearly – Understand scope, constraints, and objectives before delegating.
  • Choose the Right Tool – Match the task to the LLM’s strengths.
  • Break Down Tasks – Decompose large problems and assign roles between human and AI.
  • Craft Product Descriptions – Specify output format, audience, style, and content.
  • Guide the Process – Provide stepwise instructions, methodology, or reasoning style.
  • Set Performance Expectations – Define tone, level of detail, and perspective.
  • Iterate and Refine – Treat AI as a collaborator: review, adjust, and improve.
  • Adopt a Human-Led Mindset – AI is a tool; your insight and judgment drive success.

Mastering description is the next step after delegation. By layering product, process, and performance instructions, and following the actionable takeaways, you can collaborate with AI more deliberately, reduce errors, and produce outputs that truly meet your goals.

Sources and further reading: A Note on Ethics and AI Use: Transparency is important. For this article, I used AI tools to augment my discussion and explore phrasing, as well as to assess SEO performance and readability. While AI helped refine ideas and highlight optimization opportunities, all insights, examples, and analysis are the product of my own experience and judgment. AI served as a support tool, not a replacement for critical thinking or human perspective.

Posted by Mikhael Santos on September 17, 2025