Elicitation
Getting information from users or other systems to guide AI behavior or provide context.
Elicitation is about asking for or getting information. In AI, this often means getting details from a person using the AI or from another computer system.
For example, when you use a chatbot and it asks you questions to understand what you need, that's elicitation. It helps the AI figure out the best way to respond or what task to perform.
Elicitation refers to the process of extracting specific information, requirements, or data from a source, typically a user or another system, to inform or guide an AI's actions or responses. This can involve direct questioning, analyzing user input, or querying external knowledge bases.
Effective elicitation is crucial for tasks like prompt engineering, where precise instructions are needed, and for building agents that require context to operate. The quality of elicited information directly impacts the AI's performance and the relevance of its output.
Elicitation is key for AI agents to understand user needs and context. As frontier AI labs develop more sophisticated agents, the ability to effectively elicit information becomes crucial for their performance and utility. This is especially true for tools like Microsoft Copilot, which aim to integrate AI assistance directly into developer workflows.
- Building MCP servers with VS Code — Level up your MCPMicrosoft · Microsoft Developer on YouTube ·
- Microsoft Copilot
- Microsoft Copilot uses elicitation to understand user intent and context within development environments like VS Code, enabling it to provide relevant assistance and suggestions.
- Data Collection
- Data collection is a broader process of gathering any data, whi
- Inference
- Inference is the AI's process of drawing conclusions from data, where
- Querying
- Querying is a method of asking for specific data from a database or sy
The term 'elicitation' originates from psychology and linguistics, referring to the process of drawing out information or responses. In AI, it's adopted to describe the active process of obtaining necessary input.
Ask ChatGPT or Copilot to act as a travel agent. Then, when it asks you questions about your destination, budget, or dates, pay attention to how it's eliciting the information it needs to plan your trip.
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- PromptRole-play a student struggling with math for AI tutor simulationSimulate a student's math struggles and uncertainty for AI tutor evaluation. · 5 min
- TemplateReusable workflow templates for healthcare teamsTeams can create and share templates for common workflows like documentation or prior authorizations. · 15 min
- TemplateTemplate for building an AI tool tailored to your workA structured approach to defining and building a custom AI tool for specific business needs. · 15 min
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- HeuristicDouble coding agent task completion with docs linksProviding coding agents with a documentation link significantly increases their task completion rate. · 2 min
Questions people ask
- What is elicitation in AI?
- Elicitation is the process of getting specific information from users or other systems to help an AI understand what to do or how to respond.
- Why is elicitation important for AI?
- It's important because AI needs clear instructions and context to perform tasks accurately and provide relevant outputs.
First seen on Subvolts Sep 10, 2026. Updated Sep 17, 2026. Written by an AI model from the items above and reviewed against them weekly; report an error.