Progressive disclosure
Progressive disclosure is a technique that presents information, capabilities, or details incrementally as they become relevant or needed.
Vibe Engineering
Progressive disclosure is a technique that reveals information in successive levels only when it becomes relevant or requested.
- How it is used
- Keeps agent capabilities discoverable while limiting context to instructions and resources relevant to the current request.
- How deep it goes
- Defines three loading levels, gives typical token costs, and explains description-driven discovery and deferred files.
- Examples
- Uses a pull-request review skill with staged instructions, a checklist, migration checks, and a review template.
- What you can do after
- Configure agent skills so brief descriptions support discovery and detailed procedures load only when needed.
Designing AI Agents
Progressive disclosure is a technique that reveals detailed information or capabilities only when they become relevant to the current task.
- How it is used
- Uses progressive disclosure to reduce context pressure and selection noise in agent capability catalogs.
- How deep it goes
- Explains staged loading from descriptions through full contracts to references, while distinguishing disclosure from execution authority.
- Examples
- Illustrates disclosure with Agent Skills and deferred Claude API tool definitions.
- What you can do after
- Evaluate progressive disclosure by measuring listing costs and separating capability loading from permission to execute.
Read how Designing AI Agents explains progressive disclosure →
Also covered in
- Context EngineeringIn early access (MEAP)
- Deep Learning with R, Third Edition
- Deep Learning with Python, Third Edition
- Build an AI Agent (From Scratch)
- Authorization in Action
What to know first
- MarkdownMarkdown is a lightweight markup language that uses readable plain-text syntax to represent structured and formatted documents.
- costCost is the monetary expenditure or other resource burden incurred to acquire, produce, operate, or perform something.
- context windowA context window is a bounded span of sequence elements or contextual information that a model or processing operation can consider together.
- Keras modelA Keras model is a trainable object representing a neural-network computation and providing interfaces for training, evaluation, prediction, and saving.
Related concepts
- agent skillused by · An agent skill is a reusable package of instructions, capabilities, or resources that guides an AI agent in carrying out a task or workflow.
- context windowuses · A context window is a bounded span of sequence elements or contextual information that a model or processing operation can consider together.
- Kerasused by · Keras is an open-source, high-level deep-learning API for building, training, and evaluating neural-network models.
- pluginimplemented by · A plugin is a software component that extends a host application's capabilities through an extension or integration mechanism.
Questions about progressive disclosure
What is progressive disclosure?
Progressive disclosure is a technique that presents information, capabilities, or details incrementally as they become relevant or needed.
Which Manning books explain progressive disclosure?
Vibe Engineering and Designing AI Agents.
What should I know before learning progressive disclosure?
Manning books that teach progressive disclosure usually introduce Markdown, cost, context window and Keras model first.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

