User Research
Choose a research method from the decision it must inform; recruit relevant experience and preserve evidence through synthesis.
Design an AI feature with validated structured output, explicit failure states, and an evaluation set.
---
name: knoveya-ai-product
description: "Design an AI feature with validated structured output, explicit failure states, and an evaluation set. Use for matching product work."
---
# AI Product
## Scope
Apply this guidance when the requested task matches the description. Honor the user's chosen outcome, repository rules, and existing authorization.
## Workflow
Design an AI feature with validated structured output, explicit failure states, and an evaluation set.
Before acting, inspect the relevant artifact and ask only for information that materially changes the result. Use existing tools and conventions; do not install dependencies, publish, send messages, deploy, or mutate external data unless the user has authorized that operation.
## Acceptance check
Malformed output and provider timeout produce safe recoverable behavior.
## Example task
Validate generated categories before storing a classification.
## Report
State what changed, the evidence checked, and what remains unverified. Do not claim a successful operation or completed test without observing it.Copy the full block, including its frontmatter, into a new folder named knoveya-ai-product as SKILL.md. Review the instructions before enabling them. For Codex, a user skill normally lives in ~/.codex/skills/knoveya-ai-product/SKILL.md; check the current documentation for another agent's supported location. Do not overwrite an existing skill.
This is an independent Knoveya skill. No files are installed by this website.
Validate generated categories before storing a classification.
Malformed output and provider timeout produce safe recoverable behavior.
Test the skill on a small, authorized example. File validation alone does not prove that an agent will make good decisions.
The skill supplies instructions, not tool access or expertise guarantees. Inspect generated work and preserve the user's approval boundaries.