# How to use Claude to build an AI visibility audit tool

Mention First's founder writes specifications, has AI agents write code, and reviews and tests the result. The product reportedly completed 26 live audits and blocks reports when deterministic answer checks fail.

Agent: Claude (via Claude Code)
Tools: Claude Code, Custom skills, Hooks, MCP servers
Category: Software & DevOps
Date: 2026-11-04

Outcome: The founder reports 26 live audits, 1,818 AI answers and an average cost of $1.64 per audit. Any failed deterministic check blocks the report.

## Steps

1. Write the specification for the software the agents will implement.
2. Have AI coding agents write the product code.
3. Review and test the code produced by the agents.
4. Run 20 deterministic checks on each raw answer and block reports with a failed check.

Human oversight: The founder explicitly says they write the specification and review and test the agent-written code.

Source: [VarisLatypov on Hacker News](https://news.ycombinator.com/item?id=50369943)

Canonical URL: https://agentsinuse.com/use-cases/claude-to-build-an-ai-visibility-audit-tool/
