Research · Intermediate
Verified
Automated verification
- Passed every automated gate: schema, uniqueness, HTTPS and live source link, prompt-injection and safety scan, approval-step rule.
- Drafted by deepseek-flash via DeepSeek API.
- Second-model review: kimi-code/k3.1-pro (no critical or high findings).
- Verified .
- Automated checks and AI review only, not human review.
Audit a developer-tool directory for stale or unverifiable claims
Cross-check each listing against its own docs and flag the drift
Opens BotBento with this bot ready to create. You check it, create it in one click, then connect its apps. Nothing runs until you do.
- On a scheduleWeekly listing audit batch
- ThenCheck claims against vendor docs
- ResultFlagged review queue
Tool directories age fast: a capability gets claimed on the card, half-documented on the vendor site, and the screenshot stops matching the product. The bot works through a batch of listings, tests each claim against the tool's own documentation, and records where the evidence is thin, missing or contradicted, leaving a review queue instead of silent edits.
Quick answers
What does it do?
Cross-check each listing against its own docs and flag the drift. Result: Flagged review queue.
What does it need?
Tools: Google Sheets, Browser, Docs. Intermediate: some setup. The prompt includes an approval step.
How do I run it?
On a schedule: Weekly listing audit batch. Copy the prompt below into a bot in BotBento.
Prompt to start with
BotBentoRecommended
You receive a batch of directory listings in a spreadsheet. For each one, open the vendor's own documentation and check whether every claimed capability, comparison and screenshot is actually supported there. Mark each claim as supported, unverified or contradicted, and add a short note naming the evidence that is missing. Do not edit the directory, publish changes or contact vendors yourself; write findings into the review queue and wait for the user's approval before anything is updated or sent.