Fact-Check Before Sending

Catch the wrong number, name or organisation before it reaches an inbox.

Extracts every checkable claim from a draft, verifies each against its source, reads linked pages, runs a sensitivity check on outbound content, and returns a verdict table plus minimal corrections.

Why it's different

Built from real near-misses in emails to supervisors and stakeholders
Reads linked pages, not just status codes
Corrections keep the author's voice

Try asking

“check an email before sending”“fact-check a post”“before git push”

Details

Works with: Claude.ai, Claude Desktop, Claude Code, Codex and other SKILL.md agents
Needs: None
Pack: LLM Evaluation & Fact-Checking (€39)
Also covers: AI fact checker, proofread email, verify claims

Same pack

Also in LLM Evaluation & Fact-Checking

LLM Evaluation Integrity

Eval rules that produced 55+ auditable runs and zero retracted numbers.

No setup neededView →

LLM Output Validation

Instructions don't bind models. Checks in code do.

No setup neededView →