Observed arrival · 2026-11-17
A tamper-evident trail for AI agents
VerifiedTrail describes an audit-log service that turns AI-agent activity into evidence packages with independently checkable integrity proofs.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- AI-agent operators and security assessors
- Worth noticing
- The log excludes prompts, responses, file contents, and tool arguments; arguments are hashed and discarded.
Field notes
The service says it records event type, time, tool, model, token counts, actor, and outcome, while excluding prompts, responses, file contents, and tool arguments. Its sample walkthrough shows a public-log check; a separate API-key check is described for recomputing the chain and validating the timestamp.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
⊠LoginAccess appeared gated
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
ƒJavaScriptBrowser-side code central
One card from the complete issue