Skip to the card

Card 734 of 9992026-09-09 issue

Observed arrival · 2026-09-09

RigorRun Checks Whether Agents Actually Did the Job

rigorrun.xyz Observed source
Editorial interest 84/100 Selection signal · not a rating of the site

A local developer tool turns one demonstrated workflow into executable acceptance tests for AI agents.

Landing page captured for the 2026-09-09 issue.

Field notes

RigorRun records a human-performed workflow, compiles it into an executable contract, generates additional cases, and checks the resulting system state rather than trusting an agent transcript. The homepage’s example reports 7 sanitised steps, 22 cases across 9 categories, and 173 checks. Its separate evidence record covers four MCP servers and 37 tools, with 19 exercised and 18 listed as unreachable; the site explicitly identifies the sample as synthetic.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use

One card from the complete issue

The Red Help Tab

366,017 arrived 1,000 judged 999 catalogued Enter the complete issue
rigorrun.xyz

Landing page observed 2026-09-09. The live site may have changed.