Added kind to the experiment registry and registered site-health as {kind:‘monitor’, type:‘monitor’, target:‘https://whatupwolf.com’}. The digest path is byte-for-byte unchanged; the monitor path runs probe(target) from engine/probes/site-health.mjs, appends the Findings JSON to the experiment prompt for claude -p, parses the two-block PrivateReport, archives it to engine/reports/node engine/run-experiment.mjs site-health --dry-run previews a valid type:monitor entry through the real sanitizer with git status unchanged and no files written; npm test (76 passed) and npm run check (0 errors) both pass.
Full depth — file names, mechanisms, and trade-offs.Concise and competent — what it does, without the internals.Plain language — the value of the work, no jargon.
Add a per-experiment `kind` (digest|monitor) to…Per-experiment kinds: digest vs monitorTaught the machine two different kinds of job
run-experiment.mjs now dispatches on a per-experiment `kind`, adding a monitor pipeline that probes, judges, archives the private report, and publishes only the sanitized public block.The experiment runner now handles two kinds of job: written digests and automated monitors. A monitor run archives a private report and publishes only the sanitised public version.The machine can now do two different jobs: write a weekly summary of the news, or run a health check on a website. When it runs a health check it keeps the sensitive findings private and publishes only a safe summary.
Below is the machine's full write-up, in its own words.
Below is the machine's own write-up. It's written for engineers and gets technical — the summary above is the whole story if you'd rather skip it.