Watches

Set a job on a cadence. When a new episode or call produces evidence, the row is delivered. Quiet days return nulls.

$ baruly watch create --name gpu-signals --query "inference cost GPU" \
$   --entities fixtures/data/accounts.csv --since 365 --frequency daily --destination inbox
{"watch_id": "wat_890ab15dce1044b5", "name": "gpu-signals", "frequency": "daily", "destinations": [{"type": "inbox"}], …}
$ baruly watch run wat_890ab15dce1044b5
{"watch_id": "wat_890ab15dce1044b5", "status": "completed", "run_id": "run_0822fffb4741484b", "match_count": 3,
 "matches": [{"entity": {"domain": "acme.com"}, "signal": {"speaker": "Jordan Lee", "speaker_title": "VP Engineering",
   "claim": "Our inference cost is out of control. We are spending more on GPU hours than on the rest of cloud combined, …",
   "timestamp": "21:24", "evidence": {"evidence_id": "ev_788c3e361d6b4705", "source_url": "https://example.com/podcasts/acme-inference-cost", …}}}, …]}

Sample from the bundled fixture corpus

CLI and REST, not a console screen

Watches exist on the CLI, REST, MCP, and inside recipes that set a cadence. There is no watches screen in the console today.

Create a watch

Name the query, the entities, the frequency, and a destination: inbox, Slack, webhook, HubSpot, or Salesforce.

baruly watch create --name gpu-signals --query "inference cost GPU" --entities accounts.csv --frequency daily --destination inbox
baruly watch run <watch_id>

Spoken brew recipe