Watch a Run From the Terminal
Everything in the other recipes works from the CLI too. This one is the whole observability loop with no code at all: one pane runs the automation, one streams what it’s doing, and a browser tab shows it happening.
1. Launch
2. Stream the timeline (second pane)
Every navigation, click, typed burst, and captcha solve prints as it happens. Filter the firehose when you only care about problems:
3. Kick off work (first pane)
Connect your own tooling to the connectUrl, or run a hosted agent straight from the shell:
4. Watch it with your eyes
Open the printed URL in any browser - it’s a tokenized, expiring viewer link, safe to paste to a teammate in Slack. Mint it with --control input if they should be able to grab the mouse.
🎬 Content TODO: a terminal recording (asciinema or GIF) of the three panes - invocation running left, activity streaming right, live view open in a browser window - is worth more than any of the prose here.
5. Replay it later
Same idea after the fact: an expiring replay URL you can open or embed.
Next
- CLI output & scripting -
--json,--jq, and templates - Embed a Live Browser View - the same loop, in your product
- Agents and CI - drive all of this from automation

