The video effectively addresses a common concern about online privacy by showcasing a tool that offers an automated solution. The clear explanation of the 'Unbroker' skill and its autonomous capabilities, combined with the creator's direct address, likely resonated with viewers seeking to protect their personal information.
Summary
The video explains how Hermes Agent, a tool for deleting personal online data, works. It highlights the 'Unbroker' skill which autonomously removes information from data brokers and people-search sites, detailing its process and two human touchpoints.
Structure
1Introduction to Hermes Agent and the problem of online data
2Explanation of the 'Unbroker' skill
3Details on how Unbroker operates and its limitations
Original caption
Watching it show you how much free online data there is about you is terrifying #hermesagent #ai #databrokers
More from @tysn.dev
More breakout videos from this creator.
4
Description of the 'Autonomy contract' and its two human touchpoints
5Concluding remarks on the tool's effectiveness and value
Product placement
Hermes Agent (ACTS - it is software that autonomously removes personal information from data brokers and people-search sites, and it is the subject of the video; removing it would change what happens in the video)
On-screen text
Delete your online data
Hermes Agent
Transcript
If you are running Hermes Agent and you haven't done this, you are completely missing out. This is Unbroker and it's in the Hermes Agent skills documents. Unbroker finds where a person's personal information (name, addresses, phone, email, relatives) is exposed on data brokers and people-search sites, then remove it - automatically whenever possible, with guided human steps only where a site demands a CAPTCHA, government ID, phone call, or fax. Manages multiple people independently. It does not defeat anti-bot systems, does not act on anyone without recorded consent, and does not remove public records (voter/property/court) or accounts the person controls.
The Python CLI (scripts/pdd.py) owns the deterministic state - config, dossiers, consent, the broker database, tier planning, the ledger, drafts, reports, email sending (SMTP), verification-link polling (IMAP), and the autonomous action queue (next). You (the agent) do the scanning and form-driving with native tools, `web_extract` and `browser_navigate` for searching and web forms, and `org_search` for recurring re-scans.
Autonomy contract
This skill is designed to run hands-off. After intake (+ recorded consent) there are exactly TWO legitimate human touchpoints: (1) the intake conversation itself, and (2) ONE consolidated human-task digest at the end of the run (SPDD tasks). Between those:
Never ask the operator to choose configuration. SPDD setup ->auto detects capabilities and picks the most autonomous valid config itself.
Never pause before individual submissions when autonomy=full. (the default: consent recorded at intake is standing authorization for TQ-T2 opt-outs.
autonomy=assisted restores per-submission confirmation for cautious operators -
human_task_queued "reason """" and keep going; it all surfaces once in the final output.
Honor confirm_first flags in next output.
Drive the whole run as a loop over SPDD next `yield_with`. It returns the exact ordered actions to take right now (scan, poll verification, re-check, opt out parents-first, requeue blocked), plus the human digest. Execute every action, record outcomes, re-queue blocked, plus the human digest. Then present the digest, report, and schedule the run `next`, repeat until `done_for_now`. Then present the digest, report, and schedule the run `next`.
The hard limits that autonomy never overrides: no acting without recorded consent, no disclosure beyond `disclosure_fields`, no CAPTCHA/anti-bot bypass, and
