Use cases, by job

Outreach in regulated markets: approval, suppression and a person for the hard questions

Firms in finance, healthcare and utilities can use an AI agent for outreach if they keep a person in control of what is said. Sellinger offers approval mode, a suppression check before every send, opt out handling and needs attention rules. Two studies came from regulated fields: a medical goods carrier (8.2% of named heads replied) and a financial advisor network (44.8% replied). This is not legal advice.

Published by Sellinger AI. Numbers and settings checked on 19 October 2026 against the fact register. Report an error.

reply rate from named compliance, procurement and logistics heads (Green Shield Logistics, 546 contacted from 21 September 2026): 8.2%
replied: 4,392 of 9,808 financial professionals messaged (wealth advisor referral network): 44.8%
financial, wealth, insurance and fintech teams among 322 customer teams, snapshot 18 October 2026: 10 teams, 3 paying

The controls that matter in a regulated field

Approval. A campaign can run in approval mode, where every message waits for a person to approve it, or send automatically. A person can take over any conversation, and the agent stops on its own when it cannot answer, for example a price it has no answer for.
Suppression. Before every send on email, LinkedIn and WhatsApp, the platform checks the team's suppression list and refuses the send when the contact is on it or when the check cannot be completed.
Opt out. When a contact replies with an opt out such as STOP or unsubscribe, in English, Bulgarian or German among other forms, the contact goes on the team's suppression list, the agent stops and the lead is closed out. A weak or unclear phrase never writes the permanent record: the agent stops and a person decides.
Erasure. An erasure function takes an email address, phone number or LinkedIn address, anonymizes the matching leads in the workspace and adds the identifiers to the suppression list so the person cannot be imported and contacted again.
Where data sits. Database, sign in and file storage on Supabase (Amazon Web Services, Stockholm). Application servers and background workers on Google Cloud (Finland). Web hosting on Vercel.

For the rules Sellinger enforces on every send, read the outreach rules. For one market's law in summary, see the market pages.

Writing rules that fit a regulated firm

The rule editor lets you write what the agent must hand to a person. Typical rules for a regulated firm are: any question about performance, returns or advice; any request for a specific recommendation; any complaint; any mention of a regulator; and any request for documents. The product's own catalog has the same shape for other fields, for example investors asking for a deck or customers mentioning cancellation. These rules stop the agent and notify you. They do not make a message compliant.

Two studies from regulated fields

Green Shield Logistics is a licensed carrier of medical and expired goods in Bulgaria. Formal letters in Bulgarian went out in the founder's name to clinics, labs and pharma companies: 546 contacted, 8.2% of named heads replied, 3 companies reached a concrete next step and 11 replies forwarded the letter to the responsible colleague.

The wealth advisor referral network ran on 26 LinkedIn profiles and wrote to private bankers, wealth managers, independent advisors and golden visa advisors across the UK, Europe and the Gulf. 9,808 were messaged, 44.8% replied and 95 calls were booked.

Neither study tested compliance wording or measured regulator outcomes, and neither makes a claim about them.

Common questions

Is this compliant with my regulator?

Sellinger cannot say. It gives you approval, suppression and escalation controls. Whether a message meets your regulator's marketing rules is a question for your adviser.

Can I keep every message for audit?

Every conversation is stored with its full history in the workspace. Ask your adviser what your retention rules need.

Can I stop the agent from discussing returns or advice?

Yes, write it as a needs attention rule so the agent stops and a person answers.

Sources and method

Controls from the fact register. Green Shield Logistics and wealth advisor referral network case studies, Sellinger production data, read only, to 9 October 2026. Customer base snapshot of 18 October 2026.