Computer-use agents for the financial back office.
Agents that work on the screens your team already uses and hand back a finished case file. Starting with compliance for payment companies.
Built by a team from
Works on your screens.
Portals, registries, PDFs, your case manager, your internal tools. Zomma reads them on screen, so there is nothing to integrate, and saves a timestamped screenshot of everything it reads.
How it works
Each agent gets a computer, your logins in a vault, and your procedure. It reads every screen the work needs, writes up the case with a screenshot behind every finding, and recommends what to do. Your team decides.
Data triage and analysis.
Portals, registries, PDFs, your internal tools. It reads them on screen and saves a timestamped screenshot of each, so the file shows exactly what it saw.
Recommendation and review.
It applies your procedure and recommends the outcome, with the reasoning under it. Start it on cases your team already closed, compare with your analysts' decisions, then let it run on new ones.
Starting with compliance for payment companies.
Payment companies run the biggest queues in the back office: screening hits, transaction alerts and periodic reviews, each one needing sources read and a file written. We start there.
In the product, Screening builds the case file and Your cases applies your procedure and recommends the outcome. The same agents also handle reconciliations and disputes for payment and fund operations teams.
Same team, more cases.
- replay0:00 / 0:12
Zomma prepares the case.
Your team decides.
It runs under your control and supervision, on your procedure and your thresholds, and nothing leaves your systems without a person approving it. Your data stays inside your organization.
Give your agent a computer.
Your team already pastes the hard cases into Claude or ChatGPT. Give that agent a computer: it opens the register, runs the search, reads the website, and hands back the screenshots with the write-up. Works with Claude, Hermes, or your own agent through our API.
Common questions
How do we know it gets the work right?
You check before you trust it. We run it on work your team has already completed and compare its output with your team’s decisions, item by item. Then it runs on new work in the background until you are comfortable. Even live, it only recommends; your team makes every determination, and every step is recorded so the reviewer can see what was checked, what was found and why.
Does it work with the tools we already use?
Yes. It works on screen, the way a person does, so your portals, case manager, registries and internal systems stay exactly as they are. There is no API integration to build and nothing to migrate. It signs in with its own credentials, kept in a vault, and every two-factor prompt is cleared by a person.
What can it read and work in?
Anything your team works in on screen: bank and custodian portals, company registries, case managers, ticketing tools, PDFs, statements and spreadsheets, and your own internal systems, under credentials you control. For compliance teams that includes sanctions and PEP lists such as OFAC SDN, UK HMT, the EU and UN lists, registries such as Companies House and OpenCorporates, adverse media, court records and WHOIS. A source it cannot reach is marked unavailable in the case file rather than skipped.
Where does our data go?
Case files and screenshots are stored per organization in Zomma’s AWS environment in the United States, in a single-tenant deployment, with a retention period that you set. Model calls go to Anthropic and OpenAI under zero data retention and no training on your data, agreed in writing. Credentials are held in an isolated vault and are never sent to a model. A written data flow description is available before any agreement is signed.
How quickly can we be live?
Days, not weeks. There is no integration project: it runs on the screens your team already uses. We load your procedure, run a set of your completed cases together and compare its output with your team’s decisions. Then we agree which work to hand it first.
How is it priced?
Pricing is a flat monthly fee per deployment with no per case meter. Cost does not rise with volume inside the agreed scope, so the team can put more work through it without watching a counter. We share numbers on a call once we have seen the workflow and the case types involved.
What can our security team review?
Your security team can review the security page, the list of third-party services and the written data flow description. The SOC 2 Type 1 audit report is shared when it is issued. We also walk through the controls with your team and answer your security questionnaires.