Your product is ready. The security review is not.
Your buyers' security teams want on-prem, SSO, layered access control, an audit trail, and an answer to what the AI in your product is allowed to do. Building that takes a year of platform work that has nothing to do with your product.
Three ways to embed it
| Path | What it is | The trade-off |
|---|---|---|
| React SDK | our React components, placed inside your own app | fits your design system; weeks of work, and you own the front end |
| The API | any front end you like, talking to the engine | you build every screen yourself, and none of ours ship |
| Embedded UI | our full screens in an iframe, limited to the links and clicks you allow, with a short-lived token for each user and tenant | days; our screens, branded per tenant |
Your customers never see Swiftward. Colors, fonts, heading sizes, table density, and even which parts of the interface exist are declared, per tenant and per user, and your own stylesheet covers the rest. If your integration needs something none of the three paths cover, the platform is declarative, so adapting it is configuration.
What your buyer's security team gets
It runs on-prem or in your buyer's own cloud account, with SSO, access control down to the row and the field, multi-tenancy, secrets management and an append-only audit trail.
Governance under your brand
The same engine gives your product versioned policy, shadow testing, human review and a decision record. When your customer stops asking "is it secure" and starts asking "can you prove what your AI did for our users", you answer from that record.
Who this page is for
Healthcare AI, legal AI, fintech, HR tech, accounting AI — anyone selling AI into a regulated industry rather than operating in one.