Security
Built for teams that cannot hand-wave risk.
Delightful Computer builds AI systems for teams where being wrong is expensive and someone has to sign their name to the output. Security is handled as part of system design: data boundaries, identity, reviewer control, logging, and rollback are specified before production work starts.
Common controls include least-data design, scoped credentials, client-owned deployment, human review paths, reviewer-visible reasoning, prompt and model metadata, retrieval traceability, and audit-ready evidence. The goal is to make the system inspectable by the people who own the risk.
The public website does not expose customer workspaces, operational write actions, or production APIs. Engagement-specific systems are scoped, authenticated, and documented inside the client environment. Security reports can be sent to morgan@delightful.computer.