> For the complete documentation index, see [llms.txt](https://docs.medcrypt.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.medcrypt.com/medcrypt-documentation/msi/msi.md). # MSI overview Medcrypt Security Intelligence (MSI) applies AI to medical device cybersecurity and regulatory work: threat models, submission documents, readiness checks, audits and maturity scoring. Everything is grounded in your own documents, and you review it before it's final.


Get started	Find your way around MSI Create your first device Understand your dashboard Answer guided questions Ask MSI a question
Manage risk	Review your threat model Triage risks in the Risk Register Compare with pentest or scanner findings
Prepare your submission	Check eSTAR readiness Find and close compliance gaps Generate submission documents Run a regulatory audit
Know your device	Review and correct device knowledge Trace an AI claim to its source Manage device versions and changes
Work with your team	Assign work and track My Work Manage users and access
Measure your program	Run a maturity assessment

## How MSI works 1. **You create a device from your documents.** MSI reads your design specs, risk analyses, test reports and SBOMs and builds a knowledge base for the device: its profile, architecture and requirements. 2. **Analyses run in the background.** Threat modeling, eSTAR readiness, maturity assessment and regulatory audits read the device's knowledge base. Each run is kept, so you can compare runs over time. 3. **You review and correct.** Answer guided questions, triage the Risk Register, fix device knowledge and resolve contradictions between documents. Your answers improve the next run. 4. **You produce deliverables.** Generate submission documents, close compliance gaps and export results for regulators. Every AI claim is labeled by how well your documents support it, from **Verified** (a quote found word for word) to **Unverified** (a quote that couldn't be found). See [Trace an AI claim to its source](/medcrypt-documentation/msi/review-and-correct-device-knowledge/trace-an-ai-claim-to-its-source.md). Which features you see depends on your organization's plan. To learn about roles, workspaces and who can see what, see [Manage users and access](/medcrypt-documentation/msi/assign-work-and-track-my-work/manage-users-and-access.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.medcrypt.com/medcrypt-documentation/msi/msi.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.