> For the complete documentation index, see [llms.txt](https://docs.solcis.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.solcis.ai/get-solcis/editions.md).

# Products

The two Solcis products, what each does, and how they work together.

Solcis has two products: Solcis Compliance Studio and the Solcis Policy Engine.

**Solcis Compliance Studio.** The compliance plane, licensed commercially. It's self-hosted and air-gap capable. Compliance Studio covers policy lifecycle and authoring, learning and drift detection, the universal evidence ledger, compliance coverage and analytics (including agent discovery), compliance model management (a curated model list, routing and model performance), and integrations with GRC, SIEM and ticketing systems.

**Solcis Policy Engine.** Enforcement on the action path and at model, tool and MCP endpoints. Each intended action is evaluated before it runs, and the engine returns `Allow`, `Deny` or `Escalate`, each with a severity rating. The Solcis SDK builds it into your applications and agents; SDKs ship for TypeScript, .NET and Python. The Policy Engine is released under the Functional Source License (FSL).

## How they work together

Compliance Studio sends enforcement policies down to the enforcement points: the Solcis Policy Engine, gateways, and NVIDIA OpenShell and Microsoft AGT. Decisions and evidence come back up to Compliance Studio. The Solcis Policy Engine writes a compliance receipt for each decision; Compliance Studio's universal evidence ledger collects receipts from every enforcement point.

Policies authored once in Compliance Studio apply to every enforcement point, and every decision lands in the universal evidence ledger, so your evidence sits in one place rather than split by integration style.

An action that reaches no enforcement point isn't evaluated or recorded. Compliance Studio's coverage and agent discovery show where the gaps are.

## Enforcement points

| Property                    | Solcis Policy Engine with the Solcis SDK                               | Gateway (Solcis Gateway or your own)                        | NVIDIA OpenShell and Microsoft AGT                             |
| --------------------------- | ---------------------------------------------------------------------- | ----------------------------------------------------------- | -------------------------------------------------------------- |
| Where it sits               | Inside your application or agent, on the action path                   | In front of the servers the agent calls                     | In the agent runtime                                           |
| How actions reach it        | Your code calls the Solcis SDK                                         | Traffic is routed through the gateway                       | —                                                              |
| Change to your application  | Yes, you integrate the Solcis SDK                                      | None                                                        | —                                                              |
| What it speaks              | TypeScript, .NET, Python                                               | Model Context Protocol                                      | —                                                              |
| What it covers              | The actions you instrument                                             | Everything routed through the gateway                       | Security and infrastructure controls in the agent runtime      |
| Framework adapters          | Included                                                               | Not applicable                                              | —                                                              |
| What Compliance Studio does | Sends enforcement policies; collects decisions and compliance receipts | Sends enforcement policies; collects decisions and evidence | Supplies enforcement policies; collects decisions and evidence |

## Which enforcement point fits

| If                                                           | Enforcement point                                                  |
| ------------------------------------------------------------ | ------------------------------------------------------------------ |
| You build the agents and control their code                  | Solcis Policy Engine with the Solcis SDK                           |
| The agents are bought, third-party, or you can't change them | Solcis Gateway or your own gateway                                 |
| You want to govern MCP servers and the tools they expose     | Solcis Gateway or your own gateway                                 |
| You need enforcement inside a delivery pipeline              | Solcis Policy Engine with the Solcis SDK                           |
| Your agents run in NVIDIA OpenShell or Microsoft AGT         | NVIDIA OpenShell or Microsoft AGT, governed from Compliance Studio |
| More than one of the above is true                           | More than one                                                      |

Many organisations use more than one: the Solcis SDK for systems they build, a gateway for services they buy.

## Licensing

Compliance Studio is licensed commercially; the Solcis Policy Engine is released under the FSL. See [Licensing](/get-solcis/licensing.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.solcis.ai/get-solcis/editions.md?ask=<question>&goal=<user_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.
