> For the complete documentation index, see [llms.txt](https://docs.infraglide.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.infraglide.com/jane-ai-copilot/overview.md).
# Jane AI Overview
**Jane AI** is InfraGlideโs embedded copilot for infrastructure design, deployment diagnosis, security and cost guidance, and natural-language questions about your cloud topology.
***
## ๐ก How to Open Jane
* Press **โJ** / **Ctrl+J** anywhere in the app.
* Use the floating **Open Jane AI** control on the right sidebar.
* Inside a pipeline, the panel title is **Ask Jane**; elsewhere it appears as **Jane AI**.
* Context-specific entry points also appear on deployment logs, security findings, drift events, deployed resources (cost cards), well-architected review, compliance policy generation, and onboarding steps.
Figure 1: Jane AI Embedded Sidebar Copilot
***
## โจ What Jane Can Do
| Capability | Typical entry point |
| -------------------------------------------- | ------------------------------------------------------ |
| General Q\&A about infra / Terraform / cloud | Ask Jane panel |
| Failed deployment analysis | Executions / deployment logs โ **Ask Jane** |
| Pipeline architecture review | Designer Jane sheets โ **Architecture review** |
| Pre-deploy security posture (LLM on canvas) | **Scan posture** / pre-deploy posture sheet |
| Explain security-scan findings | Security page โ **Ask Jane** on a finding |
| Cost advisor / forecast / TCO | Deployed Resources & pipeline docs |
| Drift explanation & remediation advice | Drift report / Jane insight cards |
| Form field suggestions | **Jane** form copilot on resource forms |
| Canvas refactor / synthesize template | Designer command bar / Templates **Generate with AI** |
| Well-Architected review | **Operations โ Well-Architected** |
| Natural-language policy draft | Compliance โ **Generate policy from natural language** |
Many responses are cached per feature/scope so repeated asks stay fast.
***
## ๐ง Model & Capabilities
Jane is powered by advanced generative AI models optimized for cloud architecture reasoning, HCL syntax, and deployment log diagnostics.
If AI capabilities are not enabled for your organization, Jane displays an informational status notification explaining that AI assistance is currently inactive.
***
## ๐ What Jane Sends to the Model
Depending on the feature, Jane may include:
* Relevant canvas component attributes, node names, and visual wiring topology.
* Deployment log output and error messages for failure diagnosis.
* Aggregated resource counts for cost estimation.
* Compliance policy rules for automated drafting.
Jane never sends unencrypted cloud provider access keys or raw database credentials to the model.
***
## ๐ See Also
* [Deployment Error Analysis](/jane-ai-copilot/error-analysis.md)
* [Architecture Security Audits](/jane-ai-copilot/security-audits.md)
* [Cost Optimization & Guidance](/jane-ai-copilot/cost-optimization.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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.infraglide.com/jane-ai-copilot/overview.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.