> For the complete documentation index, see [llms.txt](https://docs.tabnine.com/main/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/agent-features.md).
# AI Features
There are several settings here for managing AI in Tabnine.
{% hint style="info" %}
This was previously located on the Agent Settings page, which was replaced with the [Cost Control page](/main/administering-tabnine/managing-your-team/settings/agent-settings.md) in v6.3.0.
{% endhint %}
### Restricting Agent from Running Tools Outside the Workspace
Tabnine Agent enforces workspace boundaries for file-system tools, preventing it from accessing or modifying files outside the active project directory. This protection is on by default and requires no configuration.
To activate, toggle the option.
### Restrict YOLO (Auto-Approve) mode in Tabnine CLI ([v6.4.0](https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/pages/risy3bTOlfBfgFRRXK8K#v6.4.0))
Prevent users from running the Tabnine CLI in YOLO mode, where all tool calls (file writes, shell commands, MCP calls) are auto-approved with no review. Takes effect on the user's next CLI session. [*See **YOLO Mode***](https://docs.tabnine.com/main/administering-tabnine/managing-your-team/settings/pages/pQCZSrkVJCA2g1RzehYu#restrict-yolo-mode-v6.4.0).
### LLM Priority Scheduling
This lets admins enable LLM priority on individual OpenAI-compatible models. Priorities apply to both chat and agent requests. Once at least one model has it enabled, an LLM Priority column appears on the Teams → Features page for assigning per-team priorities.
---
# 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.tabnine.com/main/administering-tabnine/managing-your-team/settings/agent-features.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.
