> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oasm.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat and run agent tasks

> Use the AI Studio composer to ask questions about your workspace or hand the agent a task, follow its answer, and manage your conversations

Every AI Studio conversation starts in the composer: the box where you type, with the controls that decide what the agent may do. This page covers each control, the difference between Ask mode and Agent mode, the starter prompts, a complete agent task from start to finish, and how to manage your conversations.

Before you start, connect a model. Until you do, AI Studio shows **Connect an AI Provider** with a **Connect** button instead of the composer. See [Connect a model](https://docs.oasm.io/ai-studio/connect-a-model.md).

## Start a chat

**1. Open a new chat**

Click **AI Studio** in the console sidebar, then **New Chat** in the AI Studio sidebar.

**2. Choose the scope**

The project selector above the composer reads **Whole workspace**. Leave it, or pick a project to lock the chat to that project. See [Project chats](https://docs.oasm.io/ai-studio/project-chats.md).

**3. Choose the mode**

A new chat starts in Ask mode. Click **Agent** to switch to Agent mode when the task needs tools run on a worker. The button turns orange and the console confirms with "Agent mode enabled".

**4. Pick a worker (Agent mode)**

In Agent mode a worker selector appears next to the project selector. Leave it on **Auto (any worker)** or pick a worker.

**5. Check the model, reasoning effort and approval mode**

The model and reasoning effort sit at the bottom left of the composer, the approval mode next to the send button. The defaults are usually what you want.

**6. Send your message**

Type your request, or pick a starter prompt below the composer, then press <kbd>Enter</kbd>.

![AI Studio new chat with a project selected above the composer, the worker selector set to Auto (any worker), the model and reasoning effort on the left, the Agent button active, approval mode set to Manual, and the External recon, Ports & services and Web app pentest prompt groups](https://mintcdn.com/oasmplatform/JcAER2Ib37AN8_8A/images/screens/ai-compose.webp?fit=max\&auto=format\&n=JcAER2Ib37AN8_8A\&q=85\&s=db3dd620e451ce2804f292d4be0a3c63)

A new chat in Agent mode, scoped to a project, with the starter prompt groups below the composer

The chat opens as soon as you send. Conversations are private: no other workspace member can see them.

## The composer

| Control | Where | What it does |
| - | - | - |
| **Project** | Above the composer | **Whole workspace** or one active project. Set it before the first message: once the chat exists, the project is shown but cannot change |
| **Worker** | Above the composer, Agent mode only | Where the agent runs commands: **Auto (any worker)** or one online worker. Workers that serve every workspace are marked **(Global)** |
| **Model** | Bottom left | The model that answers. Lists the models of the connection in use, with a **Search models...** box |
| **Reasoning effort** | Next to the model | How much the model reasons before it answers: **Default**, or a level the model supports |
| **Agent** | Bottom right | Switches between Ask mode and Agent mode. Only shown before the first message |
| **Approval mode** | Next to the send button | **Manual** (approve each new command) or **Auto** (run every command without asking) |
| **Send / Stop** | Bottom right | Sends the message. While the agent works, the button turns into **Stop** |

### Project

The project selector lists your active projects. A chat about a project only reads and changes that project's data, and follows the project's instructions and files. See [Project chats](https://docs.oasm.io/ai-studio/project-chats.md).

### Worker

In Agent mode the agent runs commands on a [worker](https://docs.oasm.io/worker.md). With **Auto (any worker)**, OASM uses a connected worker of your workspace, or a global one if none is connected, and the chat keeps using the worker it ran on first while that worker stays online.

* Pick the worker before you send the first message: the chat keeps the worker it starts with.
* The list only shows workers that are online right now, and refreshes each time you open it.
* If the worker you picked goes offline, the selector switches back to Auto and the console says "The selected worker went offline, switched to Auto".
* Agent mode needs at least one online worker. With none, the **Agent** button opens the connect-worker dialog instead of switching mode. If you send an Agent-mode message while no worker is online, the same dialog opens and your message stays in the composer; once the new worker joins, the message is sent on it (or on **Auto** if the worker is not ready within 10 seconds).

### Model and reasoning effort

The model selector shows the model of the connection the chat uses: your default connection in a new chat. Picking a model also saves it as that connection's model, and the console confirms with "Model updated". With no connection at all, the selector reads **Connect LLM** and opens the provider settings.

The reasoning effort selector starts at **Default**: your settings default, else the provider's. It lists the levels the model publishes, from **None**, **Minimal**, **Low**, **Medium**, **High**, **Extra high** and **Max**; a model that publishes none gets **Low**, **Medium** and **High**. The effort you pick is saved on the connection, next to its model.

You can change the model and the effort between messages of the same chat. To change the defaults, see [Models](https://docs.oasm.io/ai-studio/settings/models.md).

### Approval mode

The approval selector shows the current mode; its tooltip reads "Approval: Manual" or "Approval: Auto".

| Mode | Description in the menu |
| - | - |
| **Auto** | Run every command without asking |
| **Manual** | Approve each new command |

A new chat starts in your **Default Approval Mode** from [Models](https://docs.oasm.io/ai-studio/settings/models.md). Without one, it starts in the mode you last picked in this browser, or **Manual** the first time. See [Plans and approvals](https://docs.oasm.io/ai-studio/plans-and-approvals.md) for what each mode asks and the checks that run in both.

### Send and stop

Press <kbd>Enter</kbd> or click the send button. <kbd>Shift</kbd>+<kbd>Enter</kbd> adds a new line. The send button stays disabled while the box is empty.

While the agent works, the text box is disabled and reads "Waiting for response…", and the send button turns into **Stop**. See [Stop a run](#stop-a-run).

## Ask mode and Agent mode

| | Ask mode | Agent mode |
| - | - | - |
| **For** | Quick questions and answers | Multi-step tasks that run tools |
| **Reads workspace data** | Yes | Yes |
| **Fetches public web pages** | Yes | Yes |
| **Runs commands and tool connectors on a worker** | No | Yes |
| **Drives a headless browser** | No | Yes |
| **Changes projects, targets and installed tools** | No | Yes |
| **Proposes findings for review** | No | Yes |
| **Dispatches subagents** | No | Yes |
| **Writes a plan you approve** | Never | Before its first tool call |
| **Needs an online worker** | No | Yes |

### Ask mode

Ask mode answers questions about your workspace. The agent looks up what it needs, such as assets, targets, vulnerabilities, issues, ports, technologies, TLS certificates, statistics, workers, jobs, installed tools and projects, and answers from what it finds. For general security questions it answers from its own knowledge, and fetches a public page such as a CVE record when it needs current facts.

Ask mode cannot run commands, scans or tools. When you ask for that, the agent says the task needs Agent mode and still answers whatever it can from workspace data.

> [!NOTE]
>
> Fetching a web page is not treated as read-only, so in **Manual** approval mode the agent asks before it fetches one, even in Ask mode. Workspace lookups never ask.

### Agent mode

Agent mode does everything Ask mode does, and can also act:

* Run commands and installed tool connectors on the chat's worker, and drive a headless browser there.
* Create and change projects, add targets, install tools and run project workflows.
* Record a finding it confirmed as a proposal for review (see [Findings the agent proposes](#findings-the-agent-proposes)).
* Hand focused jobs to **subagents** that run in the background, several at once (see [Side panel](https://docs.oasm.io/ai-studio/side-panel.md#how-subagents-work)).

Agent mode works from a **plan**. When you send a task, OASM first pins a **goal** for it, then the agent writes the plan: an ordered list of the outcomes it will deliver. Every tool call, including a read-only lookup, waits until you approve the plan and the agent starts its first step. A call made before that is refused and shows **Needs plan** in the chat. A reply that needs no tool, such as a clarifying question, needs no plan. See [Plans and approvals](https://docs.oasm.io/ai-studio/plans-and-approvals.md).

> [!TIP]
>
> For a quick lookup, use Ask mode: it answers without a plan to approve.

The mode is fixed once the chat starts. To switch, start a new chat.

## Starter prompts

Below the composer of a new chat, three topic chips offer ready-made prompts. Click a chip to list its prompts; hover over one (or focus it with the keyboard) to preview it as the composer's placeholder. Click **×**, press <kbd>Esc</kbd> or click outside the list to go back to the chips.

| Mode | Groups | What picking a prompt does |
| - | - | - |
| Ask | **Overview**, **Attack surface**, **Vulnerabilities** | Sends the prompt straight away |
| Agent | **External recon**, **Ports & services**, **Web app pentest** | Fills the prompt into the composer, followed by a space, and keeps the list open. Add a target and press <kbd>Enter</kbd> |

Each group holds five prompts. Some examples:

> [tab] Ask mode
>
> * **Overview**: "Summarize the security posture of this workspace", "What are the top 5 risks I should fix this week?"
> * **Attack surface**: "Which open ports are most common, and which ones look risky?", "Find assets that expose admin panels or login pages"
> * **Vulnerabilities**: "Show my critical and high vulnerabilities and how to fix them", "Which vulnerabilities have a known CVE?"

> [tab] Agent mode
>
> * **External recon**: "Fingerprint the technologies behind my live host so I can choose the right next steps for it"
> * **Ports & services**: "Scan my public host for open ports, then fingerprint the services on what is open and report what is unexpectedly exposed to the internet"
> * **Web app pentest**: "Test my web server for TLS misconfigurations, missing security headers and exposed config or backup files"

Agent-mode prompts run real tools against real hosts, which is why they wait for you to add the target and send.

## Example: run an agent task

This walk-through scans one host for exposed services, approving each command as it comes.

**1. Start an Agent-mode chat**

Click **New Chat**, pick the project the host belongs to in the project selector, and click **Agent**. Leave the worker on **Auto (any worker)** and the approval mode on **Manual**.

**2. Pick a prompt and add the target**

Click **Ports & services**, then "Scan my public host for open ports, then fingerprint the services on what is open and report what is unexpectedly exposed to the internet". Type the host after the prompt, for example `app.example.com`, and press <kbd>Enter</kbd>.

**3. Review the plan**

The goal appears first, then the agent's plan. The **Run this plan?** prompt takes the place of the composer. Read the steps, then choose **Yes, but approve each command** (press <kbd>2</kbd>). To change the plan, type what to change in **Tell the agent how to change the plan** and press <kbd>Enter</kbd>; the agent sends a revised plan.

**4. Approve the commands**

As the agent works, each new command shows **Run this command?** with the exact command line. Press <kbd>1</kbd> (**Yes**) to run it, or type what to do instead and press <kbd>Enter</kbd>.

**5. Follow the run**

Tool calls appear in the chat as they run. Click **Open side panel** at the top right to watch the plan's progress, the subagents the agent dispatched and every tool call. See [Side panel](https://docs.oasm.io/ai-studio/side-panel.md).

**6. Read the answer**

The final answer opens with whether the goal was met (fully, partly or not), then the findings with their evidence and the next steps worth doing. Findings the agent confirmed may also wait for you under **Vulnerabilities → Pending review (AI)**.

**7. Follow up**

Ask a follow-up in the same chat, for example "Check the TLS configuration of the services you found". New work that needs tools gets a new plan to approve.

## Answers

The answer streams into the conversation:

* **Thinking**: while the model reasons, a **Thinking** label shows; once done it reads, for example, "Thought for 4 seconds". Expand it to read the reasoning.
* **Tool calls** appear inline as they run. Two or more calls in a row fold into one group labeled with the latest call and a count, such as **Transition Step** with a **46 tool calls** badge; expand it to see each call. A remote command shows its output live.
* **The plan** shows in its own card with its steps and a status: **Planning** while it waits for your approval, **Plan ready** once approved.
* **Copy**: under a finished answer, the copy button copies its text. Older answers show it when you hover over them.

Scroll up to load older messages; the arrow button at the bottom jumps back to the latest one.

![A completed Agent mode answer showing the approved four-step plan marked Plan ready, a Transition Step group with 46 tool calls, and a summary opening with Goal: met fully, next to the side panel on its Stats tab](https://mintcdn.com/oasmplatform/JcAER2Ib37AN8_8A/images/screens/ai-answer.webp?fit=max\&auto=format\&n=JcAER2Ib37AN8_8A\&q=85\&s=fb5b93c5009f5b50de3d99b4c81aca0b)

A finished Agent-mode answer, with the approved plan and grouped tool calls above it

If the connection drops or the provider returns a temporary error, the chat retries on its own and shows "Retrying… (attempt 1 of 3)". If it still fails, a **Streaming error** box shows the message with **Retry**, which asks for the answer again.

## Follow-ups

When an answer is finished, send your next message in the same chat. The agent keeps the conversation's history, project, mode and worker.

* You can change the model, the reasoning effort and the approval mode between messages.
* In Agent mode, once every step of a plan is done, new work that needs tools starts with a new plan for you to approve.
* Long conversations are summarized automatically so they keep fitting in the model's context window. The **Stats** tab of the side panel shows how much of it is used.

## Runs keep going on the server

A run belongs to the server, not to your browser tab. If you close the tab, reload, open another conversation or lose your connection, the run keeps going. Open the conversation again to pick up the live answer, or read the result once it has finished. A spinner next to a chat in the **Chats** list shows it is still running.

An approval prompt waits for you too: open the conversation again within five minutes and it is shown again. After five minutes it counts as rejected.

### Stop a run

Click **Stop** in the composer. Stopping:

* ends the run on the server,
* cancels the conversation's queued and running subagents,
* puts the plan step that was running back to pending, so your next message can pick the plan up again.

Closing the tab never stops a run; only **Stop** does. Stopping needs the `agent.write` permission.

## Conversations

The **Chats** list in the AI Studio sidebar shows your conversations, the most recently active first. Click one to open it, and **Load more** at the bottom for older ones.

### Titles

A new chat is titled with your first message. After the first answer, OASM replaces it with a short title generated from the question and the answer. A chat you renamed keeps your title. Until a title exists, the chat reads **New conversation**.

The chat's header shows its title and how long ago it started.

### Rename or delete a chat

**1. Open the chat's menu**

Hover over the chat in the **Chats** list and click **…** (**Conversation actions**).

**2. Rename or delete**

* **Rename** turns the title into a text box. Press <kbd>Enter</kbd> or click away to save, <kbd>Esc</kbd> to cancel.
* **Delete** asks you to confirm. Deleting the open chat takes you to a new chat.

To delete every conversation, click **…** next to the **Chats** heading and choose **Delete all**. Deletion cannot be undone. Renaming and deleting need the `agent.write` permission.

Deleting a [project](https://docs.oasm.io/project.md#archive-reopen-and-delete) also deletes its chats.

## Keyboard shortcuts

| Where | Keys | Action |
| - | - | - |
| Composer | <kbd>Enter</kbd> | Send |
| Composer | <kbd>Shift</kbd>+<kbd>Enter</kbd> | New line |
| Starter prompt list | <kbd>Esc</kbd> | Close the list |
| Approval prompt | <kbd>1</kbd>–<kbd>9</kbd> | Pick that option |
| Approval prompt | <kbd>↑</kbd> <kbd>↓</kbd>, then <kbd>Enter</kbd> | Move between the options and the feedback box, then confirm |
| Approval prompt | <kbd>Esc</kbd> | Reject |
| Renaming a chat | <kbd>Enter</kbd> / <kbd>Esc</kbd> | Save / cancel |
| Anywhere in the console | <kbd>Ctrl</kbd>+<kbd>K</kbd> or <kbd>⌘</kbd>+<kbd>K</kbd> | Open the quick switcher, which offers **Ask AI** when nothing matches |

## Open AI Studio from elsewhere in the console

| Where | Control | What it does |
| - | - | - |
| Quick switcher (<kbd>Ctrl</kbd>+<kbd>K</kbd>) | **Ask AI about "your term"**, offered when nothing matches | Opens a new Ask-mode chat and sends your term as the question. <kbd>Enter</kbd> picks it |
| [Search](https://docs.oasm.io/search.md) page | **Ask AI**, on a search with no results | Opens a new Ask-mode chat and sends your query |
| [Target](https://docs.oasm.io/target.md#target-detail) detail page | **Run AI Pentest** | Opens a new Agent-mode chat and sends "Pentest" followed by the target. The plan still waits for your approval |
| [Project](https://docs.oasm.io/project.md) page | **Chat with agent** | Opens a new Agent-mode chat locked to the project. See [Project chats](https://docs.oasm.io/ai-studio/project-chats.md) |
| Templates | **AI gen** | Opens a new chat with the start of a Nuclei template request filled in for you to finish and send |
| Vulnerability review page | **Open conversation** | Opens the chat in which the agent proposed the finding |

**Run AI Pentest**, **AI gen** and **Chat with agent** are only shown to members with the `agent.read` permission.

> [!NOTE]
>
> The **Analyze** button on a vulnerability's **AI Analysis** tab is not an AI Studio chat: it writes a report on the finding with your connected model, right on the vulnerability page. See [AI analysis](https://docs.oasm.io/vulnerability.md#ai-analysis).

## Findings the agent proposes

In Agent mode, the agent can record a finding it confirmed with evidence: the requests that reproduce it, the responses that prove it and a baseline to compare against. The finding does not appear among your vulnerabilities right away. It becomes a **proposal** under **Vulnerabilities → Pending review (AI)**, where a reviewer approves, rejects or merges it. The review page links back to the chat with **Open conversation**.

The agent can only propose findings when you have the `vulnerability.write` permission. See [AI proposals and review](https://docs.oasm.io/vulnerability.md#ai-proposals-and-review).

## Permissions

| Permission | Allows |
| - | - |
| `agent.read` | Open AI Studio, chat, and read your conversations |
| `agent.write` | Stop a run, answer approval prompts, rename and delete conversations, change agent settings |

What the agent may do with your workspace data follows your own permissions: a tool that needs a permission you lack is refused before anything runs. See [Permissions](https://docs.oasm.io/permissions.md).

## Related

> [card] [Plans and approvals](https://docs.oasm.io/ai-studio/plans-and-approvals.md)
>
> Approve plans and commands, and the checks that run in Auto mode too

> [card] [Side panel](https://docs.oasm.io/ai-studio/side-panel.md)
>
> Follow the plan, subagents, browser and tool calls of a run

> [card] [Project chats](https://docs.oasm.io/ai-studio/project-chats.md)
>
> Lock a chat to a project and give the agent instructions and files

> [card] [Models](https://docs.oasm.io/ai-studio/settings/models.md)
>
> Default model, reasoning effort and approval mode


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.