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

# LLM Session

An LLM Session lets you run scheduled AI analyses using large language models.

Each session executes automatically at a defined interval and produces an analysis result based on your configuration.

LLM Sessions can be used for:

* Market commentary
* Strategy reasoning
* Context-aware trade evaluation
* AI-assisted decision support

> Chart input is **optional**.\
> For visual chart analysis, see [**Chart Setup**](/startegies/llm-session/chart-setup.md).

***

### 🛠️ How It Works

On each run, an LLM Session sends the following to the AI:

* Your **custom prompt**
* System context (when available):
  * Symbol
  * Timeframe
  * Last action
* **Optionally:** a chart image with indicators

The AI processes this information and returns a structured or free-form analysis, depending on your prompt.

***

### ⚙️ Core Configuration

#### Name

Optional.\
If left empty, a name is generated automatically.

***

#### LLM Connection

Select the AI model used for this session.

* **Text-only sessions** → Any supported model
* **Chart-based sessions** → Image-capable (vision) models only

Model compatibility depends on whether **chart input** is enabled.

***

#### Analysis Period

Defines how often the session runs.

Available intervals:

* 3 minutes
* 5 minutes
* 15 minutes
* 30 minutes
* 1 hour
* 2 hours
* 4 hours
* Daily

***

#### Prompt

Defines what the AI should do.

Prompts can be:

* Descriptive (“Summarize market conditions”)
* Analytical (“Evaluate trend strength and momentum”)
* Strategic (“Assess whether conditions favor continuation or reversal”)

You may use **free-form natural language**.

***

#### Send Email

Enable this option to receive the analysis result by email after each run.

***

### 📊 Chart Input (Optional)

LLM Sessions can optionally include a **chart image**.

* When enabled, the AI receives a visual chart with indicators
* When disabled, the session runs as **text-only**

Chart configuration is handled separately.\
See [**Chart Setup**](/startegies/llm-session/chart-setup.md) for details.

***

### 🧾 Output & Results

Each session run produces an output that is:

* Stored and viewable in the platform
* Timestamped for historical review
* Optionally sent via email

LLM Sessions do **not** execute trades by default.

***

### 🔍 What LLM Sessions Are *Not*

* ❌ Not automatic trading
* ❌ Not guaranteed signals
* ❌ Not raw market data processing

For AI-generated trade signals, use **with** [**Signal Generation**](/startegies/llm-session/signal-generation.md).

***

### 🔗 Related Features

* [**Chart Setup**](/startegies/llm-session/chart-setup.md) – Configure visual chart input
* [**Session with Signal Generation**](/startegies/llm-session/signal-generation.md) – Generate actionable signals

***

### 🧠 Best Practices

* Start with **text-only sessions** to refine your prompt
* Enable chart input only when visual context is needed
* Keep prompts **clear and focused**
* Match the analysis period to the chart timeframe


---

# 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.sigrex.io/startegies/llm-session.md?ask=<question>&goal=<endgoal>
```

`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.