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

# Inside a Session

Each conversation with an agent produces a detailed record of what happened and why. Open a session in **Observatory > Sessions > Chat Sessions** and trace the full path of a conversation: what the user said, what the agent did in response, and every workflow operation that happened in between. 

This is how you find out why your agent behaved the way it did, whether you are investigating a problem or reviewing a conversation that went well. Additionally, use the [Session Analysis](#session-analysis) plugin to gain unique insights for each conversation through LLM-powered summaries, sentiment scores, and customizable evaluation criteria.

<div data-with-frame="true"><figure><img src="/files/sdA13SmB8Bd48KYO8sWb" alt="" width="563"><figcaption></figcaption></figure></div>

### What Gets Captured

Each session records everything that happened during a conversation, from the messages exchanged to the internal operations your workflow performed behind the scenes.

* **Transcript:** Every message between the user and the agent, whether text, voice, or a combination, or system events like LiveChat handoffs and CSAT submissions
* **Interaction log:** The full execution trace for each user message, with the steps the workflow ran in order. See the [Interaction Logs](/observatory/interaction-logs.md) page for the full reference
* **Variables:** A snapshot of all workflow variables at the end of the session, plus intermediate snapshots at each user message so you can track how values changed over time
* **Session metadata:** Context about when and where the conversation took place, who initiated it, and how it was categorized
* **Tickets:** References to support tickets created in external systems like Zendesk during the conversation
* **Analysis insights:** Summary, sentiment, resolution status, urgency, and classification tags generated by Session Analysis

This means you can answer questions like "what prompt did the LLM receive?", "which variable had the wrong value?", or "how did the user feel about the interaction?" all from a single session.

### Session Details

Select any session in the Chat Sessions table to open the detail view. Everything about the session lives here, organized across a set of tabs. Use the fullscreen button and adjust the panel size when you need more space. Some tabs are hidden when a session has no data for them, for example Contact for automated test sessions or CSAT for conversations without a survey.

<table data-column-title-hidden data-view="cards"><thead><tr><th>Title</th><th>Description</th></tr></thead><tbody><tr><td><h4><i class="fa-comments">:comments:</i></h4><h4>Chat</h4></td><td>The full conversation transcript, plus the interaction log and intermediate variables for any selected turn</td></tr><tr><td><h4><i class="fa-message-dots">:message-dots:</i></h4><h4>Session Details</h4></td><td>Metadata about the session and where you run and view Session Analysis</td></tr><tr><td><h4><i class="fa-brackets-curly">:brackets-curly:</i></h4><h4>Variables</h4></td><td>A read-only snapshot of all workflow variables at the end of the session, searchable by name or value</td></tr><tr><td><h4><i class="fa-face-smile">:face-smile:</i></h4><h4>CSAT</h4></td><td>Survey questions and the user's responses</td></tr><tr><td><h4><i class="fa-image-user">:image-user:</i></h4><h4>Contact</h4></td><td>The end-user's name and email when available</td></tr><tr><td><h4><i class="fa-ticket-perforated">:ticket-perforated:</i></h4><h4>Tickets</h4></td><td>Support tickets linked to this session from external platforms like Zendesk</td></tr></tbody></table>

The tab bar sits at the top of the detail view.

<div data-with-frame="true"><figure><img src="/files/HsmTzMr8GNqZo8S3QuIA" alt="" width="375"><figcaption></figcaption></figure></div>

#### The Chat Tab

The chat section displays the full conversation with user messages on the left and agent messages on the right. This is the opposite of a typical chat interface, where the current user's messages appear on the right. Here, the perspective is reversed because you are reviewing someone else's conversation.

{% columns %}
{% column %}
Each message is labeled as Bot or User with a timestamp. User messages appear on the left, agent responses on the right.&#x20;

The full conversation is preserved here, so you can read through every message exchanged between the user and the agent.
{% endcolumn %}

{% column %}

<div data-with-frame="true"><figure><img src="/files/L5KIQULDnu34xwc4vIIl" alt="" width="375"><figcaption></figcaption></figure></div>

{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column %}

<div data-with-frame="true"><figure><img src="/files/tnF7gYAKVhSodrnmYl60" alt="" width="563"><figcaption></figcaption></figure></div>
{% endcolumn %}

{% column %}

Select any user message in the transcript to reveal the interaction log behind it. Each step shows the type of operation, its duration, and whether it succeeded or failed. See [The Interaction Log](#the-interaction-log) for a full breakdown
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column %}

System events like conversation starts,  CSAT submissions and user LiveChat handoffs appear inline as separators.
{% endcolumn %}

{% column %}

<div data-with-frame="true"><figure><img src="/files/xwp4zq6ZtS4jukll3CXr" alt="" width="359"><figcaption></figcaption></figure></div>
{% endcolumn %}
{% endcolumns %}

{% hint style="info" %}
The URL updates with the session ID, and with the interaction ID when you select a specific user message. Copy the URL from your browser to share or bookmark the exact view.
{% endhint %}

### The Interaction Log

Selecting any user message in the transcript opens the interaction log behind the agent's reply to it. The trace shows each step the workflow ran to produce that reply, in order, with the type of operation, its duration, whether it errored, and the raw request and response payload.

<div data-with-frame="true"><figure><img src="/files/tnF7gYAKVhSodrnmYl60" alt="" width="563"><figcaption></figcaption></figure></div>

Each user message is the trigger that starts a workflow execution, so you select the user message to see what ran in response. The first agent message in the conversation is the exception. Select it directly, because it runs before any user input.

The panel has two tabs:

* **Interaction Logs:** the list of interactions in order. Expand any step to see its payload and details
* **Variable Values:** a snapshot of session-scoped variables at this point in the conversation, including the writes the workflow made up through this turn

This is what makes session debugging concrete instead of speculative. Instead of guessing why your agent said something, you can trace the exact sequence of operations and see the raw data behind each one.

Learn more about interactions in the [Interaction Logs](/observatory/interaction-logs.md) page.

### Session Analysis

Session Analysis is a powerful tool that turns individual conversations into structured, trackable data. It uses an LLM to generate insights from a completed session: a summary, sentiment score, resolution status, urgency level, and classification tags.

Open a session and navigate to the **Session Details** tab. Select **Run** to trigger it. After the first execution, the button changes to **Rerun**, letting you regenerate insights after updating your plugin configuration. To run analysis automatically on new sessions, enable and configure the [Session Analysis plugin](/build/plugins.md#session-analysis).

<div data-with-frame="true"><figure><img src="/files/AwX8dB954iIUb1Yv548A" alt="" width="340"><figcaption></figcaption></figure></div>

<details>

<summary><strong>Default Insights</strong></summary>

* **Summary:** A concise description of the conversation
* **Classification Tags:** Category labels that match your defined tags, automatically added to the session
* **Sentiment:** User satisfaction (Positive, Neutral, or Negative)
* **Resolution:** Whether the issue was addressed (Resolved, Unclear, or Unresolved)
* **Urgency:** Priority level (Low, Normal, or Urgent)

</details>

Toggle **Expert Mode** in the plugin settings to customize which insights are generated, filter which sessions get analyzed or chain multiple LLM executions for advanced analysis workflows.

These outputs are searchable across your sessions. In [Sessions](/observatory/sessions.md#searching-and-filtering), use **Search by signal** to filter by any signal key like `resolution` or `sentiment`, including custom signals.

{% hint style="info" %}
Session Analysis is powered by a plugin that needs to be activated and configured first. See the [Plugins page](/build/plugins.md#session-analysis) for setup instructions and advanced configuration options.
{% endhint %}

### Best Practices

* **Start from the interaction log when debugging:** Select the user message that triggered unexpected behavior to see what the workflow actually did.&#x20;
* **Manually add tags from the sidebar to mark sessions for follow-up:** Use the **Tags** field in **Session Details** to flag conversations you want to revisit, then filter the Chat Sessions list by those tags later
* **Bookmark a session by copying its URL:** The URL updates with the session ID and the interaction ID when you select a message. Share it in a ticket or paste it into team chat to point others at the exact view
* **Use Session Analysis for trends:** Run analysis across sessions to track sentiment and resolution patterns over time. Use Expert Mode to define custom insight categories that match your business needs

{% hint style="success" %}
You can now open any session, read the full transcript, and trace every step the workflow executed to produce each response.
{% endhint %}


---

# 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.helvia.ai/observatory/inside-a-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.