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

# Agent Sessions

> Track DinoAI agent runs in the Agent app: sessions panel across chat, Bolt, Slack, and API sources, chat transcripts, live credit and runtime metrics.

Every programmable agent run is a session, whether it was started from a chat in the app, a Bolt schedule, Slack, or the API. The **DinoAI Agent** app collects them all in one place, so you can follow a run live, read back what an agent did, and stop one that has gone off track.

## The sessions panel

The left panel of the Agent app lists your workspace's recent sessions, newest first. Each row shows:

* **Source icon**: where the session was started (chat, Bolt, Slack, or API).
* **Title**: the opening message or a generated label. Hover a row for the source name and the full title.
* **Live indicator**: a dot on sessions that are currently running, so you can tell an active run from history at a glance.

Sessions are deep-linkable: every session has its own URL you can share with a teammate.

## The session page

Opening a session shows a chat-style transcript with a compact header:

* **Status and session ID** next to the title.
* A pill strip with the **source**, **start time**, and **credits** consumed, plus **runtime** and **burn rate** while the session is still running.
* A **Stop** button on running sessions. Stopping ends the run; the session stays in the panel as stopped rather than disappearing.

In the transcript, your prompts render as chat bubbles and the agent's tool activity is collapsed into expandable "Ran N tools" lines, so the thread stays readable while the full detail (tool inputs and terminal output) is one click away. The thread sticks to the latest message while a run is live.

## Continuing the conversation

Sessions started from **Chat** in the app have a reply box under the transcript. Sending a message starts the agent again with everything it already knows, so you can refine the task, ask follow-up questions, or redirect the agent without starting over. The agent works through one message at a time: while it is busy the box is locked, and your next message goes when the current turn finishes.

Sessions started elsewhere are read-only in the app:

* **Slack** sessions are answered in their Slack thread, which stays the single place for that conversation.
* **Bolt** sessions are one run per trigger: each schedule run starts a fresh session. See [Triggering from Bolt](/products/dino-ai/programmable-agents/triggering-from-bolt).
* **API** sessions are continued programmatically with `sendDinoaiAgentMessage`. See the [API Reference](/products/dino-ai/programmable-agents/api-reference).

## Related

* [Creating Agents in the App](/products/dino-ai/programmable-agents/creating-agents-in-the-app) for building an agent and starting a chat with it
* [Triggering from Bolt](/products/dino-ai/programmable-agents/triggering-from-bolt) for scheduled runs
* [API Reference](/products/dino-ai/programmable-agents/api-reference) for programmatic sessions


## Related topics

- [Agent Sessions](/products/dino-ai/mcp-server/agent-sessions.md)
- [Starting a Slack Agent session](/products/dino-ai/slack-agent/starting-a-session.md)
- [Every agent session in one panel](/changelog/2026-08-05/agent-sessions-panel.md)
- [Creating Agents in the App](/products/dino-ai/programmable-agents/creating-agents-in-the-app.md)
- [DinoAI Programmable Agents API](/developers/graphql-api/api-reference/dinoai-programmable-agents-api.md)