For the complete documentation index, see llms.txt. This page is also available as Markdown.

Dastra AI agents

Dastra AI agents let you build your own specialised chat assistants and autonomous agents that run on a schedule

A Dastra AI agent is an assistant you configure yourself: you give it a role, a set of instructions, and the list of tools it is allowed to use in your workspace. Where the standard AI assistant answers anything, an agent is specialised on one mission and always behaves the same way.

Agents are configured from Workspace settings > AI agents (direct access).

List of the Dastra AI agents of a workspace
Workspace settings > AI agents — the list of configured agents

Two types of agents

Conversational Agent
Auto Agent

What it is for

A specialised chat assistant with its own personality and rules

A repetitive task that runs with nobody watching

What triggers it

A user, by opening a conversation

A manual run, a schedule, or a workflow rule

Interaction

The agent can ask questions and request confirmation

The agent can neither ask a question nor request confirmation: it goes all the way and returns its result

Where you find it

In the Dastra AI panel, through the Choose an agent selector

In AI agents, with its runs in the Inbox

What you configure

Welcome message, assistant instruction, conversation starters

System instruction, input fields, scheduling


Creating an agent

Click Create agent. Five starting points are offered:

Agent creation dialog with the five starting points
The five ways to create an agent
  • Generate with Dastra AI — describe the mission in a few words and the assistant builds the agent with you, saving it once you approve. This is the built-in /scaffold_agent skill.

  • Conversational Agent — start from a blank page for a chat assistant. See Creating a conversational agent.

  • Auto Agent — start from a blank page for a tool-driven run. See Creating an autonomous agent.

  • Dastra library — start from a ready-made template built by the Dastra team. The template is imported as a draft: review its instructions and its tools before publishing it.

  • Import an agent — drop in a definition file previously exported from Dastra.

In every case creation happens in two steps: you pick the type, you enter a name (120 characters maximum) and an optional description (1000 characters), then the full editor opens.

The editor saves automatically: the last save time is shown in the top-right corner. There is no Save button.


Publishing, deactivating, archiving, deleting

  • Enabled / Deactivated — a deactivated agent no longer appears to users and its schedules stop firing. This is the state to use while you are still tuning its instructions.

  • Archive — the agent goes to the recycle bin. Tick View recycle bin in the list to find it and restore it. Its past runs are kept.

  • Delete — deletion is permanent and also erases every session and every message belonging to the agent. Use it when you need to purge that data.

Exporting and importing an agent

The Export button produces a JSON file containing the agent definition (instructions, tools, input fields, scheduling). You can import it into another workspace through Create agent > Import an agent.

On import, Dastra resets a few things: the agent is created deactivated, without a logo and without notified users. Review it, then enable it.


Who can do what

Access to agents depends both on your plan and on your permissions.

Permission
What it allows

AI Assistant usage

Use the conversational assistant: ask questions, let the agent use its read-only tools

AI Assistant edit mode

Let the assistant create and update records from the conversation

Custom AI agents execution

See the agents of the workspace and run them

Custom AI agents management

Create, update and delete the agents of the workspace

Permissions are set in Organization settings > Roles and permissions. The MCP server is covered by a separate plan.

An agent never has more rights than the person who triggers it. Its tools run with your own permissions: if it cannot access a record, neither can the agent.


Credits and consumption

Each message you send to an agent costs 1 Dastra AI credit, whatever the number of tools the agent then uses to answer you. Resuming a conversation after a confirmation request costs nothing extra.

Your organization's monthly quota and its consumption are tracked in Organization settings > Dastra AI. Once the quota is reached, conversations and runs are refused, and the Run button of an autonomous agent is disabled.

Model families, hosting and the data sent to the models are documented in How it works.


Creating a conversational agentCreating an autonomous agentSkillsTracking runs

Last updated

Was this helpful?