Skip to main content
The Agent builder lets you create a DinoAI agent without writing YAML. You define its identity and permissions in a form, then deploy it to the workspace directly or as a pull request that writes the agent to .dinoai/agents/<name>.yml on your default branch. Start from scratch or from a template.
Prerequisites
  • Access to the Agent app in your Paradime workspace.
  • A connected git repository if you want to deploy the agent as code through a pull request.
Estimated time: 15 minutes.

​
Steps

1

Start a new agent

In the Agent app, open Agents and select New. Pick a template to prefill the agent’s identity, or choose Start from scratch. Templates are grouped by outcome: Reliability, Quality, Cost, Code review, Documentation, and Analytics.
2

Define its identity

Under Identity, set what the agent is and what it is for. These are what the model reads before anything else.
  • Name: becomes the filename under .dinoai/agents/ and how you invoke the agent.
  • Role: who the agent is (for example, “Analytics engineer reviewing revenue models”).
  • Goal: what it should achieve.
  • Backstory: context it carries into every run, such as conventions and what to be careful with.
3

Choose the model

Under Model, leave Auto selected so Paradime picks the best model for each task.
4

Set its tools

Under Tools, choose which tools the agent may use:
  • Allowed tools: only these, everything else is refused.
  • Denied tools: everything the workspace allows, except these.
Leave both empty to inherit the workspace’s tool permissions.
5

Set output and squad (optional)

  • Output: a Slack channel the agent posts results to. Leave it empty and the agent replies wherever it was invoked.
  • Squad: other agents this one can delegate to. Each sub-agent runs in its own session and reports back.
6

Deploy the agent

Select Deploy and choose where the agent lives:
  • Just here: saved to this workspace and live straight away, with no file in your repo. Ideal for iterating quickly.
  • Open a pull request: Paradime commits .dinoai/agents/<name>.yml to a branch and opens a pull request against your default branch. Merge it to make the agent available, version-controlled alongside the rest of your project.
Both kinds appear in the same agent list and are equally selectable everywhere agents run, including the Bolt command picker.
The agent appears in the agent list and in the Agent name dropdown when you add a Run Paradime DinoAI Agent command in Bolt: immediately for a Just here deploy, or once the pull request merges for an as-code deploy (from then on you can also edit the YAML directly).

​
Next steps

Run an agent with Bolt

Schedule the agent to run on cron, on merge, or after a job.

Programmable Agents reference

The YAML the builder writes, tools, and the API.

Related topics

Automate with AI agentsUpgrade with the DinoAI agentSelf-heal Dagster pipelinesBolt CI healerBolt pipeline healer