Paradime DinoAI Agent Trigger
Overview
The Run Paradime DinoAI Agent command lets a Bolt schedule kick off a Paradime DinoAI programmable agent with a specific task.
Use this command type whenever you want an autonomous DinoAI agent to run on a schedule, on PR merge, on an upstream-job completion, or any other Bolt trigger — for example, a nightly data-quality agent, a freshness check, or a "summarise yesterday's failures and post to Slack" agent.

Prerequisites
A programmable agent definition committed to your dbt™ repository under
.dinoai/agents/<name>.yml. The<name>you pick in the Bolt command UI must match an existing agent file.Generate API credentials in your Paradime workspace with DinoAI Agent capabilities.
Use the generated credentials and set them as environment variables for Bolt Schedules:
PARADIME_API_ENDPOINT
PARADIME_API_SECRET
PARADIME_API_KEY
When to Use
The Run Paradime DinoAI Agent command is valuable when:
Scheduled agent runs: Run a DinoAI agent on a cron schedule (e.g. nightly data-quality sweeps, weekly freshness reports).
Post-deployment automation: Trigger an agent after a successful production
dbt run(e.g. summarise model changes, sync docs, notify stakeholders).Incident response on failure: Chain a DinoAI agent to a failing schedule (via trigger on run completion) to investigate and report on the failure automatically.
PR-driven workflows: Combine with Turbo CI so an agent runs against a PR's branch when a pull request is opened.
How to Configure the DinoAI Agent Command
From the Bolt UI, click Add command and select Run Paradime DinoAI Agent.
Agent Name — pick the agent you want to run from the dropdown. The list is populated from the agent YAML files in
.dinoai/agents/on the configured git branch. If the dropdown is empty, you need to commit an agent definition first — see Programmable Agents → YAML Configuration.Task — describe the task you want the agent to complete. This becomes the agent's opening user message (the
--messageargument toparadime dinoai). Be specific: agents work best when the task is narrowly scoped and references concrete inputs (e.g. table names, schedule names, time windows).Click Save Command.
Configure your desired trigger type (e.g. scheduled run, on run completion, on PR merge).
Deploy your schedule.
Each scheduled run is a fresh agent session. The Bolt command does not resume previous sessions — every Bolt run that fires this command starts a new DinoAI agent session with the configured task as its first message. Use the Programmable Agents API if you need session continuity across runs.
Tools available to the agent are controlled by the agent's YAML — including its access to Bolt, Slack, Linear, the data warehouse, and the file system. See the Tools Reference for the full list and the YAML Configuration guide for how to scope them.
Related
Last updated
Was this helpful?