Triggering from Bolt
A Programmable Agent can be invoked in two ways:
From the Paradime API — using
triggerDinoaiAgentRun. See API Reference.From a Bolt schedule — using the Run Paradime DinoAI Agent command type. This page.
Use Bolt when you want the agent to run on a cron schedule, after another schedule completes, on a PR merge, or as part of a Turbo CI run. Use the API when you want to embed agent runs in a workflow you orchestrate yourself (Airflow, Lambda, webhooks, etc.).
Prerequisites
A programmable agent definition committed to your repository under
.dinoai/agents/<name>.yml. See YAML Configuration.API credentials with DinoAI Agent capabilities, set as Bolt Schedule environment variables:
PARADIME_API_ENDPOINTPARADIME_API_SECRETPARADIME_API_KEY
Option 1 — Configure from the Bolt UI
In the Bolt schedule editor, click Add command and pick Run Paradime DinoAI Agent:
Agent Name — pick the agent from the dropdown. The list is populated from
.dinoai/agents/*.ymlon the configured git branch.Task — describe the task you want the agent to complete. This becomes the agent's opening user message.
Save Command, then configure the trigger type (cron, on-merge, on-completion, etc.) and deploy.
See the full UI walkthrough at Bolt Command Settings → Run Paradime DinoAI Agent.
Option 2 — Configure from schedules-as-code YAML
The UI just writes a paradime dinoai CLI invocation into the schedule's commands: list. If you manage your Bolt schedules with YAML, add the same command directly:
The arguments mirror the UI fields:
Agent Name
--agent=<name>
Must match an existing .dinoai/agents/<name>.yml on the schedule's git branch.
Task
--message="<task>"
The agent's opening user message. Use a single quoted string; both single- and double-quotes are valid.
See Configuration Reference for the full schedule YAML schema.
Lifecycle of a Bolt-triggered run
Fresh session per run. Each Bolt run starts a new agent session — there is no continuity from one schedule run to the next. Use the API with
sendDinoaiAgentMessageif you need multi-turn continuity.Bolt waits for the agent. The CLI blocks until the agent reaches a terminal state (
COMPLETEDorFAILED) and exits with the corresponding exit code. The Bolt run therefore inherits the agent's success/failure.Logs. The agent's messages stream into the Bolt command's stdout, so they show up in the Bolt run logs (and in the live log stream when polled via the SDK).
Notifications. Slack notifications configured inside the agent YAML still fire — independently from any Bolt notifications configured on the schedule itself.
Related
Last updated
Was this helpful?