You stay in control. The agent always opens a PR — it never merges to your default branch. Reviewers approve the fix before it reaches production.
Configure from the Bolt UI
In the Bolt schedule editor:- Open the Self-Healing section.
- Toggle Enable Self-Healing.
- Pick the Slack channel the agent should run in. It must already be configured as a Slack notification channel on this schedule.
- Pick an Agent Name from the dropdown — the list is populated from
.dinoai/agents/*.ymlon the configured git branch. Leave empty to use Paradime’s default Bolt-fix agent. - Save the schedule.

Configure from YAML
If you manage schedules as code, add aself_healing block to the schedule:
What happens when a run fails
- The standard failure notification posts to every Slack channel in
notifications.slack_channels. - In the Self-Healing channel, Paradime posts
🦖 Self-healing enabled — starting healing session...into the failure thread and triggers the DinoAI agent. - In every other notification channel, Paradime posts
🦖 Self-healing started in #<healing-channel>so reviewers know where to follow along. - The agent works in-thread, posts progress, and ends with a PR link for the proposed fix.
- If the same schedule has been self-healed recently, the agent is given a summary of those prior sessions so it doesn’t duplicate work — for example, if an open PR already proposes a fix.
Related
- Notification Settings - Configure the Slack channel Self-Healing reuses
- Schedules as Code - Configuration Reference — Full YAML schema
- DinoAI Self-Healing - How the agent diagnoses and fixes the failure
- Fix with DinoAI - Manual one-click equivalent
- Programmable Agents - Author a custom
agent_name