Skip to content

Agents

Cantila's self-healing brain runs an agent swarm over your projects on a 60-second tick. High-confidence, safe actions auto-apply; destructive ones wait for your confirmation. Every action is logged, and a learning loop keeps the system honest over time.

The swarm

Eight specialized agents run on each tick:

AgentWatches
UptimeHealth checks, restarts, rollbacks
DeployBuild / release health
CostSpend anomalies and waste
ScaleRight-sizing replicas
SecurityExposure and credential hygiene
CapacityHeadroom on shared resources
MailSending health / deliverability
SMSTelephony health

What auto-applies vs. waits

  • Auto-apply (high-confidence, safe): rollback a bad deploy, scale down idle capacity, sleep an idle project.
  • Waits for confirmation: anything destructive surfaces as a proposal you approve.

Every action — auto-applied or proposed — appears in the activity feed at /v1/activity.

Trust over time

A learning loop downgrades confidence for action kinds with a bad track record, so a class of fix that has caused problems before stops auto-applying. Post-checks verify auto-applied actions and flag regressions.

Pausing

Pause the swarm at any time:

cantila agents pause

Resume when you're ready:

cantila agents resume

API reference

MethodPathNotes
GET/v1/agents/statusCurrent swarm status
POST/v1/agents/pausePause auto-apply
POST/v1/agents/resumeResume
GET/v1/agents/proposalsPending proposals to confirm
GET/v1/activityFull action log

MCP & Console

  • MCP: cantila_agents_status
  • Console: /agents