Skip to main content

Operations

How the platform runs itself — the autonomous agent fleet, monitoring, and the runbooks for when things break.

The agent fleet

Atlas is backed by an autonomous fleet. Full map: agent-fleet.

AgentJob
TriageSuitability-gates issues → agent:build / needs-*
BuildDrafts a PR into Human Review (merged ≠ live — still needs a deploy)
OrchestratorBoard-driven: picks highest-priority Todo → pipeline (nightly)
Intake RouterDedups all board writes into one issue
Market-intelCompetitor / market scanning
Cost-watch · Model-watchSpend surges; new/deprecated models
Operator (COO)Runs inside the heartbeat dispatcher tick
Learning-digestRolls capability gaps into the autonomy digest
Build pipeline reality

The build agent only ever drafts a PR you merge — critical-path work still gets built, then reviewed before merge (QA + top-model code review). The human-merge gate is the safety net, not a human-build block.

Observability watchdogs

Scheduled, detection-only, → intake + Slack: error / ops / cost / model, ci_watch (CI failures), uptime_watch (endpoint down, 15-min), freshness_watch (pipeline stalled), configdrift_watch (Cloud Run public-exposure flips, SOC2 CC6). Setup: MONITORING_SETUP. Remaining blind spots (PHI-access, $ spend, OAuth-token health) are tracked in agent-fleet + epics #365/#366.

Kill switch

tools/atlas_kill.py --pause sets system/atlas_autonomy_master. Every autonomous loop checks autonomy_paused() (deadman: fail-closed after 3 read failures). Autonomy is per-tenant, never global.

Runbook

Day-to-day: operations. Deploy: deployment.

Gap

No formal incident-response playbook (SLAs, escalation paths, post-mortems) and no data-retention / deletion runbook. High-value additions for a healthcare platform — tracked as ops gaps, not yet built.