The monitoring product just became a prompt. supabase's observability autopilot, out september 13,…
the monitoring product just became a prompt. supabase's observability autopilot, out september 13, hands you agent prompts instead of running the agents for you.
the company ships the question, not the answer.
Context
Supabase's changelog entry on observability on auto-pilot, listed as a new feature on 2026-09-13, describes a hire an agent guide with four roles, each with a prepared prompt and setup for Claude Routines, Codex scheduled tasks or Cursor Automations, running in any environment that supports MCP, with findings routed through the user's own integrations such as Linear and Slack. It also ships a query_logs MCP tool covering API, Auth, Storage, Edge Functions and Postgres logs, and the Supabase plugin bundling the MCP server and skills. The current docs say the prompts read project data read-only and change nothing, with MCP set to project_ref and read_only=true.
Supabase ships the prompt and the data access and the agent runs in the user's own harness and schedule, which supports the note's wording. No text read describes agents making production changes or Supabase-run agents, so this is not production remediation, and autopilot is the changelog's title. Role names differ between the changelog (Health, Security, Performance, Capacity) and the current docs (Health, Security, Performance, Resources), which are different dates and not a conflict. Nothing read says an earlier monitoring product was replaced. The monitoring product just became a prompt is the author's framing.
Watch next
- Any later change to the agent roles.
Sources
- Supabase changelog: observability on auto-pilotsupabase.com
- Supabase docs: automate with agentssupabase.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 22 September 2026 at 10:58 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →