proomt

Search

Search posts, papers, and topics

All posts

SupabaseSteven Eubank, Joshen Lim, Cemal Kılıç, Riccardo Busetti, Joe Sciarrino4 min readintermediate

Operate with confidence

Read on supabase.com

Summary

Supabase announced a suite of new features that let AI agents safely observe, diagnose, and fix production issues: raw log access via SQL, health‑focused advisor checks, notebook‑based queries, fine‑grained permission controls, and real‑time Postgres pipelines to analytics destinations. These tools aim to give agents a controlled environment to test fixes before opening PRs.

  • Agents can query raw project logs via SQL using the new MCP tool, enabling deeper investigations.
  • Advisor now runs health checks across Data API, Auth, Storage, and Edge Functions, with results in a new Health tab.
  • Notebooks combine SQL/log queries with markdown notes and can be managed via the dashboard or CLI for agent‑driven analysis.
  • Scoped personal access tokens, enterprise‑managed auth, and MCP elicitations provide fine‑grained permission control and user confirmation before risky actions.

Engineers building automated agents or observability tooling on Supabase need safe, observable, and autonomous capabilities to act on production issues.

5/10
devopsobservabilitysecuritydatabasesagents

Related reading

  1. Supabase Select 2026 Recap

    Supabase announced a suite of new features at Select 2026, including native‑process local development, declarative schema files with pg‑delta migrations, a Compute platform for custom services, an MCP server with auth‑aware middleware, and scaling upgrades like Multigres HA and the OrioleDB storage engine. These changes aim to make Supabase more code‑first, observable, and ready for large‑scale p…

    Supabasesupabase.com4 min

  2. Build anything: Supabase from code, and an MCP server for your app

    Supabase announced new tools for agent-driven development, including native local Supabase instances, declarative schemas, and config-as-code. They also introduced Supabase Compute for long-running services and app-specific MCP servers for user agents to interact with applications.

    Supabasesupabase.com4 min

  3. Four minutes after midnight, Codex said the page was live

    OpenAI’s Codex agents can be turned into reliable teammates by wiring them into existing tooling (Slack, Linear, GitHub, etc.) and giving them validation steps like linters and CI. With context plugins, memories, and record‑and‑replay skills, agents can draft docs, monitor deployments, and even answer messages on a developer’s behalf.

    Renderrender.com9 min

  4. SQL Manager for PostgreSQL 7.0: meet the AI Assistant

    SQL Manager for PostgreSQL 7.0 adds an AI Assistant that can generate, explain, fix, and optimize SQL, produce migration scripts from schema diffs or business requirements, and lets users control how much schema is sent to the model. It supports multiple LLM providers and local Ollama deployments.

    PostgreSQLpostgresql.org1 minrelease

  5. pgAssistant 3.8.0 : continuous improvement loop for Postgres

    pgAssistant 3.8.0 expands from a tuning advisor to a continuous PostgreSQL improvement platform, adding a Collector that records historical workload and environment data. It lets teams run an Observe‑Diagnose‑Prioritize‑Plan‑Implement‑Measure loop, compare consecutive snapshots, and measure the impact of applied recommendations.

    PostgreSQLpostgresql.org1 minrelease

  6. Database for AI Agents: 5 Evaluation Criteria

    Databricks outlines five criteria for a production‑ready database for AI agents—branch‑per‑agent isolation, serverless scale‑to‑zero, hybrid search, ACID guarantees, and a unified platform that eliminates ETL lag—illustrating each with features of its Lakebase offering and brief customer anecdotes.

    Databricksdatabricks.com10 min