Feature · /ai-detector
AI Detector
当数据库变慢,Obsfly 不只告诉你「是什么」,还告诉你「怎么办」。
In one line
基于 Claude 的查询重写、索引推荐、执行计划解读 (BYOC 下可自带 LLM)。
What you get
- Query rewrite suggestions with predicted speedup
- Index recommendations with cost / benefit / write-amplification estimate
- Config recommendations grounded in your actual workload (not generic 'tune shared_buffers' advice)
- Natural-language diagnostic: ask 'why is this query slow' and get a plan-level walkthrough
- Plan narrator: human-readable explanation of every node in an EXPLAIN output
- BYOC and Sovereign customers can bring their own LLM endpoint (Claude / Bedrock / Azure OpenAI / self-hosted)
FAQ
Does my query text leave my VPC?+
On SaaS, yes (with redaction). On BYOC and Sovereign, no — the AI engine in your data plane talks to either the Obsfly-hosted LLM with redacted context, or your own LLM endpoint. Per-workspace toggle.
Will it ever auto-apply changes?+
No. The AI Detector is advisory by design.
Related reading
AI
Anomaly detection on database metrics: why thresholds fail and what works
A walk through forecast bands, change-point detection, multi-variate anomaly, and the seasonality math that makes 'p99 over 200ms' the wrong alert by default — with the Postgres example that broke our last threshold.
Postgres
Postgres slow queries: 12 causes and how to find each one
A field-tested playbook for diagnosing a slow Postgres query in production — from missing indexes to plan flips to bloated tables — with the SQL to find each cause and the fix.
BYOC
Why regulated SaaS can't use Datadog DBM — and the BYOC fix
Walking through the architecture of a BYOC observability deployment: where data lives, what crosses the boundary, and how to satisfy SOC2 / HIPAA / GDPR without giving up the UX.