AI Agent Squad for Ops: One Complex Request, Multiple Agents in Action

Complex incidents: 5 tabs, 30 minutes of stitching

2am alert: “Why is checkout slowing down?” You need P99, slow traces, root cause, and an incident report.

The old way: Grafana → Jaeger → topology → hand-written summary. Charts everywhere, root cause nowhere — 20–30 minutes per round.

Screenshot: hopping across systems, no evidence chain

Pain point: Monitoring gives data, not conclusions. Every tool is a separate hunt.

DataBuff: one goal, an AI squad wires the evidence

Open-source AI Native OTel APM. OTel ingest + Doris storage + multi-agent troubleshooting.

In one line: orchestrate an AI squad to turn metrics, traces, and topology into an incident-ready report.

Screenshot: Ingest → Doris → Platform

Screenshot: global topology — agents judge blast radius

Up and running in 5 minutes

curl -fsSL https://databuff.ai/databuff/ai-apm-install.sh | bash

Screenshot: one command install, Web UI URL in output

Open http://localhost:27403 (admin / Databuff@123)

Screenshot: traffic-light service health overview

Settings → AI model — add your LLM API key:

Screenshot: natural-language troubleshooting after API key setup

Demo data: curl -fsSL https://databuff.ai/databuff/ai-apm-demo-install.sh | bash

Back to §1: multi-agent joint ops

Drop the §1 request into the AI chat — all 5 screenshots below are from one conversation (live demo).

①

State the goal — P99, traces, root cause, report in one message.

Screenshot: full incident goal in one prompt

②

Brain dispatches — dispatchExpertTask to metrics + inspection experts.

Screenshot: concurrent dispatch to metrics + inspection

③

Smart query — breaks down the 240ms entry span.

Screenshot: trace latency breakdown — 240ms entry

④

Health inspection — topology + slow traces + metrics to find the bottleneck.

Screenshot: inspect queryTraceList → queryMetricData

⑤

Deliver summary — remediation + incident report.

Screenshot: P0 actions + brain-merged report

vs §1: 5 tabs, 30 minutes → one message, root-cause report in minutes.

From manual stitching to commanding an AI squad

No more five browser tabs. Data stays local; code is open and auditable.

- **Module** — What you get - **📊 APM** — Topology, P99, slow-trace drill-down - **🤖 AI squad** — Multi-agent queries, synthesized reports - **🔌 OTel** — Unified trace / metric / log storage

⭐ Deploy your ops AI squad in 5 minutes

curl -fsSL https://databuff.ai/databuff/ai-apm-install.sh | bash

Try: “Analyze why checkout slowed down and draft an incident report.”

View on GitHub →