Skip to Content
Getting StartedIntroduction

Introduction

Morse AI is unified observability for the age of agents: one platform for your AI agents and the infrastructure they run on, correlated in a single trace. If you’re running an LLM framework tracer for agent behavior and a separate stack for infra metrics — stitching them together by hand when something breaks — Morse AI replaces that Frankenstack with one tool.

What “correlated in a single trace” means

Every agent run becomes a trace: an ordered record of every LLM call, tool call, database query, and HTTP request the run made. Spans are typed from the start — agent, llm, tool, http, db — so a slow run and the infra call that caused it show up in the same place, not two dashboards you have to cross-reference by hand.

What you get

  • Traces — the full run, span by span, filterable down to the cohort you check daily. See Traces.
  • Agents — the same runs, rolled up per agent. See Agents.
  • Cost — spend attributed down to the call that spent it. See Cost.
  • Reliability — error rates and failure patterns across runs. See Reliability.
  • Copilot — ask questions about a trace or a cohort directly, backed by the same data. See Copilot.

Outcomes — whether a run actually did the thing it was supposed to — are recorded alongside every trace, not sold as a separate headline feature.

Where to go next

  • New to Morse AI: start with the Quickstart — instrument one agent, verify a trace, and get to your dashboard.
  • Want the vocabulary first: see Concepts for trace, span, thread, and the typed-span model.
  • Quickstart — instrument your first agent and see a trace land.
  • Traces — the list every run shows up in.
Last updated on
Quickstart