---
title: Agent Process Observability
type: concept
tags: [agentic-bpm, observability, process-mining, llm-agents, debugging]
sources: ["[[sources/2025-fournier-agentic-ai-process-observability]]"]
created: 2026-04-15
updated: 2026-04-15
---

# Agent Process Observability

The discipline of inferring actionable insight into the inner workings of an Agentic AI system by analyzing the inputs, outputs, and **execution trajectories** as they flow between agents ([[sources/2025-fournier-agentic-ai-process-observability]]). Borrows terminology from the Agentops line of work (Dong et al. 2024, *(referenced-not-ingested)*).

## Core idea
Treat each timestamped **tool invocation by an agent** as an event. A run of the agent system becomes a trace; a batch of runs becomes a process event log amenable to [[concepts/process-discovery]] and causal process discovery.

## Key distinction
- **Intended variability** — decision points the developer explicitly specified.
- **Unintended variability** — accidental variation points emerging from under-specified prompts, tools, or roles.

Distinguishing the two is the main diagnostic task. Fournier et al. attack it with LLM-based static analysis, matching a derived gateway rule statement against the agent specification source text.

## Why it matters
LLM-backed agents are non-deterministic even with temperature=0 (Ouyang et al. 2025). Without dedicated observability, silent breaches of responsibility, loophole tool usage, and specification drift go undetected.

## Related
[[concepts/agentic-bpm]] · [[concepts/behavioral-variability]] · [[concepts/causal-process-discovery]] · [[concepts/explainability-apm]] · [[concepts/self-modification]]