---
title: "Trajectory (agent)"
description: "The sequence of plans, tool calls and memory operations that led an agent to an effect."
canonical: https://aigovernanceengineer.com/glossary/trajectory-agent
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-25
---

# Trajectory (agent)

The sequence of plans, tool calls and memory operations that led an agent to an effect. Agents are evaluated on their trajectories as well as their final outputs, because a right result reached through a tool the agent should never have held is still a failure.

- Developed in: [ch. 23, What makes an agent a governance object](https://aigovernanceengineer.com/bok/governing-agents#what-makes-an-agent-a-governance-object)
- Chapters: [ch. 14, Development](https://aigovernanceengineer.com/bok/governing-development) · [ch. 23, AI Agents](https://aigovernanceengineer.com/bok/governing-agents)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-trajectory-agent

## Sources

Defined by this Body of Knowledge: the section it is developed in is the source.