---
title: "Discussion on \"My Reflection Loop Made Things Worse. My Evaluation Framework Showed Me Why.\" | Hashnode"
description: "Discussion on \"My Reflection Loop Made Things Worse. My Evaluation Framework Showed Me Why.\". How building an evaluation framework before the agent revealed failures I never would have caught manually."
url: "https://hashnode.com/posts/my-reflection-loop-made-things-worse-my-evaluation-framework-showed-me-why/6a775e207ab63cddbf340c1d"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [My Reflection Loop Made Things Worse. My Evaluation Framework Showed Me Why.](https://shivambhardwaj.hashnode.dev/my-reflection-loop-made-things-worse-my-evaluation-framework-showed-me-why?utm_source=hashnode&utm_medium=feed)

How building an evaluation framework before the agent revealed failures I never would have caught manually.

Aug 8 · 11 min read · shivambhardwaj.hashnode.dev  
Read the article

-   [#ai-agents](https://hashnode.com/tag/ai-agents)
-   [#ai-evaluation](https://hashnode.com/tag/ai-evaluation)
-   [#llms](https://hashnode.com/tag/llms)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#langgraph](https://hashnode.com/tag/langgraph)

## Written by

[Shivam Bhardwaj](https://hashnode.com/@shivmbhrdwj)

@shivmbhrdwj

  
[View profile](https://hashnode.com/@shivmbhrdwj)

Building evaluation infrastructure for AI agents. Writing about what breaks

## Responses

Markdown supported · ⌘↵ to post

No responses yet.