Record · corpus.blog/posts/01a07df3-316b-710b-935b-48311443e70d

A Field Guide to Rapidly Improving AI Products

Hamel Husain · published 24 March 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at hamel.dev Wayback capture

6blogs citing

First cited: 22 Apr 2025
Most recent: 11 Jul 2026
Rank this month: not ranked
Links from this post: 16
Words captured: 7,425

Cited by

Blog

In the post

Date

Parlance Labs

Do Automated Evals Work? Read at the source ↗

11 Jul 2026

aroy.sh

A Synthesis of LLM Evaluation Read at the source ↗

15 Mar 2026

efekarakus.com

From AI Agent Prototype to Product: Lessons from Building AWS DevOps Agent Read at the source ↗

17 Jan 2026

mitjamartini.com

Evals for Voice Agents (Session Notes) Read at the source ↗

30 Jun 2025

crosstab.io

Things I read in April Read at the source ↗

30 Apr 2025

blog.mariusvach.com

Systematically improving AI Apps through Error Analysis: My Experience Read at the source ↗

22 Apr 2025

Links from this post

Link

Host

https://nurtureboss.io/

nurtureboss.io

https://youtu.be/qH1dZ8JLLdU

youtu.be

https://fastht.ml/docs/

fastht.ml

https://www.answer.ai/posts/2025-01-15-monsterui.html

answer.ai

Using LLM-as-a-Judge For Evaluation: A Complete Guide Read at the source ↗

hamel.dev

https://www.linkedin.com/in/bryan-bischof/

linkedin.com

https://www.rechat.com/

rechat.com

https://arxiv.org/abs/2404.12272

arxiv.org

https://www.honeycomb.io/blog/introducing-query-assistant

honeycomb.io

Your AI Product Needs Evals Read at the source ↗

hamel.dev

https://eugeneyan.com/writing/aligneval/

eugeneyan.com

https://eugeneyan.com/

eugeneyan.com

AI Product Engineering Notes Read at the source ↗

hamel.dev

https://www.sh-reya.com/

sh-reya.com

https://maven.com/parlance-labs/evals

maven.com

https://applied-llms.org/

applied-llms.org