Jason Liu
jxnl.co · Personal blog · on HN since 2024
Jason Liu is an independent consultant who writes about RAG systems, context engineering and AI coding agents.
What HN saysHN commenters link his post on subagents as a way to keep the main agent's context clean, and his RAG posts, which draw on consulting work.
26HN people shared it
6linked it in comments
31stories submitted
740story points
4 months agolast shared
2024people per year2026
Most-shared posts
- 1Predictions for the Future of RAG4 people · 7 points · first shared 2024 · 1 comments on HN
- 2How to build a terrible RAG system3 people · 12 points · first shared 2024 · 1 comments on HN
- 3Advice to young people, the lies I tell myself2 people · 157 points · first shared 2024 · 62 comments on HN
- 4How to use codex to get the most out of it2 people · 6 points · first shared 2026 · discussion on HN
- 5Best Tools for Indie Tech Consultants2 people · 3 points · first shared 2024 · discussion on HN
- 6Context Engineering: Rapid Agent Prototyping – Jason Liu2 people · 1 points · first shared 2025 · discussion on HN
- 7Context engineering slash commands subagents2 people · first shared 2025
- 8Services2 people · first shared 2024
- 9Cautionary tale on using Chase bank for indie business1 people · 295 points · first shared 2024 · 263 comments on HN
- 10Systematically Improving Your RAG1 people · 176 points · first shared 2024 · 53 comments on HN
- 11Losing My Hands1 people · 61 points · first shared 2024 · 75 comments on HN
- 12Everything I Learned from AI Consulting1 people · 5 points · first shared 2024 · 1 comments on HN
- 13RAG Anti-Patterns1 people · 2 points · first shared 2025 · discussion on HN
- 14How to Be Data Illiterate (and How to Avoid Them)1 people · 2 points · first shared 2024 · discussion on HN
- 15Implementing Naturalistic Dialogue in AI Companions1 people · 2 points · first shared 2024 · discussion on HN
What HN people wrote when they linked it
redhale · 2025-10-12
Subagents are a critical feature that GH Copilot still lacks. They allow your main agent to use another agent as a tool, meaning the main agent's context doesn't get nearly as polluted. Good read on the benefits of this pattern: https://jxnl.co/writing/2025/08/29/context-engineering-slash-commands-…
CharlesW · 2025-09-13
> Subagents do not work well for coding at all
Subagents can work very well, especially for larger projects. Based on this statement, I think you're experiencing how I felt in my early experience with them, and that your mental model for how to use them effectively is still embryonic.
I've found that the primary benefit for subagents is context/focus management. For example, I'm doing auth using Stytch. What I absolutely don't want to do is load https://stytch.com/docs/llms.txt and instructions for leveraging it in my CLAUDE.md. But it's perfect for my auth agent, and the quality of the output for auth-related tasks is far higher as a result.
A recommended read: https://jxnl.co/writing/2025/08/29/context-engineering-slash-commands-…
eduction · 2024-08-23
Also why is there a post dated 2025? https://jxnl.co/writing/2025/06/15/my-self-reflection-on-success-and-g…
jxnlco · 2024-05-22
check out the other rag stuff https://jxnl.co/writing/category/rag/
all based on consulting calls and advisory work (i sell the implementation so sorry i don't post one click deploys)
hamelsmu · 2024-06-02
Hi, Hamel here. I'm one of the co-authors. I'm an independent consultant and not all clients allow me to talk about their work.
However, I have two that do, which I've discussed in the article. These are two production use cases that I have supported (which again, are explicitly mentioned in the article):
1. https://www.honeycomb.io/blog/introducing-query-assistant
2. https://www.youtube.com/watch?v=B_DMMlDuJB0
Other co-authors have worked on significant bodies of work:
Bryan Bischoff lead the creation of Magic in Hex: https://www.latent.space/p/bryan-bischof
Jason Liu created the most popular OSS libraries for structured data called instructor https://github.com/jxnl/instructor, and works with some of the leading companies in the space like Limitless and Raycast (https://jxnl.co/services/#current-and-past-clients)
Eugene Yan works with LLMs extensively at Amazon and uses that to inform his writing: https://eugeneyan.com/writing/ (However he isn't allowed to share specifics about Amazon)
I believe you might find these worth looking at.
mloncode · 2024-06-02
Hi, Hamel here. I'm one of the co-authors. I'm an independent consultant and not all clients allow me to talk about their work.
However, I have two that do, which I've discussed in the article. These are two production use cases that I have supported (which again, are explicitly mentioned in the article):
1. https://www.honeycomb.io/blog/introducing-query-assistant
2. https://www.youtube.com/watch?v=B_DMMlDuJB0
Other co-authors have worked on significant bodies of work:
Bryan Bischoff lead the creation of Magic in Hex: https://www.latent.space/p/bryan-bischof
Jason Liu created the most popular OSS libraries for structured data called instructor https://github.com/jxnl/instructor, and works with some of the leading companies in the space like Limitless and Raycast (https://jxnl.co/services/#current-and-past-clients)
Eugene Yan works with LLMs extensively at Amazon and uses that to inform his writing: https://eugeneyan.com/writing/ (However he isn't allowed to share specifics about Amazon)
I believe you might find these worth looking at.