DEV Community

sunnydachs profile picture

sunnydachs

I enjoy building things for fun and exploring new technologies.

Location Japan Joined Joined on  Personal website https://github.com/sunnydachs github website
I changed a tool's schema four ways and watched three agent frameworks break differently — 36 runs measured

I changed a tool's schema four ways and watched three agent frameworks break differently — 36 runs measured

Comments 1
5 min read

Want to connect with sunnydachs?

Create an account to connect with sunnydachs. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
AI answers are easy to get but expensive to read — a CLI that filters them down

AI answers are easy to get but expensive to read — a CLI that filters them down

1
Comments
3 min read
Do agents survive a crash, and why does an LLM retry execute the same side effect twice? 34 runs measured

Do agents survive a crash, and why does an LLM retry execute the same side effect twice? 34 runs measured

1
Comments 3
4 min read
What happens when enterprise requirements hit Strands, LangGraph, and CrewAI - 45 runs measured

Real-world benchmarks reveal hidden framework bugs

What happens when enterprise requirements hit Strands, LangGraph, and CrewAI - 45 runs measured

7
Picked as gem Comments 17
4 min read
I built the same agent in Strands, LangGraph, and CrewAI — and recorded every LLM call to see how they actually differ

I built the same agent in Strands, LangGraph, and CrewAI — and recorded every LLM call to see how they actually differ

2
Comments 2
4 min read
Your GDScript arrays are slower than you think? — I built a CLI that detects the pitfalls and benchmarks them

Your GDScript arrays are slower than you think? — I built a CLI that detects the pitfalls and benchmarks them

1
Comments
4 min read
Your OpenAPI spec is a contract. Nobody is checking it. I built a CLI that detects spec↔code drift with zero dependencies.

Your OpenAPI spec is a contract. Nobody is checking it. I built a CLI that detects spec↔code drift with zero dependencies.

1
Comments 2
4 min read
The tracking plan said "implemented". The dashboard says otherwise. I built a CLI that detects plan↔code drift using only AST.

The tracking plan said "implemented". The dashboard says otherwise. I built a CLI that detects plan↔code drift using only AST.

1
Comments
3 min read
Your README code examples are silently lying — I built a CLI to detect documentation drift using only AST, no LLM

Your README code examples are silently lying — I built a CLI to detect documentation drift using only AST, no LLM

2
Comments
3 min read
Audit your Excel pivot tables before they break — a read-only CLI with zero dependencies

Audit your Excel pivot tables before they break — a read-only CLI with zero dependencies

2
Comments 5
3 min read
I automated Dependabot PR cleanup — and drew a hard line on what NOT to automate

I automated Dependabot PR cleanup — and drew a hard line on what NOT to automate

1
Comments
4 min read
loading...