alihan/12-factor-agents
1
0
Fork 0
mirror of https://github.com/humanlayer/12-factor-agents.git synced 2025-08-20 18:59:53 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update brief-history-of-software.md

Browse Source
This commit is contained in:
Dex
2025-07-02 13:52:58 -05:00
committed by GitHub
parent ff01dbc9a2
commit f070b6d535
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
content/brief-history-of-software.md
View File

@@ -99,6 +99,10 @@ I'll even perhaps posit something I've heard in passing quite a bit, and that YO
Most builders I've talked to **pushed the "tool calling loop" idea to the side** when they realized that anything more than 10-20 turns becomes a big mess that the LLM can't recover from. Even if the agent gets it right 90% of the time, that's miles away from "good enough to put in customer hands". Can you imagine a web app that crashed on 10% of page loads?
**Update 2025-06-09** - I really like how [@swyx](https://x.com/swyx/status/1932125643384455237) put this:
<a href="https://x.com/swyx/status/1932125643384455237"><img width="593" alt="Screenshot 2025-07-02 at 11 50 50 AM" src="https://github.com/user-attachments/assets/c7d94042-e4b9-4b87-87fd-55c7ff94bb3b" /></a>
### What actually works - micro agents
One thing that I **have** seen in the wild quite a bit is taking the agent pattern and sprinkling it into a broader more deterministic DAG.