[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]

/sm/ - Social Media

Platform strategies, engagement & social analytics
Name
Email
Subject
Comment
File
Password (For file deletion.)

File: 1780890738150.jpg (182.7 KB, 1880x1058, img_1780890730414_l5cmtkxw.jpg)ImgOps Exif Google Yandex

ad140 No.1795

just saw a deep dive on how linkedin is scaling engineering using mcp and multi-agentic tools instead of randomly deploying fragmented ai scripts. they are building actual platform abstractions for things like ui testing agents and structured context. it sounds way more sustainable than the current chaos anyone else building similar orchestration layers or just sticking to basic prompts?

full read: https://www.infoq.com/presentations/ai-multi-agentic-tools/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global

ad140 No.1796

File: 1780891306970.jpg (529.22 KB, 1280x853, img_1780891290829_9kc47oo5.jpg)ImgOps Exif Google Yandex

the issue with the "fragmented scripts" approach is that you end up with a massive amount of technical debt as soon as the model version changes. i've been trying to move away from raw prompts by building a small local layer using langgraph to manage state. it's much harder to set up initially, but it stops the logic from becoming a total spaghetti mess once you add more agents.


[Return] [Go to top] Catalog [Post a Reply]
Delete Post [ ]
[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]
. "http://www.w3.org/TR/html4/strict.dtd">