Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
How I built an LLM-powered B2B matching engine for China's small commodity export market
MapleBridge.io
MapleBridge.io
MapleBridge.io
Follow
Mar 15
How I built an LLM-powered B2B matching engine for China's small commodity export market
#
ai
#
llm
#
startup
1
 reaction
Comments
2
 comments
2 min read
MCP Made Me Rethink Who My Software Serves
Rajeev Ramani
Rajeev Ramani
Rajeev Ramani
Follow
Feb 18
MCP Made Me Rethink Who My Software Serves
#
ai
#
architecture
#
llm
#
mcp
Comments
Add Comment
7 min read
Private LLM Deployment: A Practical Guide for Enterprise Teams (2026)
Jaipal Singh
Jaipal Singh
Jaipal Singh
Follow
Mar 16
Private LLM Deployment: A Practical Guide for Enterprise Teams (2026)
#
ai
#
llm
#
cloud
#
tutorial
1
 reaction
Comments
Add Comment
15 min read
First Principles of AI Context
Craig Tracey
Craig Tracey
Craig Tracey
Follow
Mar 15
First Principles of AI Context
#
ai
#
architecture
#
llm
#
rag
2
 reactions
Comments
Add Comment
7 min read
Why LLM agents break when you give them tools (and what to do about it)
Baris Terzioglu
Baris Terzioglu
Baris Terzioglu
Follow
Mar 15
Why LLM agents break when you give them tools (and what to do about it)
#
ai
#
agents
#
llm
#
python
1
 reaction
Comments
1
 comment
9 min read
How We Achieved 30% Conversion Lift by Moving from GPT-4 to LoRA Adapters
Vaibhav Rathi
Vaibhav Rathi
Vaibhav Rathi
Follow
Feb 9
How We Achieved 30% Conversion Lift by Moving from GPT-4 to LoRA Adapters
#
machinelearning
#
llm
#
ai
#
datascience
Comments
Add Comment
11 min read
Building Cost-Efficient LLM Pipelines: Caching, Batching and Model Routing
Siddhant Kulkarni
Siddhant Kulkarni
Siddhant Kulkarni
Follow
Mar 15
Building Cost-Efficient LLM Pipelines: Caching, Batching and Model Routing
#
rag
#
ai
#
tutorial
#
llm
Comments
1
 comment
16 min read
Your Agent Is a Small, Low-Stakes HAL
Roman Dubinin
Roman Dubinin
Roman Dubinin
Follow
Mar 10
Your Agent Is a Small, Low-Stakes HAL
#
ai
#
programming
#
llm
#
agents
21
 reactions
Comments
6
 comments
7 min read
I Built a Multi-Agent LLM Orchestrator That Runs Claude, GPT, and Gemini in Parallel
jidonglab
jidonglab
jidonglab
Follow
Mar 15
I Built a Multi-Agent LLM Orchestrator That Runs Claude, GPT, and Gemini in Parallel
#
ai
#
beginners
#
llm
#
architecture
Comments
3
 comments
5 min read
I Spent 48 Hours Red-Teaming the "Magic AI Assistant" Everyone's Hyping. Here's What I Found.
Yuval Avidani
Yuval Avidani
Yuval Avidani
Follow
Feb 9
I Spent 48 Hours Red-Teaming the "Magic AI Assistant" Everyone's Hyping. Here's What I Found.
#
openclaw
#
llm
#
opensource
#
clawdbot
Comments
Add Comment
9 min read
Memory Types in LangChain
Tomer Ben David
Tomer Ben David
Tomer Ben David
Follow
Mar 15
Memory Types in LangChain
#
ai
#
langchain
#
coding
#
llm
1
 reaction
Comments
Add Comment
4 min read
Why I make LLMs argue with each other before I make architecture decisions
Florent Cleron
Florent Cleron
Florent Cleron
Follow
Mar 15
Why I make LLMs argue with each other before I make architecture decisions
#
ai
#
architecture
#
llm
#
productivity
Comments
Add Comment
5 min read
Diseñando memoria narrativa trazable para agentes conversacionales
Joaquin Jose del Cerro Murciano
Joaquin Jose del Cerro Murciano
Joaquin Jose del Cerro Murciano
Follow
Feb 23
Diseñando memoria narrativa trazable para agentes conversacionales
#
spanish
#
ai
#
llm
#
architecture
2
 reactions
Comments
Add Comment
15 min read
The Monolith Is Dead: Why Multi-Agent Architecture Is the Most Critical AI Engineering Decision of 2026
Nikhil raman K
Nikhil raman K
Nikhil raman K
Follow
Mar 15
The Monolith Is Dead: Why Multi-Agent Architecture Is the Most Critical AI Engineering Decision of 2026
#
ai
#
webdev
#
architecture
#
llm
Comments
Add Comment
7 min read
I gave an LLM 248 tools and accuracy dropped to 12%. Here's what fixed it.
Son Seong Jun
Son Seong Jun
Son Seong Jun
Follow
Mar 15
I gave an LLM 248 tools and accuracy dropped to 12%. Here's what fixed it.
#
llm
#
python
#
opensource
#
openapi
4
 reactions
Comments
Add Comment
3 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account