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
What happens when you tell an autonomous agent it's wrong
Ross Douglas
Ross Douglas
Ross Douglas
Follow
Feb 19
What happens when you tell an autonomous agent it's wrong
#
ai
#
opensource
#
architecture
#
llm
9
 reactions
Comments
7
 comments
6 min read
How to QA Test Your AI Agent: A Practical Playbook for 2026
Tahseen Rahman
Tahseen Rahman
Tahseen Rahman
Follow
Feb 22
How to QA Test Your AI Agent: A Practical Playbook for 2026
#
ai
#
llm
#
testing
#
devops
1
 reaction
Comments
Add Comment
7 min read
LLM-as-a-Judge: Automated Scoring and Reliability vs. Human Evaluation
Lamhot Siagian
Lamhot Siagian
Lamhot Siagian
Follow
Feb 22
LLM-as-a-Judge: Automated Scoring and Reliability vs. Human Evaluation
#
ai
#
llm
#
rag
#
testing
2
 reactions
Comments
Add Comment
6 min read
Evals Aren’t a One-Time Report: Build a Living Test Suite That Ships With Every Release.
Lamhot Siagian
Lamhot Siagian
Lamhot Siagian
Follow
Feb 22
Evals Aren’t a One-Time Report: Build a Living Test Suite That Ships With Every Release.
#
llm
#
ai
#
evaluation
2
 reactions
Comments
1
 comment
6 min read
The Two-Brain Architecture: Decoupling Recall from Learning
Osamudiamen Osazuwa
Osamudiamen Osazuwa
Osamudiamen Osazuwa
Follow
Jan 18
The Two-Brain Architecture: Decoupling Recall from Learning
#
llm
#
agents
#
vectordatabase
Comments
Add Comment
2 min read
Why Your AI Agent Should Use a Speech API Instead of LLM Inference
Fabio Augusto Suizu
Fabio Augusto Suizu
Fabio Augusto Suizu
Follow
Feb 21
Why Your AI Agent Should Use a Speech API Instead of LLM Inference
#
ai
#
llm
#
api
#
machinelearning
Comments
1
 comment
6 min read
The Time Our Voice AI Couldn’t Understand “Yes” (And the Cultural Lesson That Fixed It)
FARHAN HABIB FARAZ
FARHAN HABIB FARAZ
FARHAN HABIB FARAZ
Follow
Jan 19
The Time Our Voice AI Couldn’t Understand “Yes” (And the Cultural Lesson That Fixed It)
#
ai
#
voiceai
#
promptengineering
#
llm
Comments
Add Comment
4 min read
The Claude Code Information Hierarchy
Christina Norman
Christina Norman
Christina Norman
Follow
Feb 21
The Claude Code Information Hierarchy
#
claudecode
#
ai
#
llm
#
productivity
Comments
1
 comment
2 min read
Você já ouviu falar do meme do monstro Shoggoth?
Lhayana Vieira
Lhayana Vieira
Lhayana Vieira
Follow
Jan 17
Você já ouviu falar do meme do monstro Shoggoth?
#
ai
#
llm
#
machinelearning
Comments
Add Comment
2 min read
Five Non-Negotiable Principles for Controllable AI Systems
yuer
yuer
yuer
Follow
Jan 19
Five Non-Negotiable Principles for Controllable AI Systems
#
ai
#
architecture
#
llm
#
systemdesign
Comments
Add Comment
3 min read
Mastering Cache Hits in Claude Code
Christina Norman
Christina Norman
Christina Norman
Follow
Feb 21
Mastering Cache Hits in Claude Code
#
claudecode
#
ai
#
llm
#
productivity
4
 reactions
Comments
Add Comment
16 min read
Dynamically Generated Languages vs MCP Servers
djuleayo
djuleayo
djuleayo
Follow
Jan 18
Dynamically Generated Languages vs MCP Servers
#
ai
#
architecture
#
llm
#
mcp
Comments
Add Comment
7 min read
What is an LLM Gateway?
smakosh
smakosh
smakosh
Follow
Feb 21
What is an LLM Gateway?
#
llm
#
ai
#
architecture
#
devops
Comments
Add Comment
4 min read
How LLM Memory Actually Works in Production Systems
Dextra Labs
Dextra Labs
Dextra Labs
Follow
Feb 21
How LLM Memory Actually Works in Production Systems
#
ai
#
machinelearning
#
llm
#
rag
1
 reaction
Comments
Add Comment
4 min read
The Knowledge Base That Lied to 10,000 Customers (And How We Caught It)
FARHAN HABIB FARAZ
FARHAN HABIB FARAZ
FARHAN HABIB FARAZ
Follow
Jan 18
The Knowledge Base That Lied to 10,000 Customers (And How We Caught It)
#
rag
#
llm
#
ai
#
knowledgebase
Comments
Add Comment
6 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