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
Prompt Caching: What Belongs in the Cacheable Prefix, What Kills Hit Rate
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Prompt Caching: What Belongs in the Cacheable Prefix, What Kills Hit Rate
#
llm
#
prompt
#
ai
#
performance
Comments
Add Comment
8 min read
HyDE, Multi-Query, Decomposition: Which Query Rewrite Actually Moves Recall?
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
HyDE, Multi-Query, Decomposition: Which Query Rewrite Actually Moves Recall?
#
rag
#
ai
#
llm
#
benchmark
Comments
Add Comment
10 min read
Your P99 Latency Lies. Streaming Users Feel TTFT.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Your P99 Latency Lies. Streaming Users Feel TTFT.
#
llm
#
observability
#
performance
#
ai
Comments
Add Comment
8 min read
Sub-Agents vs One Big Agent: 4 Signals That Decide It
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Sub-Agents vs One Big Agent: 4 Signals That Decide It
#
ai
#
llm
#
agents
#
architecture
Comments
Add Comment
9 min read
Stop Keying Agent Replay on Tool Names. Use Fingerprints.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Stop Keying Agent Replay on Tool Names. Use Fingerprints.
#
ai
#
llm
#
agents
#
testing
Comments
Add Comment
8 min read
Stop Using JSON Mode for Structured Output. XML Tags Win 4 of 5 Cases.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Stop Using JSON Mode for Structured Output. XML Tags Win 4 of 5 Cases.
#
llm
#
prompt
#
ai
#
python
Comments
Add Comment
7 min read
Eval-Driven Canary: Shipping Prompt Changes Behind a Quality Gate
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Eval-Driven Canary: Shipping Prompt Changes Behind a Quality Gate
#
llm
#
devops
#
cicd
#
ai
Comments
Add Comment
9 min read
Few-Shot Examples Are Eating Your Tokens. Here's the Cull Test.
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Few-Shot Examples Are Eating Your Tokens. Here's the Cull Test.
#
llm
#
ai
#
prompt
#
testing
Comments
Add Comment
8 min read
3 Dashboards Every LLM Team Needs: Cost, Quality, Latency, Wired End-to-End
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
3 Dashboards Every LLM Team Needs: Cost, Quality, Latency, Wired End-to-End
#
observability
#
llm
#
grafana
#
monitoring
Comments
Add Comment
10 min read
The 3 RAG Citation Patterns: One Regulators Accept, One Users Read, One Nobody Should Ship
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
The 3 RAG Citation Patterns: One Regulators Accept, One Users Read, One Nobody Should Ship
#
rag
#
ai
#
llm
#
architecture
Comments
Add Comment
10 min read
Goal Completion Verification: The Step 90% of Agents Skip
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Goal Completion Verification: The Step 90% of Agents Skip
#
ai
#
llm
#
agents
#
reliability
Comments
Add Comment
9 min read
Self-Consistency at N=5 With Sonnet Beats One Opus Call on 3 Task Types
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
May 23
Self-Consistency at N=5 With Sonnet Beats One Opus Call on 3 Task Types
#
llm
#
ai
#
python
#
benchmark
Comments
Add Comment
8 min read
Diffusion Language Models: How NVIDIA Nemotron-Labs Diffusion Shatters the Autoregressive Speed Ceiling
Manoranjan Rajguru
Manoranjan Rajguru
Manoranjan Rajguru
Follow
May 23
Diffusion Language Models: How NVIDIA Nemotron-Labs Diffusion Shatters the Autoregressive Speed Ceiling
#
ai
#
llm
#
nvidia
#
machinelearning
Comments
Add Comment
18 min read
Best AI Agent Security & Guardrails Tools in 2026: LLM Guard vs NeMo vs Guardrails AI
Agdex AI
Agdex AI
Agdex AI
Follow
May 23
Best AI Agent Security & Guardrails Tools in 2026: LLM Guard vs NeMo vs Guardrails AI
#
aiagents
#
llm
#
security
#
webdev
1
 reaction
Comments
2
 comments
3 min read
Built a Predictive Incident Response Agent with LLMs and Vector Memory
Ayodhya Krishna Teja
Ayodhya Krishna Teja
Ayodhya Krishna Teja
Follow
Apr 19
Built a Predictive Incident Response Agent with LLMs and Vector Memory
#
agents
#
llm
#
rag
#
sre
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