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
We fixed the worst prompt variant. It got better. That doesn't mean the fix worked.
Maya Andersson
Maya Andersson
Maya Andersson
Follow
Jul 3
We fixed the worst prompt variant. It got better. That doesn't mean the fix worked.
#
ai
#
programming
#
llm
#
analytics
Comments
2
 comments
9 min read
Evals for Agents: Scoring Task Success, Trajectory, and Human Review
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Evals for Agents: Scoring Task Success, Trajectory, and Human Review
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
8 min read
Per-Agent Cost and Token Attribution Straight From Your Traces
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Per-Agent Cost and Token Attribution Straight From Your Traces
#
ai
#
agents
#
observability
#
llm
Comments
Add Comment
7 min read
The 2 a.m. Runaway Loop: Detecting and Killing an Agent That Won't Stop
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
The 2 a.m. Runaway Loop: Detecting and Killing an Agent That Won't Stop
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
7 min read
Agent State Desync: Why Your Agent Forgets and How to Fix It
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Agent State Desync: Why Your Agent Forgets and How to Fix It
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
6 min read
Incident Response When Your Agent Is on Fire: A Runbook
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Incident Response When Your Agent Is on Fire: A Runbook
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
6 min read
Context Bloat in Long-Running Agents: What to Keep, Summarize, and Drop
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Context Bloat in Long-Running Agents: What to Keep, Summarize, and Drop
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
6 min read
The Agent Production-Readiness Checklist You Can Run Before Shipping
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
The Agent Production-Readiness Checklist You Can Run Before Shipping
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
7 min read
Planning and Decomposition for Agents: Structured Output Over Free-Form Reasoning
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Planning and Decomposition for Agents: Structured Output Over Free-Form Reasoning
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
6 min read
The ReAct Loop From Scratch: The Agent Baseline Before Any Framework
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
The ReAct Loop From Scratch: The Agent Baseline Before Any Framework
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
7 min read
Agent Memory Done Right: Short-Term, Long-Term, and the Scratchpad
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Agent Memory Done Right: Short-Term, Long-Term, and the Scratchpad
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
6 min read
Your First Tool-Calling Agent With No Framework, Just the Bare SDK
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Your First Tool-Calling Agent With No Framework, Just the Bare SDK
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
6 min read
Meta's Agents Rule of Two: A Practical Defense Against Prompt Injection
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Meta's Agents Rule of Two: A Practical Defense Against Prompt Injection
#
ai
#
agents
#
security
#
llm
Comments
Add Comment
6 min read
Designing Agent Tools: Schemas and Descriptions That Prevent Misfires
Gabriel Anhaia
Gabriel Anhaia
Gabriel Anhaia
Follow
Jul 4
Designing Agent Tools: Schemas and Descriptions That Prevent Misfires
#
ai
#
agents
#
llm
#
python
Comments
Add Comment
6 min read
Choosing the Right Scraping Interface for LLM Workflows
Anakin
Anakin
Anakin
Follow
Jun 4
Choosing the Right Scraping Interface for LLM Workflows
#
webscraping
#
llm
#
api
#
architecture
1
 reaction
Comments
Add Comment
4 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