From Dev.to Community
Tech Articles
Curated developer articles, tutorials, and guides — auto-updated hourly
sunnydachsSep 21, 2026 • 4 min read
What happens when enterprise requirements hit Strands, LangGraph, and CrewAI - 45 runs measured
What happens when enterprise requirements - human approval gates, audit trails, structured output -....
#agents#ai#llm#python
7 17
Sneha M KSep 19, 2026 • 5 min read
MCP vs. API Explained: Do We Still Need APIs After MCP?
No. MCP doesn't replace APIs — it sits on top of them. An MCP server is, almost always, a thin...
#ai#api#llm#mcp
13 13
Debashish GhosalSep 24, 2026 • 5 min read
7 Agent Eval Mistakes That Cost Me Weeks (And the One-Line Fixes That Ended Them)
You've been there. You run the eval, the number comes back, and something about it doesn't sit...
#ai#evaluation#llm#programming
24 5
Mika FlowersSep 25, 2026 • 8 min read
Can Two Local AI Agents Build an App Without Me? I Gave Them 6 Rounds to Find Out
I have very, very limited experience with AI agents. I've used AI heavily while building software,....
#ai#llm#showdev#python
9 5
Debashish GhosalSep 22, 2026 • 5 min read
I Cut 2,490 Agent Test Runs to 206 and Kept the Same Coverage
The full matrix was 83 agents × 30 scenarios = 2,490 runs. Each one a real LLM call, 30–80 seconds.....
#ai#programming#testing#llm
16 4
Debashish GhosalSep 25, 2026 • 5 min read
I Trusted My Agent Demos for Years. Then I Built a Gate That Says No.
Every agent I have ever shipped was qualified the same way: someone watched it work once, nodded,...
#ai#llm#controlplane#agents
18 7
TokenLatSep 22, 2026 • 4 min read
Your agent's cost problem isn't the model. It's the steps you never measured.
A few weeks back I watched an agentic pipeline burn a month of budget in three days. The instinct...
#ai#llm#architecture#agents
10 9
DevOps DailySep 21, 2026 • 11 min read
We Measured the 200x Claim, and Got It Wrong Twice First
Last week we wrote about the classification problem hiding in your LLM bill, and about how to read a...
#ai#llm#benchmarking#jev
11 6
Enrique BruzualSep 22, 2026 • 9 min read
RAG ranking is not the same as judging with Jev
How I went from "Trust me, bro" to "boomer with receipts" using Jev By separating...
#rag#testing#llm#ai
2 4
Arsh SharmaSep 21, 2026 • 7 min read
How monday.com Runs Agent Evals Against Real Dependencies: Webinar Recap
An agent eval suite's outcome can only be trustworthy if it's operating in an environment similar to...
#ai#testing#llm#agents
25 2
Harsh RavalSep 23, 2026 • 12 min read
I Compared 5 LLM Gateway Tools for Real-World Production Use
When an LLM application starts handling real users, calling a model API is usually easy. The problem...
#ai#llm#devops#discuss
28 11
anassBldSep 23, 2026 • 4 min read
How We Cut 70% of Multi-Agent Token Waste by Replacing Supervisor LLMs with Typed State Machines
Why supervisor LLM agents create infinite retry loops and silent token inflation, and how to replace...
#agents#ai#architecture#llm
10 24
Manohar HalappaSep 20, 2026 • 8 min read
Architecting for AI-Native Platforms: RAG, LLM Orchestration, and Agentic Patterns
AI adoption in an enterprise SaaS platform is rarely about adding an LLM API and calling it...
#ai#architecture#llm#rag
3 5
Naveen AlavilliSep 25, 2026 • 6 min read
I Built Nabsun: An Open-Source AI Browser That Works in Your Real Tabs
You have three documentation tabs open, a form half-filled, and the account you need already signed....
#opensource#ai#agents#llm
3 0
Kiell TampubolonSep 22, 2026 • 5 min read
The LiteLLM Supply Chain Backdoor: What 3 Hours Means for Your AI Agent Gateway
On March 24, 2026, two backdoored versions of litellm sat on PyPI. Version 1.82.7 went up at 10:39.....
#security#ai#llm#infosec
6 2
Hardcore EngineerSep 19, 2026 • 4 min read
The Negative Test That Passed for the Wrong Reason
Last february we swapped our embedding model from text-embedding-3-small to bge-large, thinking...
#debugging#llm#rag#testing
4 13
Alex MercedSep 21, 2026 • 29 min read
Fast Classification Models, LLMs, and the Apache Iceberg Lakehouse
Open the bill for any team that has put a large language model into a data pipeline and look at what...
#ai#data#llm#machinelearning
1 1
Etka OzerSep 23, 2026 • 4 min read
I made retrieval 4x better and my agent got worse
Recall@1 went from 13% to 50%. Recall@5 from 13% to 80%. Over the same week, the number of question...
#ai#llm#agents#debugging
2 11
Seenivasa RamaduraiSep 21, 2026 • 9 min read
Stop Sending Every Decision to an LLM: Code vs. Jev vs. Claude
Why bounded semantic decisions may become an important layer in agentic AI architecture. .....
#agents#ai#architecture#llm
4 2
jackSep 24, 2026 • 5 min read
AI cost modelling: measure your own token counts, the published table was off by 2.3x
We resell image generation, so we have to know what a generation costs us before we can price it....
#ai#architecture#api#llm
2 1
Onkar DeokateSep 23, 2026 • 5 min read
Opus 5.5 Made Cache Reads 60% Cheaper. I Redid the Math on My Text-to-SQL Architecture
TL;DR: Claude Opus 5.5 came out yesterday with cache reads at $0.20 per million tokens, 60% cheaper....
#ai#llm#architecture#postgres
1 4
MCPulseSep 21, 2026 • 6 min read
Readers took my MCP schema study apart. Here's what they found.
I published a survey of 4,749 public MCP server schemas a few weeks ago. The headline was that 17.7%...
#ai#mcp#llm#devtools
3 2
Pierre-Laurent MedoriSep 22, 2026 • 8 min read
How do you stop an LLM from leaking API keys in the code it writes? Default to secret
On July 22 I typed a one-line prompt on a test app: a widget built on a well-known REST API, the kin...
#ai#security#llm#softwareengineering
10 9
JohnSep 21, 2026 • 5 min read
Your LLM Telemetry Table Does Not Have One Denominator
A routed LLM telemetry table can put several incompatible populations under one model label. The com...
#ai#testing#analytics#llm
2 10