From Dev.to Community
Tech Articles
Curated developer articles, tutorials, and guides — auto-updated hourly
CortexFlowOct 16, 2026 • 7 min read
Your LLM Gateway Holds Every API Key. LiteLLM Let Any User Steal Them: CVE-2026-35029 Patch Guide
CVE-2026-35029 and CVE-2026-59823 let any LiteLLM user escalate to admin, run code, and steal every ...
#security#cve#litellm#aiagents
0 0
Travis Frisinger4d ago • 8 min read
Self-Healing Tests Are the Vendor Version of the Corrupted Signal
The 2026 self-healing wave sells an auto-repair mechanism for a test's locator when the app changes:...
#testdiscipline#vendoranalysis#aiagents#rewardsignals
1 0
Khriztian Moreno3d ago • 14 min read
Semantic markup for AI: turn your forms into WebMCP tools without JavaScript
In the first post in this series, every WebMCP tool was a JavaScript object: a name, a description, ...
#webmcp#aiagents#mcp#chromeai
3 0
Orvi Das3d ago • 7 min read
Feature Flags for AI Agents: Disable One Tool Without a Redeploy
Feature flags for AI agents: how to disable one tool in production without a redeploy, and why the f...
#featureflags#aiagents#agentsafety#killswitch
1 1
Orvi Das6d ago • 8 min read
AI Agent Rollback: Why the Saga Pattern Fails for Tool Calls
Compensating transactions can
#aiagents#sagapattern#rollback#compensatingtransactions
0 0
Mehdi MohseniOct 16, 2026 • 14 min read
Why Agents Need a Knowledge Base: The Gaps an LLM Can't Fill by Itself
When a team starts building an agent, the first version is very often only a model, a system prompt....
#rag#knowledgegraph#dotnet#aiagents
0 0
Khriztian Moreno3d ago • 12 min read
WebMCP — Why agents shouldn't have to guess how your UI works
You ask a browser agent to book the cheapest nonstop flight from Bogotá to Madrid. The agent takes a...
#webmcp#aiagents#mcp#chromeai
0 0
JeffOct 16, 2026 • 3 min read
The Agent Deleted the Comment That Explained Why the Code Looks Weird
When an agent refactors code, it routinely deletes comments that look like noise. The ones it drops ...
#aiagents#coding#refactoring#softwareengineering
0 0
Jeff1d ago • 4 min read
The agent wrote its own test input, watched it pass, and called the edge case closed
An agent fixes an edge case from a messy real input, then verifies the fix against a tidy synthetic ...
#aiagents#testing#contextengineering#workflow
0 0
JeffOct 16, 2026 • 2 min read
The Agent Wrote a Test That Mocks the Function Under Test
When an AI agent writes unit tests, the most common failure isn't weak assertions — it's mocking the...
#aiagents#testing#ci#coding
0 1
Jason Miller2d ago • 3 min read
Put Your AI Agent's Permissions in Postgres, Not the Prompt
Odds are good that somewhere in your company, a database connection string lives in an .env file,...
#apiauth#secrets#soc2#aiagents
0 0
JeffOct 17, 2026 • 3 min read
The Agent Converted the If/Else Chain to a Lookup Map and Dropped the Side Effect
When an AI agent collapses an if/else chain into a lookup map, it treats branches as data and can dr...
#aiagents#refactoring#coding#javascript
0 0
Jeff5d ago • 3 min read
The Agent Added a Retry Loop and Retried on the Auth Failure Forever
Agents add retry loops the way they add error handling: uniformly, without reading which failures ar...
#aiagents#reliability#coding#javascript
0 1
sk. saddam6d ago • 3 min read
Your fraud analyst sees rows. Fraud is a shape.
How we built CaseFile, a graph-walking investigation agent, in one hackathon day — and what it taugh...
#aiagents#graphdb#falkordb#hackathon
0 0
Jason MillerOct 16, 2026 • 3 min read
Your LLM API Keys Are Cash. The METR Breach Proves It.
The METR attacker spent three weeks inside a researcher's cloud instance and touched nothing...
#apiauth#secrets#aiagents
0 0
Zahid Hasan Tonmoy6d ago • 4 min read
AI Agent Autonomy Levels: A Small TypeScript Approval Gate
An agent with a delete tool and a loose prompt can read “clean up my old entries” as permission....
#ai#aiagents#typescript#beginners
0 2
Jeff1d ago • 4 min read
The agent silenced the flaky test instead of fixing the race, and the bug just moved
A flaky test fails intermittently. The agent reaches for the cheapest way to make it stop failing: r...
#aiagents#testing#debugging#workflow
0 0
Jeff2d ago • 3 min read
Two Parallel Agents Edited the Same File; the Merge Dropped One Quietly
Why parallel agent branches collide on a shared manifest, why a clean green merge hides a dropped ch...
#aiagents#concurrency#git#testing
1 1
Jeff1d ago • 4 min read
The agent fixed it in another worktree and tested the wrong checkout
When an agent edits one worktree but runs tests against the primary checkout, green reports a clean ...
#aiagents#git#testing#agentic
0 0
Jeff2d ago • 4 min read
The Agent Made the Exception Quiet Instead of Fixing It
Why an agent reaches for a broad swallow instead of fixing the root validation, why a green suite mi...
#aiagents#testing#errors#debugging
1 0
Jason Miller6d ago • 3 min read
Google's AI Found 500 XSS Bugs, and the Model Is the Least Interesting Part
Google turned an AI agent loose on its own web apps and it came back with more than 500 verified XSS...
#dast#aiagents
0 0
Jeff2d ago • 4 min read
The Agent Renamed the Symbol but Left the Old Name in the Error String
Why an agent renames an identifier cleanly across the symbol graph yet leaves the legacy name in err...
#aiagents#refactoring#debugging#verification
1 0
Emre Ferik4d ago • 8 min read
I built an AI agent factory to make 570 exercise visuals. Here's what each model got right and wrong.
Field notes from October 2026. Not a benchmark: one project, real logs, honest mistakes. I'm...
#ai#aiagents#llm#showdev
0 2
Jason Miller1d ago • 3 min read
Six Expired Domains Can Hijack Your AI Agents: Notes From a 15,465-Server MCP Audit
If your agents call MCP servers you don't operate, here is the attack that costs less than lunch. OX...
#apiauth#aiagents#supplychain#soc2
0 0