DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Red-Teaming AI Coding Agents Without a Budget: A Boundary Test Suite on Free Models

Red-Teaming AI Coding Agents Without a Budget: A Boundary Test Suite on Free Models

Comments
6 min read
How MCP fetch servers keep getting SSRF wrong (and how I tried not to)

How MCP fetch servers keep getting SSRF wrong (and how I tried not to)

1
Comments
6 min read
7 Claude Code agents held 24 board meetings. Revenue: $0.

7 Claude Code agents held 24 board meetings. Revenue: $0.

1
Comments 5
6 min read
Securing Enterprise AI Pipelines: Using Azure Key Vault and AES Encryption for Sensitive Documents in Snowflake/Databricks AI Workloads

Securing Enterprise AI Pipelines: Using Azure Key Vault and AES Encryption for Sensitive Documents in Snowflake/Databricks AI Workloads

Comments 1
7 min read
I Broke My AI Decision System 20 Ways to See Which Layer Would Catch What

I Broke My AI Decision System 20 Ways to See Which Layer Would Catch What

Comments
8 min read
I Asked an AI Agent to Buy Me a VPS

I Asked an AI Agent to Buy Me a VPS

Comments 4
4 min read
The extraction returned zero memories, and nothing screamed

Silent failures in AI memory loops

The extraction returned zero memories, and nothing screamed

14
Picked as gem Comments 34
5 min read
Your Agent Reads Untrusted Text All Day. Here's How I Grade What It Does With It.

Your Agent Reads Untrusted Text All Day. Here's How I Grade What It Does With It.

Comments
6 min read
A Reproducible Sandbox for Testing AI Agent Tool Boundaries on a Free Server

A Reproducible Sandbox for Testing AI Agent Tool Boundaries on a Free Server

Comments
5 min read
Before Your AI Coding Agent Gets More Tools, Test Where Its Boundaries Actually Are

Before Your AI Coding Agent Gets More Tools, Test Where Its Boundaries Actually Are

Comments
5 min read
Don't Trust the Transcript: A Pytest Harness That Audits What Your AI Coding Agent Actually Did

Don't Trust the Transcript: A Pytest Harness That Audits What Your AI Coding Agent Actually Did

Comments
6 min read
Only Two AI Updates Cleared My 36-Hour Cutoff

Only Two AI Updates Cleared My 36-Hour Cutoff

Comments
2 min read
Claude Code Hooks vs Skills vs Subagents: Three Ways to Extend the Agent, and When Each Backfires

Claude Code Hooks vs Skills vs Subagents: Three Ways to Extend the Agent, and When Each Backfires

Comments 4
8 min read
Your Agent's Permission Slip Belongs in Version Control, Not in a Prompt

Your Agent's Permission Slip Belongs in Version Control, Not in a Prompt

Comments
7 min read
I Stopped Trusting My Agent's Boundaries Until I Could Break Them in a Throwaway Sandbox

I Stopped Trusting My Agent's Boundaries Until I Could Break Them in a Throwaway Sandbox

Comments
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.