AI Agents & Automation

Day 12: I took a week off from coding to audit 15 Android apps for accessibility. WhatsApp and Google apps are fully automatable. Local banking and government apps? Completely invisible. My AI agent is becoming an accessibility audit tool.

Run an enrollment agent from a school's admissions inbox

AI Governance — EU AI Act Compliance, Risk Assessment, and Audit Logging

🚀 Introducing Career Agents: An Open-Source Collection of AI-Powered Career Assistants

Stop Scrolling Your Agent's Logs. Debug It Like a Program.

Identity Is the New Perimeter: Why AI Agents Break Zero Trust

Implementing Zero-Trust Networking and Identity for Microsoft Foundry Agents

We deployed a LangChain agent for a client and it silently failed for two weeks. Here's what we built to make sure it never happens again.

Why AI agents need three types of memory (and how I built all of them)

What Six Arguing AI Agents Taught Me About Building One That Actually Works

Why your AI agent needs deterministic guardrails (and how to add one in a few lines)

Your AI agent is the most over-privileged account you own

Stratagems #6: Alex Walked Into an AI Compliance War Room. Every Director Watched the Dashboard. He Watched the Pipeline.

Why 88% of Agent Pilots Die: The Infrastructure Readiness Gap Nobody Talks About

The Reviewer Blessed the Bug: Why Agent-Written Code Needs Layered Review

Agentic AI Security: Risks, OWASP Agentic Top 10, and Defensive Patterns (2026)

How to Create an AI Agent using Vercel Eve

What a browser MCP snapshot actually costs (I measured it)

Where Sovereignty Begins

Your Next Teammate Won't Be Human. It'll Be an AI Agent.

Tokenizer Changes Can Break AI-Agent Budget Assumptions

I let an AI handle an outage. It invented a hack that never happened, then spiraled

Six Bugs Only a Live Model Could Teach Us

The Gap Every AI Gateway Misses: Why HTTP 200 Is Not a Correct Response

MCP vs API: Why Traditional APIs Are Failing AI Agents

Smart Node: the Self-Hosted AI Crew I've Been Building

Agent Evidence Levels (AEL): grading the evidence your AI agent leaves behind

The Agent Can Drive. You Still Need to Know the Route.

Solon 4.0 ReActAgent: A Practical Guide to Building AI Agents That Think and Act

I Didn’t Build an AI. I Built a Technician That Never Sleeps.

AI-Assisted AuthZ Review: Reading Permission Boundaries in Ory Kratos

FaroIQ: how I built a 9-agent pipeline for nonprofits with Azure AI Foundry

# Building MediAssist: An AI Health Agent with Persistent Memory Using Qwen + MongoDB

Why Framework Callbacks Fail to Stop AI Agent Financial Runaways

Now you can run opencode on termux :)

Open Knowledge Format (OKF): The Markdown Standard Your AI Agents Have Been Waiting For 📚

Generality Is Real (Within Your Modality)

Ignoring HITL is a massive technical risk: Human-in-the-Loop

Teaching AI Coding Agents How to Build Workflows with Skills and MCP

Text-to-SQL is still brittle. Snowflake's Cortex Sense is a new take.

Choosing the Right Tooling Layer for Your Agent

The Agent Tool-Calling Pattern

Vegas Amnesia: I turned Cognee's memory lifecycle into a detective game

How to Choose the Right Eval for an AI Agent

Building Structured Inter-Agent Communication: A Practical Guide

5x Agent Quotas, 5x the Trust Problem

ReWOO: plan every tool call up front, then call the model only twice

Is There a Claude Agent SDK for Ruby? Here's What to Use Instead