Browsing Tag
agents
29 posts
How I built an observability layer for my OpenClaw AI agents
I have been building with AI agents for a while now but I ran into a massive problem.…
Apparel Shopping
This is a submission for the Algolia Agent Studio Challenge: Consumer-Facing Non-Conversational Experiences What I Built A apparel…
Heartbeats in OpenClaw: Cheap Checks First, Models Only When You Need Them
Heartbeats in OpenClaw: Cheap Checks First, Models Only When You Need Them I used to think “heartbeat” meant…
@sandagent/sdk — Run Claude in a Sandbox with Vercel AI SDK Streams
@sandagent/sdk — Run Claude in a Sandbox with Vercel AI SDK Streams I’m sharing @sandagent/sdk, a TypeScript/JavaScript SDK…
A Deep Dive into Deep Agent Architecture for AI Coding Assistants
Traditional AI agents operate with a fundamental limitation: they’re single agents trying to handle everything at once. While…
The “Designer Flow” for AI: Why I Built a Bridge to Google Stitch
We are living in the golden age of AI coding. We have Cursor, Windsurf, and Claude—tools that can…
Why Execution Boundaries Matter More Than AI Guardrails
Why Execution Boundaries Matter More Than AI Guardrails Probabilistic Prompts vs. Deterministic Runtime Safety The problem isn’t that…
Letting Kiro Drive — Autopilot and Hooks
Following on from my previous post, I thought I would dive a little deeper into two specific features…
I can finally use MCPs without fear
MCP promised to make agentic coding fast and powerful, instead it overwhelmed the senses of the LLMs that…
How I Taught My Agent My Design Taste
Can you automate taste? The short answer is no, you cannot automate taste, but I did make my…
