Skip to content

Writing

Blog

Writing on production AI systems, LLM architecture, and AI agents.

Vibe coding PR review series: Kody and OpenRouter, by Mehdi Zare.

I tested whether AI PR reviews catch cleanup I never asked for

I ran 48 reviews with a free code model and Claude Opus 5.5 to test unrequested cleanup. Both caught the reorder, but some findings invented requirements.

7 min read
My vibe coding PR review system: Kody and OpenRouter, by Mehdi Zare.
AI Engineering

How I set up PR reviews for vibe coding with Kody and OpenRouter

My Kody and OpenRouter setup for reviewing AI-written code: BYOK pricing, model routing, real dashboard screenshots, and what free-model fallbacks can and cannot do.

7 min read
A cloud outline with a small square node and a stack of three server blocks with a node on top, joined by a two-way arrow.
Agents & Automation

Grok Bot vs OpenClaw

Hosted Grok versus self-hosted OpenClaw for beginners who want to automate work. Both sides, no pick — start free, upgrade when a wall shows up.

8 min read
Two app windows side by side, one holding a speech bubble and the other a grid of blocks, separated by a dashed line.
AI Engineering

Grok Bot vs Claude Desktop

A both-sides compare of conversational Grok and Claude Desktop for beginners who want to automate work. No pick, no eval table.

9 min read
A simple desktop app window with a cable and plug connecting it to a small square block.
AI Engineering

Claude Desktop for Beginners

Install Claude Desktop, start a first chat, add a novice MCP connection, and keep secrets out of the prompt. Not Claude Code.

9 min read
Four vertical bars of different heights, the tallest in warm tan, connected by a bracket to a small three-by-three evaluation grid.
LLMs in Production

Grok 4.6 costs, limits, and evals vs the models I actually pay for

Grok Build is the coding-agent product. Grok 4.6 is the model that powers it. Official evals, API costs, and limits — copied from xAI, not rounded.

11 min read
A loop of four icons connected by arrows: a speech bubble, a magnifying glass, a pencil and a folder highlighted in warm tan.
AI Engineering

How I Actually Use Grok Bot

I use conversational Grok as a thinking, research-preparation, and drafting tool—not as an authority. Here is the six-step workflow I actually follow, including how I verify claims and protect sensitive data.

11 min read
Scattered dots passing through three layered triangular panels and converging on a single tan diamond.
AI Engineering

How AI Works: From Data to Decisions — A Developer's Introduction to AI Systems

A developer's guide to how AI works end to end: defining the decision, preparing data, training or selecting a model, running inference, applying deterministic product controls, and monitoring real outcomes in production.

12 min read
A segmented bridge between a small platform and a larger one, with one loose tan block resting below the span.
AI Engineering

Why Most AI Projects Die Before Production (And It's Not a Tech Problem)

The most-cited AI failure stat is made up, but the real numbers are worse, and the reason is almost never the technology.

5 min read