# AI Tech Magic
> Field notes on why AI agent pilots stall and how to fix them: spec-engineering, evals, guardrails, and production lessons from real engagements.
Public Ghost content for AI and LLM tooling. Use `/llms-full.txt` for consolidated page and post context.
Append `.md` to any post or page URL to get the content in Markdown (for example, `/example-post.md`).

## Pages
- [About this site](https://blog.aitechmagic.com/about.md) - AI Tech Magic is an independent publication launched in February 2026 by Virginia Kalesic. If you subscribe today, you'll get full access to the website as well as email newsletters about new content when it's available. Your subscription makes this site possible, and allows AI Tech Magic to contin…

## Posts
- [The $45K School That Wrote a Better Spec Than Most AI Pilots](https://blog.aitechmagic.com/alpha-schools-agent-spec.md) - Alpha Schools bounded its AI to two hours a day and paid humans $100K for judgment. That's a spec, and it's the discipline most agent pilots skip.
- [Prompt Engineering Is Over. Specification Is the Skill That Replaces It.](https://blog.aitechmagic.com/specification-engineering.md) - "Prompt engineering is dead," everyone says — and then no one names what comes next. Here's the discipline that does: deciding what a system should know, do, and be before you write a single prompt.
- [Why 88% of AI Agent Pilots Never Reach Production](https://blog.aitechmagic.com/why-ai-agent-pilots-fail.md) - The AI pilot failure rate is real — but the cause isn't the model. A practitioner's take on why agent pilots die, and the three traits of the ones that ship.

## Optional
- [RSS Feed](https://blog.aitechmagic.com/rss/)
- [Sitemap](https://blog.aitechmagic.com/sitemap.xml)
- [Full content of pages and posts](https://blog.aitechmagic.com/llms-full.txt)