AI Engineering Enablement
Making engineering teams actually faster with AI.
I'm Jay Narang — an engineering leader writing up what I'm building and learning as AI tooling lands in the enterprise: the tools, the working patterns, and the governance that survives contact with a large regulated organisation. Patterns and lessons, never internal specifics.
Publish pipeline
# draft in obsidian → push → deploy
$ git push origin main
→ astro build · static html
→ deploy cloudflare pages
✓ live in 24s
$ git push origin main
→ astro build · static html
→ deploy cloudflare pages
✓ live in 24s
cloudflare · deployed github-actions · green tailscale · mesh
Homelab
Infrastructure judgment, kept honest.
Writing about
Notes on shipping AI, at the pattern level.
- AI solution design, from first principles A 12-module learning path through strategy, architecture, evaluation, and security — the arc of a working thread, filled out where it stayed shallow. AI enablement Guide · · 4 parts
- Choosing the right Claude model — Opus, Sonnet, or Haiku? The question I get asked most: which model should this run on? A decision framework for matching model tier to task complexity, volume, and cost. AI enablement Essay · · 6 min
- An AI coding glossary — the vocabulary that makes teams effective Half the confusion in AI tooling adoption is vocabulary. The terms I find myself explaining most, from tokens and context windows to handoffs and grilling. AI enablement Guide · · 8 min
- Two minutes to a better Claude Code status line The default status line tells you almost nothing. ccstatusline shows real-time token usage, context health, and git state — configured in under two minutes. Tooling Note · · 3 min