// agentbrief.dev

What working engineers are building with Claude, MCP, and the agent stack.

No analyst-speak. No "industry experts agree." Just shippable patterns from production work — written by an engineer who's running this stuff in real systems.

tue brief · fri deep-dive · free · no tracking

// what you get

tue

Tuesday brief

5–7 stories from the AI engineering stack. Quick takes from a working engineer. ~600 words, ~3 min read.

fri

Friday deep-dive

One long-form story per week — the one that matters. ~1,200 words. Names tradeoffs. Takes a side.

voice

Anti-slop voice

No "significant breakthrough." No "industry experts agree." Real opinions from someone shipping production code with Claude.

kit

Shippable patterns

Code, configs, and agent workflows you can lift. The starter kit ships them embedded in real working examples.

// from the log

all posts →
  1. Real screenshots, not stock slop — headless source-page capture

    Stock footage screams content farm. Capturing the actual source — the repo, the docs, the release notes — with a headless browser makes the output look like it came from someone who read the thing.

  2. Record your own voice — forced alignment instead of paying for TTS

    Synthetic narration is the fastest tell that something is AI slop. Narrate in your own voice and still automate the timing — forced alignment maps your audio to the script for frame-accurate captions, free.

  3. What "production" actually means for an LLM pipeline

    The demo works on your laptop. Production is everything the demo skipped — retries, idempotency, output validation, cost tracking, and what to do when the model returns garbage at 3am.

// start here

Start with the newsletter

Free. Twice a week. Engineer-to-engineer. No tracking gimmicks, unsubscribe with one click.

Subscribe →