miniu + abcodex · I built the system that reads the operators I'd rather be reading.

Here's the honest version. I bookmark too much. I read too little. So I built a daemon that reads 70 named operators for me every morning at 07:00 IST, tests the ideas in a sandbox by 08:30, emails me a verdict trail, and pushes the survivors to codex.iamkesava.com the same day. The shelf is now a pipeline. The pipeline ships. Private on my Mac Mini, public on the open web. This is the consulting product, run on myself first.

What it was

Every PMM seat I held had the same gap. Smart operators were publishing the answers. Nobody on the team had time to read them, test them against our context, and ship the survivors into the operating cadence. The shelf of bookmarks kept growing. The work kept reverting to first instincts.

The diff

Before: a folder of saved links, a weekly intent to read them, a quarterly guilt that nothing got tested. The smart operator's idea died on the shelf.

After: a daemon that reads the shelf for me at 07:00 IST, drafts and sandbox-tests candidate ideas at 08:30, surfaces a verdict trail by email, and pushes the survivors public the same day. The shelf is a pipeline. The pipeline ships.

What it looks like

What I actually did

1. Built the operator pulse. 70 named operators across 15 lanes (PMM, GTM, SEO, AEO, performance marketing, inbound, outbound, product GTM, pricing, prompt engineering, agent frameworks, AI-native marketing org, creator marketing, humanizing AI copy, evals). The lane structure surfaces blind spots fast. Daily 07:00 IST scheduler task in miniu writes raw quotes to disk.
2. Built the AI digest. A second sub-Claude reads the pulse, finds candidate patterns, runs Tier A actions in a per-day sandbox (install + test a tool, draft a real artifact, propose a new skill), writes verdicts.json with a trajectory per candidate.
3. Built the sandbox gate. Tier A autonomous. Tier B (live config) and Tier C (judgment) surface only. I reply +, -, later, or ? to the morning email. The poller updates state every 30 min.
4. Built the public publish. abcodex ingest script reads the digest, strips internal references, validates against schema, runs the full pipeline (validate, stage, build-index, build-static, build-og, build-feeds), commits and pushes. GitHub Pages serves codex.iamkesava.com.
5. Wired self-evolution. LEARN every 15 min after every Claude Code session. MAINTAIN at 03:00 IST. CONSOLIDATE inside maintain, Sonnet rolls all memory into principles.md. DEBRIEF pushes work-domain learnings to the shared team substrate. Four dimensions, one runtime.

What stayed honest

The 1350-page count is from the build pipeline output, self-reported. The 70 operators and 15 lanes are countable in data/ai-digest/goals.yaml. The four self-evolution dimensions are in nanoclaw/src/self-evolve.ts. The public site is the easiest to verify: open codex.iamkesava.com, read today's daily, click into the patterns, check the operator citations. If the system stops shipping, the daily file stops appearing. The proof is the cadence.

What it does not do: write outbound DMs, approve its own promotions, or touch live config without me. The gates are deliberate. A research scan that auto-publishes is a fabrication engine.

What it became, in substrate

• routines/operator-pulse-daily. The named-operator scan that pre-stages quotes for the morning digest.
• routines/ai-digest-daily. The sandbox-gated promotion loop.
• skills/sandbox-promote. Tier A autonomous. Tier B and C surface-only.
• skills/digest-ingest. Strip internal frames, validate against schema, publish.
• patterns/loss-leading-adoption-via-public-scan. Run the research engine for yourself, ship the survivors public, the right buyers find you reading from the same shelf.

Why this is in the portfolio

This is what the consulting client buys. Not slides about AI-native practice. Not a deck about the flywheel. The working system that ingests their expert operators, tests candidates against their context in a sandbox, and ships polished output to their team on a daily cadence. Substrate is the open-source skeleton. miniu plus abcodex is the proof I run it on myself first, in public, before I install it for anyone else.