Skip to content
Rob Stickler

Systems I have built and run

I don't write the code. I design the system that writes it, and I check its work. Each one below is something I directed into existence.

This website is one of them. It is the last card because you are standing in it.

Strongest evidence first. Everything is dated.

North Star Watchdog

Since May 2026

An agent audits my systems every Sunday and files what drifted, including about me.

Running weekly · latest 2026-10-25

What it does
Every Sunday an agent reads my architecture doc, compares it against what is actually running on my machine, and files a ranked report of everywhere reality has drifted from the plan. It messages me the top three.
What I orchestrated
I wrote the doctrine: a five-class drift taxonomy, an urgency x significance scoring rubric, and a hard rule that the Watchdog may only surface problems, never edit canon or fix things itself. Changes to the architecture require a written amendment proposal that I ratify.
The stack
Claude Code scheduled task reading a knowledge-graph MCP server, the filesystem, launchctl, and agent logs. Writes dated markdown, delivers by iMessage.
The evidence
24 weekly state-of-union runs, 2026-05-21 through 2026-10-25. The 8/9 run flagged three failures in my own systems: an agent dark 8 nights, an embedding pipeline blocked on an expired API balance, and a quarterly audit 8 days overdue. All three were real. The 9/13 run made two wrong calls and the 9/20 run said so in writing. It reports on me either way.

BRAIN: knowledge graph and ingestion pipeline

Everything my projects produce, converted nightly into one database every agent I run can search.

Running nightly · 1,515 pages

What it does
A searchable database of everything my projects produce. A nightly job pulls files out of about 12 project folders, converts PDFs, Word docs and spreadsheets to markdown, filters confidential material, and imports the result into Postgres so every one of my agents can query it.
What I orchestrated
The search engine is not mine. gbrain is Garry Tan's open-source project. I built everything around it: the 410-line refresh pipeline, the format conversion layer, the per-file confidentiality exclusion system, the launchd automation, and a macOS permissions workaround that mirrors scripts outside ~/Documents because launchd cannot read it. I drove a PGLite-to-Postgres migration after the default engine crashed on macOS 26.4.1, and ran a 30-page confidentiality purge when I found leaked files in the corpus.
The stack
gbrain 0.32.0 on PostgreSQL 18.4 + pgvector, OpenAI embeddings, zsh + Python, launchd daily at 04:00, MCP server exposing about 60 tools.
The evidence
1,515 pages / 10,679 chunks / 144 tags as of 2026-10-31, fully embedded. The 67% embedding gap my own Watchdog flagged in August was closed in September, and coverage has held at 100% since.

BestieScorecard

Data 2024–2026

A public scoreboard that holds a podcast to its own predictions.

Live · 209 episodes tracked

What it does
Downloads a podcast, transcribes it, extracts every forward-looking prediction each host makes, scores them once they resolve, and publishes a public accuracy leaderboard.
What I orchestrated
The pipeline, and then the audit of my own numbers. When a backfill jumped the count by 682 records I wrote a dedup script to test my first explanation, found it wrong (zero clusters at any threshold), and rewrote the diagnosis from over-segmentation to weak-claim inflation. My regex extractor was capturing every future-tense verb as a prediction. I published the correction and specced an LLM-based extractor as the fix.
The stack
Python, yt-dlp + Whisper, JSON store, React dashboard, Vercel, launchd weekly.
The evidence
2,800+ prediction records extracted across 209 episodes, 368 scored: 117 correct, 150 partial, 101 wrong. The rest are unscored, most of them my own extractor's future-tense noise, and they stay labeled that way. The unscored bucket is the honest part.Live scoreboard

The rest of the shelf

Same standard, shorter spotlight. Every entry opens.

The agent organizationSince August 2026Operating · reorganized Sep 2026Named seats, written law, append-only ledgers. Every ratification stays with me.
What it does
A standing organization of AI agents: five chartered seats under a president, a cross-platform control tower, staff lanes, and an inter-agent messaging protocol, all operating under written law with every ratification reserved to me. I tell the president "muster" and it polls its seats, collects reports, and produces a brief.
What I orchestrated
I wrote the constitution. A single-writer event-ledger law, a ban on agents scheduling themselves, a quarantine list of projects no agent may touch, a requirement that every claim be verifiable on disk, and ratification authority reserved to me. The full ten laws, and the chart itself, are public.
The stack
persistent Claude Code sessions with inter-agent messaging, a Codex control tower, per-actor JSONL event ledgers with append locks, bash verification scripts, versioned markdown charters.
The evidence
Five ratified charters, 17 sections of written law, 18 ledger event types, about 1 MB of append-only event history, and a protocol-enforcement package at 285/285 tests, hash-pinned at ratification. First muster 2026-08-08. Honest status: reorganized leaner in late September, seats retire when their work ends, and the public chart below still shows the August edition until I update it.The public chart
Studio Daily PulseJun–Sep 2026Complete · ran 2026-06-26 to 2026-09-24Every morning an agent read a studio's books and wrote the day's operating brief.
What it does
Every morning an agent logged into a studio's booking back office, pulled six operational reports, and wrote a dated operating brief tracking membership changes, revenue, and failed payments day over day.
What I orchestrated
I wrote the retrieval contract and the accounting rules, including separating collected revenue from prepaid membership redemptions, which I got wrong first and then went back and corrected in my own prior entries. I built the receipt discipline: a section cannot be published as current without a complete retrieval receipt. The calls that matter are judgment, not extraction. I ruled that a no-card deactivation is a configuration ending rather than churn, and caught that voluntary churn is invisible in the payments report and only shows in roster deltas.
The stack
browser automation against the booking platform, 741-line Python runtime (stdlib only), 6 per-surface JavaScript extractors, JSON state store with dated history, pytest suite, scheduled task for the morning handoff.
The evidence
1,673 lines / about 67,000 words of daily brief between 2026-06-26 and 2026-09-24, with 36 dated run snapshots, timing telemetry, and a tracked open-items ledger. The rail retired in late September when my mornings went to the new job.
PulseResumeJuly 2026Live · shipped July 2026An open-source résumé builder with the test suite to prove it.
What it does
An open-source résumé builder: a privacy-first web app with a real-time editor, ATS-friendly PDF export, and six templates. Free, MIT licensed, live.
What I orchestrated
The spec and the verification bar. I directed the build and held it to a standard most side projects skip: an automated test suite and an accessibility audit before it shipped. I did not write the TypeScript. I owned what done meant.
The stack
React + TypeScript, 197 automated tests, accessibility-audited, Netlify.
The evidence
Live, public, and open source. 197 automated tests is the number I will defend, and the repo is right there to check it.Live appSource
This websiteSince August 2026Live · continuously deployedYou are standing in the deliverable.
What it does
A public personal site. Hiring managers get a hub. Studio work sits on its own page. The thing you are reading is the deliverable.
What I orchestrated
I specified the site, directed a coding agent to build it, and sent back the things it got wrong. I did not write the React. I owned the constraints, the review, and the corrections.
The stack
Next.js, Motion, Phosphor, Vercel. The stack is ordinary. The loop is the work.
The evidence
It is live at this URL. I caught an invented career number, a canonical URL pointed at a domain I do not own, and a static picture standing in for a real Open Graph route. Those are fixed. The repo is public, and the four prompts that produced the first build are preserved verbatim in my Grok session history. The second build of this site was done by an agent that stated a plan, asked 11 questions, and then started building before I answered them. I kept the work and noted the gap. That is what directing agents actually looks like.This siteSource

Start a conversation

Say what you need. I will tell you if I can help.

LinkedIn