Between roles, I didn't wait. I designed, built, and shipped a system that runs my work for me: a self-maintaining knowledge base, a fleet of custom AI agents, a live public product, and automations that run while I sleep.
Every number above is generated, maintained, and queried by the system itself, and version-controlled like real software.
Most people use AI like a search box: one question, one answer, forgotten. I built the opposite: a persistent operating layer with memory, structure, and a job to do. This is how I think about systems and adoption. The same instinct I brought to scaling partner success.
A structured library of 1,900+ interlinked notes, plus 6,000+ documents auto-ingested and summarized. The system doesn't just store; it compiles raw input into clean, cross-referenced knowledge, then lints it for gaps. The same pattern Andrej Karpathy published in 2026.
How it works →17+ custom skills, each a purpose-built AI worker: a morning-briefing analyst, a five-person advisory council, a research synthesizer, a job-application strategist. Invoked with a single command.
Scheduled jobs fire on their own: daily reading gets synthesized and filed, a weekly review compiles itself, daily life capture runs in the background. No prompting required.
Full git version history, a privacy firewall, an audit log on every action, and a single-source-of-truth design so nothing silently drifts. Built with the discipline of production software.
Not slideware. Live systems, in production, that I and other people use today. The throughline of my career: turn capability into something a real user actually adopts.
A public AI chatbot that talks to recruiters and visitors as me. The moment someone shares their company it runs a live web search and makes every answer company-aware; a classifier scores sentiment and fit in real time; every lead is logged with topics and follow-up priority. Keys are server-side, it auto-deploys from a private repo, and it was security-hardened after surviving a real abuse incident.
callconnor.com →How it works →A local mission-control dashboard that auto-starts at login. Live AI-usage and spend telemetry, one-click launches for every agent, the project queue, calendar, quick capture, and an embedded editor that edits, commits, and deploys callconnor.com in a single click.
runs locallyHow it works →A fully private AI running on my own hardware. Local models in Docker with their own chat UI. It shares the exact same tool servers and memory as the cloud AI, so sensitive work can run entirely on-device, offline.
runs locallyHow it works →Separate from the daily system: a purpose-built project, taken from concept to a running tool to see one idea all the way through.
A purpose-built Partner Success console for a brokerage's set of accounts. Every account is a structured file system (success plan, stakeholders, decisions, health), and a transparent engine scores each one Healthy, At Risk, or Critical, then reads that score in context, so a ramping account and an established one near renewal get different verdicts, the way mature CS platforms score health. Each comes with the single play that moves it, and clicking Start on any task opens an AI session already loaded with that account's full context. It runs today, ready to point at real partners.
runs locallyHow it works →Information flows in from everywhere, gets distilled and connected, and comes back out as briefings, decisions, and finished work.
The flow above is the overview. Each piece, the brain, the knowledge graph, the local AI, the privacy boundary, the command center, has a full architecture deep-dive: how it is built and why.
Explore the full architecture →Each is a repeatable agent with a defined job, inputs, and output format. Productized workflows, not one-off prompts.
Pulls calendar, reminders, email, job pipeline, and yesterday's loose ends into one start-of-day report, then drafts the day's note.
Convenes a five-member advisory board (Career, Innovation, Risk, Finance, Marketing) plus a Socratic chairman to pressure-test any real decision.
Compiles the week into a structured retrospective and runs a system health check. Fires itself every Friday, unattended.
Scans a week of inbox and sorts every message into action / job-search / follow-up / FYI / noise so nothing important slips.
Searches the web, filters signal from hype, and delivers a tight briefing on capability shifts that actually matter to my stack.
Pulls an idea from two unrelated fields and cross-pollinates them against what I'm working on. Engineered serendipity.
Runs a half-formed idea through research, a steel-man, and an adversarial case-against, then converges it into a sharp position brief built to be shared, not just filed.
Pulls from the AI-news pipeline and fresh web research to draft a signal-over-hype newsletter issue, staged as a ready-to-send platform draft.
Reads a job posting, assesses fit against my profile, and drafts a tailored application work-up automatically.
Produces sales-grade intel on a target company (stage, culture, partnerships motion, recent news, people), scored against my profile for fit.
Researches the interviewers and the company, picks the right stories to tell, and builds a tight prep sheet plus the questions to ask back.
Researches a hiring manager, recruiter, or referral, then drafts a short, specific, in-voice message tied to one target role and built to get a reply.
Synthesizes a pre-call briefing for any account in the Account OS: health, stakeholders, open escalations, goals, and the one play that moves it.
Takes locally-extracted saved videos (caption, transcript, on-screen text), fact-checks each claim against the web, and scores it for accuracy and relevance to my stack.
Audits deferred and parked threads so nothing promising quietly rots in the backlog.
Writes a structured record of every working session, appends new tasks, and commits the whole system to version history.
A daily unattended pipeline: clipped articles and podcasts are summarized, filed, archived, and committed every morning. No input from me.
Plus several more maintenance and utility agents that run in the background, from knowledge-graph upkeep to capture-inbox sweeps to transcript pipelines, keeping the whole system clean and current.
The difference between "playing with AI" and a system you can stake work on is the unglamorous infrastructure. This has it, because shipping something people rely on is the part I've always cared about.
The entire system is a git repository with full history. Every change to every note and skill is tracked and reversible, backed up to a private remote.
Private journaling is walled off from the cloud AI entirely and processed by a model running locally on my own machine. Sensitive data never leaves the device.
How it works →Every tool the AI touches is logged, with guardrail hooks that can block risky actions. The system watches itself.
Skills are defined once and referenced everywhere, so the system can't silently drift out of sync. A real engineering pattern, applied to personal tooling.
It remembers context, preferences, and history across every conversation; it gets more useful over time instead of starting from zero.
The system keeps a written map of its own architecture and a changelog, re-confirmed on a schedule, so it stays understandable as it grows.
The system is actively under construction. What's next is as ambitious as what already runs.
A multi-pass pipeline (research, steelman, adversarial case-against, converge) that turns a half-baked idea into a publishable position document. Separates an idea's merit from my ability to personally build it, so a strong idea I can't ship still becomes a sharp document worth sharing.
An allowlist-driven snapshot of the knowledge base, derivative-only, publishes to a private GitHub repo on demand. The artifact people get when they want to see how I actually think: not slides, the raw working corpus minus the private bits.
A dedicated always-on Mac mini to host the long-running services (podcast ingestion, persistent assistant host, knowledge-graph MCP) so the laptop can sleep without breaking the system. Architecture decided, hardware pending.
A periodic publication built on the idea-brief pipeline's output. Sharable positions on the topics I've thought hardest about. Each brief doubles as portfolio and audience: no double work.
Apple Watch trends sanitized into a thin derivative the local AI can read (sleep, exertion, recovery) so its suggestions can factor in whether I'm sharp or fried. Strict boundary: locally-derived summaries only, never raw health data, never leaves the machine.
The same architecture this runs on, an AI that incrementally builds and maintains a persistent, interlinked knowledge base, is the pattern Andrej Karpathy published in 2026.
Not a chatbot. Not a hobby. Operator-built infrastructure that compounds: evidence of how I'd approach the next role from day one.