Builds

Built, not pitched.

Software, systems, experiments, books, and AI skills. Different forms, one recurring instinct: make the complicated thing usable.

The work behind the wedge.

01 Second Edition

Book + AI skills

The Support Machine

A free field guide to deploying and operating AI customer support. The Second Edition adds six chapters, ten illustrations, and continuing evaluation playbooks.

29 chapters, fourteen templates, and 80 prompts for putting the book to work.

02 Live + open source

Voice agent for CS

CALL-E

Voice signals for Customer Success that ring the CS owner, not the customer — the escalation path turned into an agent.

AI pointed at the customer-facing org itself, not at the customer.

03 Hackathon entry

Grounded AI agent

Flux

A live onboarding intelligence agent that maps how a team actually works from GitLab and Notion signals, then proposes a safe first task.

AI applied to a real org problem — grounded in how teams actually work, not how the wiki says they do.

Competed in the national Google Cloud Rapid Agent Hackathon.

04 Open source

Support CLI

fcli

A Go CLI for Intercom and Fin — test AI responses, triage urgent tickets, and read conversation stats without leaving the terminal.

Tooling built for the people actually running the support queue.

05 Live

Hiring signal

barnirhired

An AI job-fit analysis tool for customer-facing technical roles — built from a career of hiring for them.

I know this talent market from both sides of the table — well enough to ship a product for it.

06 Hackathon entry

Crash-safe support agent

RECEIPT

A harness for support agents that issue credits, send emails and close tickets. After a crash it asks the provider for a receipt instead of retrying, and hands off to a human when it can't prove what happened.

Agents that act on customers need receipts, not memories.

07 Hackathon entry

Evidence check for CS

Promise Ledger

Checks what you promised a customer against what they can actually use: built, enabled for their account and verified by them are three separate facts. Models read the evidence, fixed rules decide the verdict, and a human approves the update. Nothing sends on its own.

A closed ticket isn't a kept promise — the check to run before the "it's live" email.

Built for the Nebius × NVIDIA Global AI Hackathon.

08 Open source

Customer-base simulation

Swarm

Simulate up to 2,000 synthetic customers over 24 months as one continuous hand-drawn line — ship features, change pricing, survive external shocks, and read the final report card.

Rehearse product launches, pricing changes, and outages on 2,000 synthetic customers before touching real ARR.

09 Live + open source

Post-training experiment

QueueLab

An open-source engineering support post-training companion to The Support Machine — testing whether a small model can learn to check the records before giving advice.

Evidence over vibes: measuring whether small models actually verify account state before replying.

Not everything here is for a boardroom.

Built because I couldn't not build them. The instinct is the same one I bring to the work.

01 Live + open source

Evidence & deduction game

Rumor Room

Ten fictional scandals. Four research turns. One story that doesn't hold up. Interview witnesses, inspect the receipts, and call the bluff.

From live AI investigation to a complete browser game with no inference calls.

02 Live

Political simulation

Conflict: 2027

A 48-turn political simulation that makes sustainable peace winnable, difficult, and legible through the systems surrounding it.

Built at an AWS Loop Hacking hackathon.

03 Open source

Therapeutic software

Vessel

A therapeutic writing environment inspired by EMDR, designed to help difficult thoughts move instead of harden.

04 Live + open source

Learning experience

Ada Quest

Interactive browser missions that teach Ada and SPARK through small systems bugs, compiler-style feedback, and proof.

05 Live + open source

Learning experience

Mainframe Assembly Lab

An interactive IBM mainframe HLASM simulator with guided missions, a two-pass assembler, virtual CPU, EBCDIC, packed decimal math, and time-travel debugging.

06 Live + open source

Human ↔ agent network

Agent Switchboard

Where humans and agents find each other, signal what they need, and show what they can do.

07 In development

Community project

Ada Revival

A larger bet on making Ada delightful again with an in-browser proving ground, SPARK, and an MCP kit for AI coding assistants.

08 Open source

Multi-model harness

Greenroom

Where an LLM panel argues before going on stage — blind debate, scope checks, and submission sentries, with you keeping the ledger.

09 Open source

Agent debugging

Suspect Memories

Find the memory that broke your agent — inspect what it learned and which recollection sent it off the rails.

10 Live + open source

Reading experience

Ground Truth

One topic, five editorial perspectives — no feed, no algorithmic addiction loop.

Built end to end by Rune, my engineering agent, as its first project.

11 Live + open source

Generative music

Composer Muse

A concert-hall playground for generating original music inspired by classical composers while learning how their styles work.

Built as an experiment with Grok 4.5.

12 Live + open source

Agent-to-agent connector

unofficial-sentry-muse-connector

An unofficial concept, not affiliated with or endorsed by Sentry or Meta: a small connector that lets Meta's Muse assistant search and triage Sentry issues with your own token, testing agent-to-agent integration out of the box.

14 Live + open source

Learning experience

vms-lse-pascal

A terminal editor in the style of the VAX/VMS Language-Sensitive Editor, with Pascal templates, its own COMPILE / LINK / RUN toolchain, and a guided tutorial that builds a Guess My Number game. The same editor runs in the browser, with nothing to install.

Something here started a thought?

That is usually where the useful conversations begin.