Software that takes a real job off someone's desk, shows its reasoning so a human can check it, and gets better every time it's corrected. Running in production, on their own domains, with the tests to prove they hold.
Three linked sites for production optimization and Proof-of-Value work: a candidate brief, a working demo on public New Mexico well data, and the playbook for running it with an operator.
36 Delaware Basin wells from public NM OCD data. Each well gets its own Arps decline curve; the gap to actual is split into availability, operating, design and reservoir causes and priced. 425 bbl/d of gap found, about 200 bbl/d recoverable.
Production Solutions Engineer: each duty matched to evidence, the field-to-software career line, and how I would run a 30-day Proof-of-Value.
A sample 30-day proposal for a fictional operator, an article on what AI agents can and can't do about downtime, and a 30-60-90 day plan.
Twelve years split between the rig floor and the codebase. Each site below takes the same career and answers a different kind of job posting, requirement by requirement, and shows the work behind it.
Seven years on active rigs in the Delaware and Midland Basins — cuttings, gas chromatography, mud logs, well control, field QA. Basins, formations, unit work and field QA.
SQL Server, MySQL and PL/SQL in production; schema design, tuning, ETL pipelines and Power BI reporting. Dashboards, pipelines and the systems behind them.
Hybrid rules + LLM systems in production, built with Claude Code and Codex, front ends, and the Linux deployment that ships them. Agent501, CompanyMan and the deployment under them.
Permian wellsite years plus Power BI, SQL and AI agents (Claude, Codex), pointed at production optimization and Proof-of-Value work for operators. Includes GapFinder, a lost-production analysis of 36 Delaware Basin wells from public state data.
The product the field years turned into — rig-site reporting that starts with a photo of the tank board.
Codes bank and card transactions against a client's chart of accounts and grant structure. It states what it matched on and how often it's seen that pattern, holds anything it hasn't seen rather than guessing, and keeps every correction — so the pile a human touches shrinks month over month.
Production, unit costs, capital, funding, people and safety for an oil and gas operator on one screen. The charts are the easy part: nothing an executive asks for lives in a single system, so the real work is a crosswalk that resolves telemetry tags, property numbers, cost centres and lease records to the same well. The dashboard shows that join on its own page rather than hiding it.
Rig-site reporting for the operator's representative. Photograph the tank board, the mud report, the morning numbers — it reads them, checks them against yesterday, and returns a formatted daily report plus a mobile dashboard the office can open. Runs on the company man's own laptop with a folder connection, or hosted white-label per operator.
Three years of Power BI dashboards over real-time drilling and geological data — formation tops, mud logs, LWD/MWD, directional surveys, cuttings and gas shows. Dimensional models, tuned SQL against SQL Server and MySQL, large operational logs on Hadoop, and Excel VBA / Power Query automation behind the recurring deliverables. Also trained the field crews who used them, which decides whether a dashboard survives.
Every site and app here runs on one box I provision and administer personally: nginx server blocks per subdomain, TLS via certbot, systemd services, and a git push that redeploys within a minute of the commit. Nobody else's platform, nobody else's build pipeline — which is why I can answer questions about how it actually works.
Ingests long-form audio and video and returns structured, searchable transcripts. Packaged properly with a CLI and tests because re-running the same manual extraction by hand stopped being acceptable.
Roughly 25 repositories, most private. Happy to walk through any of them.
A US accounting practice doing the monthly close for non-profit clients. Every transaction needs seven labels, not one — account, fund, restriction, location, programme, sub-programme, grant — because funders audit all of it. Days a month, by hand, thousands of rows.
One agent per domain, each solving a job somebody actually does by hand. The bookkeeping two are live. The second takes production data and puts the answer in front of an executive instead of in a spreadsheet nobody opens.
Bookkeeping that learns.
Production data, surfaced for the people who decide on it.
Where a field is losing oil, why, and what it is worth.
If there's a job in your business that runs on precedent and patience, it's a candidate.
I'm open to roles and to interesting problems. Fastest way is the form; email works just as well.