Notes from the work
Writing.
Stories from the systems I've built. Real numbers, real screwups, real fixes.
2026-06-23 9 min read
Building an enterprise search that knows when to say 'I don't know'
Hybridge's knowledge is scattered across drives, decks, and people's heads. I'm building an internal search that answers questions in plain language, with citations, and that refuses to guess when it isn't sure. This is how I'm thinking about a RAG you can actually trust, built one stage at a time.
Read the post
Posts ranked by how much the project behind each one moved the company.
2026-06-23 9 min
Building an enterprise search that knows when to say 'I don't know'
Hybridge's knowledge is scattered across drives, decks, and people's heads. I'm building an internal search that answers questions in plain language, with citations, and that refuses to guess when it isn't sure. This is how I'm thinking about a RAG you can actually trust, built one stage at a time.
2026-06-21 12 min
How I rebuilt a brittle call grader into a coaching platform
A prototype scored every front-desk call out of 60 and emailed a link to a Google Doc. I rebuilt it into a coaching platform: a verbatim quote behind every score, patient safety as a loud flag, the math kept out of the model, and a dashboard a manager actually opens. Here is the whole story, including the bugs my tests could not catch.
2026-06-20 10 min
Teaching an AI to read the whole patient and lean toward a treatment, before the doctor does
The Centralized Diagnostic Filter is HYBRIDGE's diagnostic operating system. AI reads every input a complex case generates (CBCT, intraoral scans, clinical photos, radiographs, a risk survey), surfaces the findings, scores future tooth-loss risk, and leans toward a treatment direction, all before the consult. Then the doctor validates every finding. This is the forward-deployed problem at its hardest: turning a veteran clinician's mental model into a buildable, phased system. Phase 1 is in build.
2026-06-20 8 min
Reconciling a dental day without opening the spreadsheets
Two front-desk staff spent about three hours each every day cross-checking three exports by hand to confirm every patient seen got documented and billed. I built a deterministic engine that does the cross-check and shows them only the flagged patients. Shipped, live, and HIPAA-safe by construction.
2026-06-13 7 min
I built an open-source app to run my job hunt
JobPilot finds fresh roles across 160+ company boards, scores each against my profile, writes a tailored resume and cover letter per match, and tracks every reply to offer. It's now open-source, and it ended up touching all four things I do: data, ML, software, and shipping.
2026-06-10 4 min
How I taught the consult grader to write report cards
We already score every patient consult. Now an AI reads all those scores and writes each doctor a coaching report card, every Monday at 8 AM, with nobody clicking anything. Plus the five bugs I squashed on the way.
2026-06-10 6 min
How I built a job-search autopilot in 5 hours
Refreshing LinkedIn for jobs that were posted three weeks ago is not a strategy. So I built JobPilot: 7 job sources, 4 runs a day, 4 tailored resumes, one dashboard, for under $5 a month.
2026-05-29 4 min
How I caught my pipeline lying to me (and made it confess)
Runs showed ✅ done while emails never sent, rows never appeared, and whole meetings just vanished. Nine kinds of silent failure, all hidden. The fix was making the dashboard stop lying.
2026-05-20 5 min
How I saved our accountant 400 hours a year
Every week our accountant hand-copied numbers from five different systems. A dozen small Python scripts do it for him now, built the way he actually works.
2026-05-20 5 min
How making movies made me a better engineer
People keep telling me films and engineering are separate. They're not. Here's what ten years of making movies did to the way I build.
2026-05-19 4 min
How I built an AI that grades every patient consult
A Zoom call comes in. My tool finds the doctor, grades the consult against the CEO's 7-point checklist, and emails back a color-coded report, without making things up.
2026-05-18 4 min
How I rebuilt a 10-year-old pricing tool in a month
A 10-year-old pricing tool, rebuilt in about a month around one database rule that makes the 6-month price promise impossible to break.
2026-05-12 4 min
How I built a clinic dashboard people actually trust
Two clinics, three messy boards, and a patient-to-lead match that was only 49% right. The fix wasn't a clever algorithm. It was reading the data properly.
2026-05-02 5 min
How I replaced a $98K quote with a $50-a-month tool
A vendor wanted $98K up front and $26K a year to flag bad dental CT scans. I built it in-house on Cloud Run for under $50 a month, with one painful lesson.
2025-09-10 4 min
How I trained Llama to argue more convincingly
I trained Llama 3.1 to write better comebacks in online debates, using a reward model and RLHF. Here's what actually moved the needle, and what didn't.
2025-05-01 3 min
How I built the boring parts of an ML system on purpose
A loan-scoring service where I built the unglamorous parts on purpose: training in containers, model history, quality gates, automatic retraining. The gates mattered most.
2024-12-08 4 min
How we went from 42nd to 1st in a class AI contest
A CIFAR-10 competition across 55 teams, a hard 5M-parameter cap, and two weeks. Tuning got us stuck at 92%. The thing that actually won it was almost embarrassingly simple.
2024-05-18 4 min
How I built a recommender for 22 million records
I built a recommendation system that handles 22 million records: one fast step to narrow the field, one smart step to rank it. It beat 'just show what's popular' by 20%.
2024-05-12 4 min
How I caught fake news and read the mood of an election
I built two models for the 2020 election: one to flag fake news, one to read how people felt across 1.8 million tweets. The modeling was the easy part.
No posts in this discipline yet.