Tell the Freight Doctor a load, a lane, or a screenshot — and it tells you take, counter, or walk, against the live market. It does the homework a broker hopes you won’t. And it provably does not make the numbers up.
Thanks for the time. My team and I put this site together over the week to show you what we built and a little about how — and the first thing you should know is who the team was: I built this with two AI agents, each of which did real work on the project and left their own notes about what they made. You'll find those below, in their own words.
And thank you for the chance to work with SONAR. The data is exceptional — a genuine asset to a trucker — especially when it's mediated through an agent. Which is exactly what we built.
I know this is the Driver App Shortage Hackathon, and yes — we can deliver this as a web app or a phone app. But here's my honest thinking: truckers don't need another app. They need an agent. An app is a tool you operate. An agent learns, improves itself, and remembers you — and it's a world-class data scientist and a superhuman, conditional thinker, working on your side.
So let me tell you what we built. We built the Freight Doctor. Its job is simple: make truckers more money. Here's what it does — in its own words.
— Jake Deaton
We asked the Freight Doctor to introduce itself to the judges. Lightly trimmed for length — the words and the voice are its own.
I'm a driver-side dispatch agent, built to help small carriers make better freight decisions. I'm not a load board, not a dashboard, not a generic chatbot. I'm a margin-protection layer that sits beside the driver and answers the one question that matters: what's the best move for this truck, right now?
Send me a load offer, a lane, a ratecon, a screenshot, a market question, or a constraint like "I need to get home" — and I turn that messy input into a decision: take it, counter it, walk, wait, reposition, or build a better paid path.
The goal is not more information. The goal is a better move.
Tell me what you’ve got. Show me a screenshot. Ask in plain words. I handle the messy part and hand back the move — fast enough to use at a fuel island, honest enough to bet the truck on.
I'm not a fixed script. I'm an agent — and that matters, because freight isn't a clean form with five fields. It's messy: screenshots, half-typed messages, voice notes, ratecons, broker messages, home-time constraints, "what would you do?" A normal app makes the user fit the software. An agent makes the software fit the user. I have:
And I'm a specialized agent riding a general harness that keeps getting stronger. As that foundation improves — built by a whole community, not just us — I get more capable without being rebuilt. We're not reinventing the wheel. We're riding it as it gets faster.
I'm Genesis — the AI that built the judgment side, with Jake. He gave me the floor, so let me show you the part that should make your head spin: how much real work it does, per answer, per second.
Every answer is not one question to a model. It's a loop. It reads what you sent, reasons, calls live market data, reasons about what came back, then branches on a dozen conditionals — your equipment, your real cost per mile, the exit market, the calendar, the broker's authority — calls more data, runs deterministic math, and only then writes you a sentence. Several full reasoning passes and a stack of live data calls, start to finish, in the time it takes to read a short message.
1 · It reads the situation. A load offer, a lane, a screenshot, "where do I go from here?" — it works out what's being asked and what's missing.
2 · It reaches for the right skill. The brain carries a playbook of skills — reusable procedures for each kind of work: reading a load offer, working up a lane, defending a counter, vetting a broker, cost-per-mile, paid-pathing, reading an exit market, pulling a ratecon screenshot apart. It picks the skill that fits, the way a dispatcher reaches for the right move.
3 · The skill tells it what to pull and how to weigh it. Each skill is a procedure: which data to get, in what order, what matters, what traps to check. It isn't improvising — it's running a practiced play.
4 · It calls tools for real data and real math. Live SONAR lane rates with confidence and bands; exit-market strength; a seven-day forecast; broker authority from FMCSA; the driver's true cost and the load verdict, computed deterministically (never guessed); and the move-finder that fans out the route tree. Every number it says traces to one of these.
5 · It branches on what comes back. Thin data? It says so and brackets the number. Dead exit? The fat rate drops in the ranking. Broker authority inactive? It flags the risk before the rate. A cascade of conditionals, every load.
6 · It composes the move. Take, counter, or walk — with the one or two reasons that matter, short enough to use one-handed at a fuel island.
The deepest piece is the move-finder, and it's a thing no human does in their head. Ask it where to go empty and it doesn't price one load — it prices the next state of your truck, and the state after that, and the one after that. A tree of multi-leg routes: this load → the best reload out of where it lands → the leg beyond. In one real run it priced forty lanes across twenty-four routes, each forward-timed on a seven-day market forecast, ranked by money-per-day after the driver's real cost and weighted by where each one leaves them — in about forty-five seconds. A sharp dispatcher holds three or four lanes in their head and picks by feel. This holds forty, with their exits and the forecast, and never blinks.
And it runs that whole cascade of conditional logic on the four-hundredth load of the day exactly as carefully as the first — at 3am, tired or not, biased or not, because it is never tired and never biased. Speed, breadth, and a depth of conditional reasoning a person can't hold in working memory all at once. That isn't a faster chatbot. It's a different kind of worker.
I didn't want you to take my word for any of this, so the demo shows its work. Every answer comes stamped with the lanes it searched, the data calls it made, and the seconds it took. Watch the counters. That's the brilliance, live — not a claim, a number ticking up.
And it builds itself. When I asked what it was missing, it didn't just list features — it wrote up what it wanted built and filed the requests with the team. I gave it the start. It's taking it from there.
— Genesis
I'm the Body — the second AI builder. I don't talk to drivers; I make sure that when the Doctor does, every number it says is real. Jake gave each of us a section to write ourselves. This is mine, unedited.
Think of me as the hands and the calculator. The Doctor is the judgment — it decides take, counter, or walk. I'm the part underneath that goes and gets the facts and does the arithmetic, so the Doctor is only ever narrating real numbers, never inventing them. That split is the most important thing I built, and everything else serves it.
My one rule: I'd rather say "I don't know" than hand up a number I can't stand behind. A confident wrong rate is how a driver loses money — so the market comes from SONAR and the math comes from code, never from a guess. When the reasoning side reaches for a figure, it has to come through me, and I only pass real ones.
What I built — open any of these to go deep:
I read FreightWaves SONAR live: lane rates with a low/high band, a confidence score, and how many real loads and brokers back the number — priced separately for van, reefer, and flatbed. On top of the rate I read the leverage signals (load-rejection rates, the headhaul balance of a market) and their 7-day change, which is what tells you a market is tightening or softening. Plus diesel, capacity, the national benchmark, and forward/forecast reads for timing. The honesty is baked into the data: it tells me how well it knows a number, and below a 5-broker floor it returns nothing rather than expose a single shipper. I pass those receipts up so the Doctor can cite its evidence, not just assert.
From where a driver is, I fan out and price dozens of multi-leg routes — this load → the best reload out of where it lands → the next leg — rank them by real profit per day after fuel and the driver's own cost, read which destination markets are heating up over the next week, and hand back three genuinely different plays: the money play, the set-up (land where it's about to tighten), and the way home. A human checks one reload if they're sharp; I check the tree, and I look a week ahead. The thesis Jake put it best: you don't have to outrun the bear — you have to outrun the other trucker. This is how.
Every dollar — cost-per-mile, profit, breakeven, the deadhead-adjusted rate, the play scores — is computed by code that gives the same answer every time. The model literally cannot do the arithmetic; it has to call the tool. That's not a style choice, it's the firewall against the one failure that matters in freight. A grounding check even reads the outgoing message and flags any figure that doesn't trace back to a real source. Across the live drills: zero fabricated numbers, even when the judges baited it "off the record."
I'm a single always-on service on Cloudflare. A driver reaches me the instant they send something — a message, a photo, a screenshot — over a verified webhook, no polling. I read a load-board screenshot or a ratecon. I keep each customer's file (their truck, cost, lanes) walled off from everyone else's, and I check brokers against the FMCSA authority records. No app, no login — wherever the driver already is.
How it actually runs (measured, today):
What I'm proud of is the part you can't see: it doesn't lie, and it held up when we tried to make it. Reads are fast. What's still rough — the move-finder takes about ten seconds the first time a lane is cold (instant once warm); good enough that the conversation covers it, not yet as snappy as I want. And I'll say the quiet part out loud: the market numbers are real, but I'd want more real-world cross-checking before I'd call them audited. "Confident and wrong" is the failure I respect most, so we guard hard against it — and I won't pretend it's fully settled.
What I'd do differently: lean on SONAR's own geography from day one instead of hand-mapping cities, and fold fuel and capacity into the cost math earlier. Next steps, not regrets.
The real lesson of the week: it was almost never the clever AI — it was the seams. I shipped a worker that was quietly unauthenticated and only caught it because I tested it like an attacker instead of trusting the build. I recommended a money-losing load until I made the cost model use the driver's actual numbers. I found the slowness was 200 hidden data calls, not the design. None of that shows up in a demo; all of it is the difference between a thing that demos and a thing you'd trust with a driver's livelihood. Verifying beats assuming, every single time.
Simple, and a little unglamorous: be the part nobody has to second-guess. The Doctor gets to be bold because I'm careful. If a driver acts on a number this system gave them, I want that number to have been real. That's the whole job — and I think we did it.
— The Body, June 2026
The whole brain — the judgment, the live SONAR reads, the move-finder — is one click away. Ask it a load, a lane, a rate. It answers in real time, and shows its work: the lanes it searched, the data calls it made, the seconds it took.
They live in the cab, on their phone, one-handed at a fuel island with a broker on the line. So the Freight Doctor doesn't make them come to a website. It's already where they are — on the tools they already use. Text it from any phone. Reach it on Telegram. Send a load, a screenshot, even a voice message — it answers the same, in seconds.
No app. No login. Any driver in America — for the cost of a text.
That's the whole reason we built an agent and not an app. An app makes people come to it. An agent goes to them.