I build AI companies for a living. Founder @ Trarian AI. 3x AI founder. Ex-CTO @paxtonai, Ex-Head of AI @zestyai. Portland/Vancouver, WA

Portland, OR
Joined November 2008
Replying to @michaelulin
What's worked for us: the agent never grades its own homework. Separate reviewer with fresh context, and tests that exist before the diff does.
1
1
26
Michael Ulin retweeted
Replying to @michaelulin
rules in CI, not in docs agents treat a red check as law and a doc as advice
1
1
30
Replying to @michaelulin
Short spec first, then give Claude the live source before it edits. Patch what's there instead of rewriting from memory. Then have Grok or GPT critique the live build and ship v2. That loop catches more than any single prompt ever will.
1
1
29
Michael Ulin retweeted
Replying to @michaelulin
what's helped me most is a second model reviewing before i merge. codex catches stuff claude code misses and the other way around. made a small tool for that, it's in my pinned post
1
1
28
Replying to @michaelulin
Letting Codex or Claude Code rip without tests or specs is vibe coding with extra steps, and the software factory end of that spectrum is mostly just writing the checks first.
1
1
41
Michael Ulin retweeted
Is anyone focused on getting high-quality software out of coding agents? I'm surprised how much AI coding still boils down to prompting Codex or Claude Code and letting it rip. I wrote about 5 approaches, from vibe coding to software factories. What's actually working? scientificfounder.substack.c…
6
2
10
196
Michael Ulin retweeted
Replying to @michaelulin
What works for us: the agent drafts acceptance tests first, a human approves them, then it implements against them. A fresh session reviews only the diff. Prompting harder never beat that loop.
1
3
19
Michael Ulin retweeted
The only generation that knows how computers work is also the most relaxed about AI:
324
865
170
9,257
515,417
Michael Ulin retweeted
first vibecoded billion-dollar company?
287
476
261
7,088
3,343,980
Michael Ulin retweeted
LangChain Community Spotlight: Paper2Any 📄✨ Transforms research papers and PDFs into editable presentations, diagrams, and scientific figures using agent-based workflows. Open-source platform with multi-LLM support and production-ready deployment. Check it out: github.com/OpenDCAI/Paper2An…
3
22
1
66
9,025
Michael Ulin retweeted
Being a non techy is hard nowadays....everyone is vibecoding and shipping products. So I host AI build sprint for builders to ship and take it to the market. (We need serious founders)
9
6
83
2,693
Michael Ulin retweeted
Recent studies in neuroscience and psychology are reframing ADHD not merely as a set of cognitive hurdles but as a powerful driver of breakthrough creativity and innovation. Long stereotyped for difficulties with focus, attention, and impulse control, individuals with ADHD traits often exhibit superior divergent thinking—the capacity to generate a wide array of novel ideas by connecting distant or unrelated concepts. This stems from reduced adherence to rigid mental frameworks, enabling freer conceptual expansion and the production of more original, unconventional solutions than neurotypical counterparts. Heightened mind-wandering, especially when deliberate (purposefully allowing thoughts to drift), acts as a fertile source for this creativity, bypassing conventional boundaries to yield abundant "outside-the-box" insights. Complementing this cognitive flexibility is a neurological drive for novelty rooted in lower baseline dopamine signaling. This creates a chronic need for stimulation, translating into exploratory, risk-tolerant behavior and a propensity for adventure—qualities that can disrupt routine settings but prove invaluable in dynamic fields. Impulsivity, often reframed as rapid action initiation, becomes a catalyst for pursuing bold ideas and seizing opportunities in high-stakes environments. These traits align closely with the profiles of many successful entrepreneurs, inventors, and pioneers. In fast-evolving creative and innovative economies, the ADHD brain's wiring for quick associative leaps, tolerance of uncertainty, and motivation through novelty-seeking provides a distinct edge, turning potential challenges into engines of originality and progress. Emerging evidence from 2025–2026 research reinforces this view: studies link stronger ADHD traits to elevated creative achievements via mediated mind-wandering, intuitive insight-driven problem-solving, and higher real-world inventive output, highlighting neurodiversity's role in fueling societal advancement. [Maisano, H., et al. (2026). ADHD Symptoms Predict Distinct Creative Problem-Solving Styles and Superior Solving Ability. Personality and Individual Differences (February 2026)]
232
1,022
262
6,572
436,341
Michael Ulin retweeted
Traditional Sportsbooks: "You're winning too much. We're limiting your account to $5 bets." 🚫 Prediction Markets: "You're winning? Great. Here's more liquidity." 🤝 The model has shifted. Use Tenki AI to find the inefficiencies, calculate your edge, and trade where your skill is actually an asset. Intelligence is only a threat to a rigged house. In a real market, it's currency.
The Economist has a great piece on strategy sportsbetting apps use to throttle smart bettors: ▫️Skilled players are “sharps” and given “stake restrictions” if they play too well (bets are capped). ▫️Rest of players called “Square”. ▫️In 2025, 4.3% of active UK accounts had a “stake factor” below the maximum bet allowance of 100%. ▫️Sportsbook will take bets with a profit margin as low as 4.5%. ▫️If they are able to do good “player-profiling” and keep the “sharps” from playing, the profit margin can reach 10-20%. ▫️As important as keeping out “sharps” is hooking “whales”, the deep-pocketed players that are willing to keep playing (and losing) large sums. ▫️Some “whales” are actually “sharps” in disguise, though. They’ll lose a bunch of bets to lull the sportsbook then put down a massive bet when they have an edge. ▫️While there is a risk of a “whale” being a “sharp”, the value of a real “whale” is so high that sportsbook will take the risk ▫️“In March 2024 PointsBet, raised its share of online sports-gambling revenue in New Jersey from 11% to 24% after wooing a single cash-spouting customer away from DraftKings.” (I can confirm that this wasn’t me). ▫️How sportsbook profile players: > Playing on Mobile is a good sign (where majority of people play) > Playing on PCs is a bad sign (it’s easier to compare odds and run models) > E-wallets are a red flag (sportsbooks prefer debit direct deposit that can attach a player to a single account; e-wallet is more anonymized and players can move cash between sportsbook more quickly to shop for the best odds) > Women bettors are a red flag (most bettors are men and “sharps” often use women to place bets) ▫️First wagers are a major tells (typical bettors go after top leagues — NFL, NBA, EPL — and do so near the start of the game). ▫️Popular bets for “squares”: who will win, scoring margins and how star player will perform (also, they love multi-leg parlays). ▫️“Sharps” go after less popular leagues and place bets as soon as odds are published, when they are most mispriced. They also go after less popular bets such as “pts in Q3” or stats from a random player (“Sharps” rarely do parlays and don’t withdrawal winnings often). ▫️One gambling consultant tells The Economist that “By the time a customer places his first bet, [sportsbooks] are 80-90% certain they know the lifetime value of the account.” ▫️”Sportsbooks look at a player’s ‘closing-line value’ — a measure that compares the odds at which he bets with those available right before a match begins. If it is consistently ahead of the market over his first ten wagers, he is highly likely to beat the book in the long run.” ▫️Sportsbook mathematically monitor players and creates a new risk score every 6-8 hours (risk score = estimate of probability that customers will wind up unprofitable). ▫️E-wallet users, women and bets over $100 are flagged. These suspicious bettors are given 30% of maximum bet (and proven sharps only allowed 1%). ▫️High-skilled players will often get a “beard” to bet on their behalf. Most sportsbooks ban this practice but it is widespread. ▫️Safest “beards” are close friends and relatives because you can mostly rely on them to pay out any winnings. The “beards” try to look like degens (playing at 3am, bet non-stop and doing ridiculous parlays) before placing a winning bet. ▫️The most effective strategy for “sharps” is “whale-flipping”. Find a losing gambler, then ask to put a (likely) large winning bet amongst their pool of guaranteed losers. ▫️Once “sharps” max out the people they can use as “beards”, they tap professional networks called “movers”. These “movers” employ a bunch of “mules” who can put down bets on the behalf of the network. Low-end movers charge 10-20% while high-end movers charge 50% of winnings. *** Lots other great details here: economist.com/christmas-spec…
1
4
175
The prediction market space just got a lot more interesting. Gemini received CFTC approval this week to launch a regulated prediction market platform in the U.S. After a five-year licensing journey, the Winklevoss twins are officially entering the arena alongside Kalshi and Polymarket. Cameron Winklevoss put it boldly: "Prediction markets have the potential to be as big or bigger than traditional capital markets." We agree. Here's what this signals: → Regulatory momentum is real. The CFTC under Acting Chair Caroline Pham is actively supporting this space. → Major players are going all-in. Robinhood, Coinbase, Crypto.com, and now Gemini—the institutional interest is undeniable. → The market is maturing fast. Industry projections put the TAM at $95B by 2035, with 46% annual growth. At Tenki, we're building the AI forecasting infrastructure to help traders navigate these markets with better data and sharper predictions. More regulated exchanges means more opportunities—for traders and for the ecosystem as a whole. This is exactly the kind of validation that turns a niche into a category. investmentnews.com/fintech/g…
2
1
2
167
Happy Thanksgiving 🦃 Building Tenki has been a ride. Grateful for our investors, team, and especially our early customers and waitlist crew. More to come. Thanks for being here.
1
1
84
Most prediction market traders on @Kalshi and @Polymarket size bets by vibes. Bad idea. We built a free Kelly Criterion calculator—plug in your edge, get your optimal bet size. Stop leaving money on the table (or blowing up your bankroll). trytenki.ai/tools/bet-calcul…
1
1
2
116
We launched with zero front-end product. Just a landing page pointing to a Typeform. Two weeks later: paying customers. Our CEO @michaelulin just wrote about everything we learned shipping fast, charging real money, and letting customers tell us what we got wrong. Biggest lesson? Having a 76% accurate model ≠ having a product people will pay for. open.substack.com/pub/pionee…
1
2
69
Our CEO @michaelulin joined Justin Johnson from Motivate at Economic Development for Central Oregon (EDCO) last week to talk about building lean AI organizations. The conversation covered a lot of ground — from building the same revenue with 4 people that used to take 40, to why 95% of enterprise AI pilots fail to deliver ROI (hint: it's a culture problem, not a tech problem). Some highlights from Mike's perspective: On the wrong narrative: Stop thinking about doing the same work with fewer people. Start thinking about what you could accomplish with 10x leverage. We didn't get more efficient local breweries during the Industrial Revolution — we got Budweiser and Miller. On getting started: Don't create an AI committee. You don't have an email committee. Figure out what you're trying to achieve first, then align AI initiatives with those goals. On company culture: The organizations adapting fastest are the ones that give people permission to experiment and fail. If your team doesn't feel psychologically safe trying new things, they won't adapt. Thanks to EDCO for hosting this conversation. If you're thinking about AI beyond the hype, this might be worth a watch: youtube.com/watch?v=t8HkxZXp…
1
1
94
A Texas physicist who smoked 6 packs a day died on a Manhattan sidewalk at age 41. His formula helped beat Vegas, made Buffett billions, and now runs the most sophisticated trading algorithms on Wall Street. This is the wild story of the Kelly Criterion. 🧵
2
1
1
87