Anuar (@_startuphacker) header
Anuar (@_startuphacker) profile picture

Founder @ https://teapawt.org/t.co/73ZP71hlt9 - building benevolent Skynet of Construction

Toronto, Ontario
Joined July 2017
We just raised $2M to build intelligence layer for construction. My last startup failed. We built a product and got users, but we couldn’t fundraise and couldn’t close sales. For months afterwards, I felt like a failure. When I decided to try again, I started with what we’d gotten wrong: sales. As a technical founder, I knew how to build, not how to sell. So I talked to 30+ potential co-founders until I met Lylia Djait-Paulien, who spent years at IBM leading complex enterprise deals. Then we went looking for a problem expensive enough that a business would pay to solve it. Neither of us had ever worked in construction. Cold calls turned into meetings, meetings turned into pilots, and pilots turned into annual contracts. It took 18 months and a pivot to get here. Today, Lylia and I are announcing a US$2M pre-seed round for Tyce, backed by BDC Thrive Fund and MaRS Investment Accelerator Fund. Construction is a $2T+ industry in North America, yet AI has barely touched how it works. We’re changing that. Tyce is building the intelligence layer for the built world, giving teams grounded answers from their own project data in seconds, so they can catch multi-million-dollar mistakes before construction starts. We’re hiring founding engineers in Toronto (full-stack and AI agents). If you want to build AI that will shape the physical world, DM me or tag someone below 👇
61
3
3
141
8,283
The only acceptable way to code a construction startup
1
6
341
This is what we are building - Construction Skynet
1
80
Replying to @aleximm
And yet stock price might not follow
1
276
Pitched Tyce to 3 ministers of Ontario to help build more housing in the Province #TorontoTechWeek
1
158
Founder mode - activated 💀
1
7
280
3 major product overhauls. 100 meetings. 0 customers. Here's what we got wrong and how we made it work. We started with consulting and IT firms - helping them draft contracts like Statements of Work from templates. The demo looked great. Spinning loader, document appears, room goes quiet. But we were generating into Microsoft Word, and Word's limitations made the actual product feel like a toy. So we did the irrational thing: we built our own word processor from scratch so AI agents could control formatting and make edits natively. That bought us real UX freedom. Then we realized generation without context is useless. So we built a file system at Tyce, think Google Drive, but AI-native. You could point an agent at a folder of past projects with @ folder, and it would run hybrid semantic + keyword search automatically. Suddenly, a 1-line prompt could produce a 10-page document grounded in your actual work. Then we added Tabs - multiple documents, multiple formats, open at once. The agent sees everything you're working with in the same context. No context switching. Then we went deep on intelligence: more tools, better models, evals, prompt optimization. When agentic search arrived, we scrapped hybrid search entirely. Content quality jumped immediately. Then came governance: permissions, billing, the stuff enterprise actually needs before they'll deploy. Along the way we also realized along the way that construction was the right industry to go deep in. The documents are complex, the stakes are high, and the workflows are broken in ways that AI can actually fix. Today, Tyce can write proposals, review contracts, analyze estimates, and find scope gaps buried in 2,000-page PDFs. One year. Three overhauls. A hundred meetings. The most expensive lesson we learned: building the right product for the wrong customer is the worst place a startup can be. Video below shows what it looks like today 👇
4
204
So far timeline checks out... We have 2-3 years left folks
1
4
103
Agents again doing DDoS attack on Github 🤡
1
152