Anuar

We just launched! And we are #1 on ProductHunt! 🚀 Tyce is an AI Agent that crafts the smartest documents. With Tyce you can write in the flow, Cursor-like vibes but for knowledge workers. Tyce is deeply integrated with our Word Processor, it can find relevant information in your company’s file storage and generate polished documents in seconds. After talking to over 300 people to learn their processes and pain points - sales, operations, compliance and legal, we were surprised to learn that despite advancements in LLMs people still do document workflows manually. From finding the relevant sources, drafting the first version to reviewing and eventually signing documents - this workflow takes weeks, sometimes months! Existing tools like Microsoft Copilot and Drive Gemini have little adoption and sub-par UX, we realized that one needs to rebuild the whole UX and backend from the ground up so that you can write in the flow. We want to reimagine productivity tools with AI, starting with the most popular productivity tool - Document Processor.

Pitched Tyce to 3 ministers of Ontario to help build more housing in the Province #TorontoTechWeek

If you are in Toronto for the Tech Week, drop by DMZ at Yonge Dundas to chat with founders

Some founders raise in 3 days, others in 6 months. Literally heard that directly from founders. The difference btw those was mainly FOMO

@AmritaMathur People still think we need to build before selling it, SV does the opposite

Is it just me or does it feel cray there is hardly any focus on distribution at #TorontoTechWeek? Every event is "build Canada" or "AI this" and "Hackathon that".

@tobi Looking forward to homecoming

This is a going to be a great week in Toronto! torontotechweek.com

@lennysan @danshipper !remindme in 2 years

.@danshipper: "I would buy SaaS stocks right now. SaaS stocks will be up majorly in the next couple of years."

@kazdenc We need this for startups

in honour of Toronto Tech Week, my builder sunday project was tinkering with this Canadian Tech directory of companies and VCs 🇨🇦cadtech.fyi

Background agents will take their time to scale as we are connect all sources of context and build more capable agents

There are many different types of pivots a startup can do: sales & marketing pivot, problem pivot, technology pivot, product UX pivot etc... You should be micro-pivoting all the time in some of them! 😜

@mscode07 People look chill but are crazy into tech, agree?

@_startuphacker What are you finding

Founder mode - activated 💀

@nikitabier @ianmiles Is there a way to “reset the reach” for accounts like this?

@ianmiles Perhaps it's not the algorithm but rather, the sudden pivot from politics to promoting scam coins? I have seen users lose some reach after engaging in criminal activity and robbing their followers.

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 👇

A few months ago OpenAI lost their lead to Anthropic, now people are switching back to Codex from CC... Once someone trained a better intelligence and wraps it into a product your users are gone

Canada needs to pivot to selling HBM memory

@zechengzh So agents can be bash-ing anything now! 😆 Great approach, will check it out

Introducing Mirage, a unified virtual filesystem for AI agents! 6 weeks. 1.1M+ lines of code. We rewrote bash from the ground up so cat, grep, head, and pipes work across heterogeneous services. S3, Google Drive, Slack, Gmail, GitHub, Linear, Notion, Postgres, MongoDB, SSH, and more, all mounted side-by-side as one filesystem. Bash that AI agents already know works on every format! cat, grep, head, and wc parse .parquet, .csv, .json, .h5, even .wav! One pipe can stitch S3, Drive, GitHub, Slack, and Linear together, same Unix semantics throughout. Workspaces are versioned too. Snapshot, clone, and roll back the whole thing with one API call. A two-layer cache turns repeated reads into local lookups, so agent loops stay fast and cheap. Drop a Workspace into FastAPI, Express, or a browser app. Wire it into OpenAI Agents SDK, Vercel AI SDK, LangChain, Mastra, or Pi. Run it alongside Claude Code and Codex. Site: strukto.ai/mirage GitHub: github.com/strukto-ai/mir… #AIAgents #OpenSource #AgenticAI #Strukto #Filesystem #VFS

@adamghowiba Looks like smth overly complicated big corporate would create and show in fancy pitch decks 💀

JP Morgan's investment research team just shared exactly how they built their multi-agent system "Ask David", and it's the same architecture pattern showing up everywhere: - supervisor agent orchestrates - specialized subagents handle retrieval, structured data, analytics - LLM-as-judge reflection node before the answer ships - human-in-the-loop for the last accuracy gap worth watching for anyone building:

hahahahhaha

@KobeissiLetter Will happen to every economy that’s in the AI supply chain or utilizes AI to the fullest

Markets in Taiwan and South Korea are making history: The total market cap of Taiwan's stock market is up to a record $4.5 trillion, surpassing Canada’s $4.4 trillion for the first time. Taiwan’s stock market value has also exceeded that of the UK for the first time 2 weeks ago. This comes as Taiwan’s market cap has surged by +$2.7 trillion or +150% over the last 12 months. At this pace, Taiwan could overtake India and become the 5th largest world market as soon as next month. Meanwhile, South Korea's stock market cap is up to a record $4.1 trillion, having overtaken the UK last week, and on track to surpass Canada this month. Collectively, the two markets have added +$4.6 trillion in market value over the last 12 months, driven by AI-related stocks. AI is transforming Taiwan and South Korea into a global economic power.

A few months ago, @_startuphacker and I decided to pivot @tyceai to focus on construction. Since then we've had conversations with over 70 construction companies and civil engineering firms. Sat in office rooms. Walked job sites. Talked to the people actually running these projects. What became clear pretty quickly: construction is an incredibly complex, high-risk industry. A single project can involve hundreds of trade partners, years of planning, and billions of dollars on the line. And it's completely people-driven. We realized early on that this industry needs domain-specific intelligence, not general AI. So that's what we're building at Tyce,purpose-built for construction teams. States and provinces are investing billions in infrastructure right now. Cities are being reshaped. That investment needs to be executed well, and the teams doing the executing deserve better tools. That's where we want Tyce to be. Grateful for every GC and engineer who opened their doors and shared what their world actually looks like. That's what's driving what we're building.