Last Friday we launched Railblocks 2.0, but I also had a fever. So I kind of missed the launch 🫠 I am here now to make up for it 😤 ... with ÏT 📺 ÏT 📺 A fictional series about an Investment Firm and their journey with AI 🤖 In this first episode, the “basement crew” is tasked with answering a vague question from Ivan their creator and one of the firms partners. Maybe it’s the fever that got me going on this side quest. But I am kind of fond of this dual-world concept of upstairs and downstairs now. To me this reflect the Zeitgeist of everyone who runs operations, including our customers - investment firms. We are all trying to figure out how to best work alongside AI. To make that work we have to bring empathy to both upstairs and downstairs. This is what we set out to solve with Railblocks 2.0. And to do so we are making these moves 1️⃣ We bring two more co-founders @EricFriedman and @nmsnow alongside @Lorenzo__CB , @vladoustinov and me. This brings us to 5 co-founders in total + a powerhouse A Team behind us ready build the most amazing firm operating systems out there. I am grateful that 2+ years on, we are able to make such a decisive move, that kind of works most naturally only with a scaled + bootstrapped company. We collaborated with Eric and Nate on several shared private equity and venture capital clients almost since the beginning of Railblocks. This felt like a natural next step to solidify our joint ambitions and direction. Both Eric and Nate bring lots of network and experience in sales, finance and legal, as well as a local presence in the US - New York 🗽 which is Railblocks's primary market today. 2️⃣ New brand + positioning 😤 here it is Railblocks helps family offices, venture capital and private equity funds build their own proprietary AI Operating System: an environment designed to enable reliable, secure, and scalable agentic work. We embed forward deployed engineers inside those firms and create a custom OS for them on top of Cloudflare, using infrastructure technology around data and workflows we've developed in house. - Lorenzo, Vlad and I are so grateful to be able to bring Eric and Nate along to double down on an incredibly fascinating ICP and problem space. It feels like we now have the right kind of laser obsession and all the rocket fuel we need to level up even more and build amazing stuff along the way. ps: if you are interested to see our 1-click install firm os built entirely on @CloudflareDev : ) a teaser at firmos.railblocks.com

By far the best deep dive on @Cloudflare OS rn that actually hits home

per aspera ad astra

photopea mcp + executor = strangely hypnotising everytime i watch an asset take shape

does PR velocity count as PMF?

me reading what @RhysSullivan has been shipping for Executor every morning feels like starting my day with a freshly ironed newspaper

Which is why I am grateful that Cloudflare are shipping so many primitives specifically for this ecosystem.

I am looking forward to seeing first examples like this which make use of Cloudflare Artifacts rather than Github ..

bigger than fable 😍

Policies are coming to executor.sh Being able to take an MCP like the @render MCP which only comes with a full-scope API key - and inject policy on code mode mcp patterns is amazing. @RhysSullivan shipping all the good stuff

production grade agent coding is not becoming the future anymore. it is the future. what felt strange, new and somewhat frowned upon 8 months ago has shifted so fast …internally i see senior engineers shipping alongside ai in ways that begin to feel poetic 🥺

Context is like lifeblood to agentic systems. The quality of context is directly related to the quality of output. Because context varies from business to business and changes over time it is a really complex and individual problem to solve for. At @railblocks we think about this problem from the perspective of ops engineering - building internal systems. Here a (simplified) example… 🗣️ “What you say” (the prompt) “Create me a new email onboarding sequence for our trial users who haven’t upgraded after 7 days. Use this sequence logic, this copy, and embed in these internal interface.” 👀 “What the model needs to see” (the context) For that request to actually work, the model needs a ton of context, that doesn't live in a single source of truth. It is scattered across source code, internal decisions and external integrations. Some examples .. 📦 Stored data > where users and trials are stored 🔬 Schema & types > how user models and subscription states are structured 🧠 Business rules > trial period calculations and timezone handling logic 🔄 Workflows > where email sequences are scheduled and triggered 🖥️ Interfaces > campaign dashboard and email template components 🔗 Endpoints > email service provider and user management APIs 🍀 Examples > existing onboarding patterns and conversion sequences Agents are getting smarter. They ingest more source code, call various tools including MCPs, consult OpenAPI documentation. But the reality is that pulling all this together still feels fragmented. I dream of a future where building internal systems becomes as simple as expressing intent. For that to happen, we need better solutions for surfacing the right context at the moment of creation...

Luma is simple and beautiful but it’s a standalone product and its data is completely silo’ed from the rest of your stack. Fixing this isn’t easy: their API is rudimentary and they don’t have webhooks 😫 That’s where @triggerdotdev and @attio come in. With a mix of cron jobs and the new App SDK from Attio we are able to sync data across for less than $1/mo and with higher polling intervals than @zapier

Why have Python and Typescript become the go-to languages for LLMs? Sure, it makes sense at face value. Both are hugely popular and more data to train on means more nuanced LLMs. But this feels like an incomplete view of the world...? The cost of generating code is trending towards zero. But what is the value of that code, if we cannot reliably assert that it is in fact written reliably? I think some of the hardest "AI code generation" problems to solve in the coming years relate to this question. A fundamental factor constraining code reliability are the properties of the underling language in which the code is written. This is not the only factor, but it is an important one to consider. And it begs the question what would be the ideal language / framework for LLMs if datasets were equal. From that perspective Javascript and Python feel porous to me and functional programming languages like Elixir feel solid and more promising. Wouldn't an LLM want immutable data, no shared state, pattern-matching, recursion, and higher-order functions as part of its everyday reality? All this popped in mind today because I saw @chris_mccord just released phoenix.new - which to me feels like a valiant effort for Elixir / Phoenix in the "race of relevance" in the age of AI code gen. I'd love to see more discussions and long-term thinking around what languages would actually be most helpful for LLMs .. by design.

Linear UX starts on the website. "D" shortcut for downloading .. no second wasted 🤯

This is my favourite new #MCP stack.. MCP React Client = @Cloudflare use-mcp + @aisdk MCP Server = serverless on @modal_labs Took a few hours to spin up an internal tool that translates natural language to SQL to insights