Florian Bühringer @capeflow

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

x.com/i/article/2030…

@dhadrien_ I am in ... under the ethos of BattleBots

@vladoustinov @arthaud_ @Lorenzo__CB yup i do have the evidence of that at my fingertips

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 🥺

Florian Bühringer @capeflow

a year ago

The vibes ...

0 0 2 282 0

@klarnaseb What SaaS are you keeping?

@tobimori Congrats, this is lit

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...

you could check out the advanced filters on table.sadmn.com github.com/sadmann7/shadc… and possibly use that as a baseline inspiration, also from a more practical perspective for an implementation .. also looking directly in Linear / Airtable how the UX is done can help ..

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

Lorenzo Castro @Lorenzo__CB

11 months ago

Our clients can now manage their entire events lifecycle right from their CRM ✨ → No more wrangling CSVs: all data syncs magically in the background → No more context switching: a simple, fully integrated where data already lives → 10x better UX & cheaper infra costs vs.

1 4 20 5K 8

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

Cloudflare is on the Zeitgeist

Cloudflare @Cloudflare

12 months ago

We're open-sourcing use-mcp, a React library that connects to any MCP server in just 3 lines of code, as well as our AI Playground, a complete chat interface that can connect to remote MCP servers: cfl.re/3SWQcYv

21 127 995 93K 704

How we deduped 10.000s of CRM records in @airtable in <5 minutes💡 Last week, a @railblocks client handed us 50.000 records from 100 sources in Google Sheets. After importing them into Airtable & creating the data structure, we managed to clean most of its duplicates in under 5 minutes after building a custom script. Preparing the script is what took us time though. Let me guide you through our process:

Are job titles meaningless? What is their purpose in the first place? When Lorenzo and Vlad brought me on as co-founder, they also gave me a title of CTO. The purpose of this title is mostly to express expectations, to signal what shoes should be filled. But a title is not a title. The same title can mean many things, depending on factors like company size, industry, interpretation etc. Some titles are there to make folks feel good about themselves. Others exist to box them. Nowadays skills collide across disciplines, so everyone ends up and is able to do a little more of everything. The developer does design work, the designer does developer work. Tangential skills are acquired by ICs and roles become more broadly spread, with AI acting as extension of human output. Teams reduce in size, and increase in output. Things are in flux… And sure, titles can signal wisdom and competence in a time of chaos. They affirm X should be competent at Y. But if Y keeps shifting and X keeps evolving, maybe the title is less relevant?

Among the hardest truths I learned as an entrepreneur, is that a harmonious and cohesive team is so critical when trying to make it. This is especially relevant on a co-founder level. If you aren’t able to talk about everything, be part of each others lives, and have complete trust in one another .. you’ll be in trouble. We kicked off our first offsite. For now it’s just the three of us. We have been growing a lot, and have as much to figure out. We need to align on our north star, and figure out any more immediate steps to get there. Our team is expanding and we are building a product that supercharges building internal systems. Everything feels quite wild. Being with Lorenzo and Vlad reminds me of how important personal dynamics are in figuring it all out. And how important it is to foster and appreciate a culture of harmony. I used to call “co-founder struggles” failing for the wrong reasons in my head. But I think about it differently nowadays. It’s just one of the many many things you have to get right as you grow a company, and it’s far from easy. So when you have it, you should hold onto it.

This is closest I have seen to the vision we have for @railblocks with the main difference being that we are focussed more intently on a first-class experience for developers. All-in it’s exciting to see enterprise-focussed solutions like Clark or Retools AI-assist

Brad Menezes @bradmenezes

a year ago

I’m excited to introduce Clark, the first AI Agent to build internal enterprise apps. We’ve raised $60M, including a fresh $23M from @sparkcapital @kleinerperkins, @MeritechCapital and Greenoaks. Unlike consumer vibe coding tools like Lovable, Replit and Bolt that only generate

762 750 5K 1.9M 7K

The vibes ...

@weinmann_arthur This already is a reality, with possibilities of scope and complexity constantly expanding . The most interesting question, I think, is what will it take to build such code generators that can be used by businesses - where security stakes are highest