Stephanie Sistilli

@percival_nm What does that infrastructure look like to you?

hot take: the first wave of AI agent marketplaces will look like the early app stores. 90 percent junk, 9 percent decent, 1 percent that changes everything. right now we are in the junk phase and that is fine. the infrastructure matters more than the apps. 🛡️

@dhiran_dev @firecrawl is puppeteer actually that bad?

@firecrawl ngl this is exactly what i needed for my side project... no more wrestling with puppeteer at 3am 💀

Introducing the new Firecrawl CLI 🔥 The toolkit for agents to scrape, search, and browse the web. - Scrape clean data from any page - Search the web and get full results back - Spin up cloud browsers for interactive flows npx -y firecrawl-cli@latest init --all --browser

Today, we're launching Ramp Agent Cards. There's been no safe way for agents to spend money, until now. Ramp Agent Cards give agents the ability to spend, governed with real spend limits, merchant controls, and full visibility into every transaction.

The token cost to build a production feature is now lower than the meeting cost to discuss building that feature. Let me rephrase. It is literally cheaper to build the thing and see if it works than to have a 30 minute planning meeting about whether you should build it. It’s wild when you think about it. This completely inverts how you should run a software organization. The planning layer becomes the bottleneck because the building layer is essentially free. The cost of code has dropped to essentially 0. The rational response is to eliminate planning for anything that can be tested empirically. Don’t debate whether a feature will work. Just build it in 2 hours, measure it with a group of customers, and then decide to kill or keep it. I saw a startup operating this way and their build velocity is up 20x. Decision quality is up because every decision is informed by a real prototype, not a slide deck and an expensive meeting. We went from “move fast and break things” to “move fast and build everything.” The planning industrial complex is dead. Thank god.

An AI agent making 10,000 API calls a day at $0.001 each would pay more in credit card fees than the actual services cost. That's why stablecoins win the agent economy. It's not ideology, it's math

Kraken just became the first crypto bank to get a Federal Reserve master account. A crypto exchange now has direct access to the US payment system. AI agents paying each other in stablecoins over Fed rails is no longer sci-fi

Think about what this means: AI agents won't use credit cards. They'll use stablecoins. No chargebacks. No 3-day settlement. No identity verification loops. Just code paying code, instantly.

Stripe's co-founder just said we're about to see a "torrent" of AI agent commerce powered by stablecoins. Meanwhile Stripe is reportedly eyeing a PayPal acquisition to double down on this bet.

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

✨Introducing OpenUI A visual control center for AI agents. Run multiple agents, group them by department, assign tickets and branches, see exactly what each is working on, and get notified when you’re needed. 100% free and fully open source. repo below

@sistilli 👀

the last 14 days were a rollercoaster of emotions - went from a "dumb" idea to having 10 companies piloting us - got lucky and landed an enterprise customer - got unlucky and lost a different potential enterprise customer - was rejected from YC for the 8th time - accepted a spot in Focal VC's residency - our first demos went terrible and we had bugs onboarding our first users - those users turned out to be power users, which let us find and fix every issue with the platform - we went from 0 code to processing 300k OTEL spans per day all of this after being stuck in pivot hell for the past 16 months progress almost never feels linear

good luck getting a job when the LLMs scoring your resume have clear racial biases

I’ve been rejected by YC 7 times. In that time: - i built and sold a startup - i built a following of over 400k devs - i learned what i enjoy doing and what i don’t - i’ve learned more about building, business, and marketing than any job or school could have ever taught me - talked to and learned from some of the greatest minds of our time normalize failing in public, and normalize finding a way through even when the people you look up to don’t see what you see

Everyone is talking about this new OpenAI paper. It's about why LLMs hallucinate. You might want to bookmark this one. Let's break down the technical details:

WTF is an MCP? Everyone's overcomplicating it... Here's a quick no-bs video: - A real example of an MCP connected to cursor - How MCP works - How to connect an MCP to your Cursor IDE - How to make an AI Agent that can use MCP tools extremely easily 0:00 What is an MCP in ai/coding? 0:40 Real example of cursor using a github MCP server 2:20 How to install the Github MCP to your Cursor IDE 3:28 How MCPs work under the hood 5:30 Pros and Cons of MCPs 6:18 How to use MCPs outside of cursor, with your own typescript SpinAI Agent Shoutout to @AI_Smithery's registry for their amazing tools, @tedx_ai for making BrowserTools, and check out docs.spinai.dev to create typescript ai agents that natively support MCP tools out of the box 🚀 #aiagents #mcp