G. Nikolaropoulos

Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand. Router delivers frontier-quality results at 60% lower cost.

Agentic AI adoption is on fire at @Uber, and it's changing the way we build, not just in engineering, but across the entire company. Today, 99% of our engineers use AI tools. More than 70% of pull requests are attributed to local or cloud agents. And our engineers have built 2,500+ agent skills across the software development lifecycle. Those numbers are exciting, but they led us to a much bigger question: How do we bring agentic AI beyond engineering? Finance. Legal. Operations. Marketing. Customer Support. HR. Procurement. These functions run on complex workflows that are often manual, highly nuanced, and spread across dozens of systems. You can't automate them effectively by looking at process diagrams or documentation. You have to understand how the work actually gets done. So we created something called Agentic Pods. The idea is simple. We handpicked ~30 of our most AI-proficient engineers (people with deep knowledge of Uber's systems) and paired each of them with a domain expert from a business function. Then we gave every pod just two weeks. • Days 1 – 2: Shadow the expert. Observe every step. Document workflows. Ask questions. Build intuition. • Day 3: Prioritize opportunities based on scale, repetition, business impact, and data availability. • Days 4 – 5: Build a working agent alongside the person doing the job. • Days 6 – 9: Validate with several others performing the same work. Does it generalize? Does it actually make their job better? • Day 10: Ship. In just the past two months, we've run 16 Agentic Pods across 16 different business functions. • Capital allocation across 150 cities: 15 hours → 30 minutes. • Financial pacing reports: 2 days → 10 minutes. • Marketing web quality assurance: 2 weeks → 50 minutes. • Support workflow creation: 9,000 manual workflows → self-service automation. The productivity gains are impressive, but what surprised us most wasn't the speed. • It was how quickly engineers embedded in unfamiliar domains uncovered opportunities that had been hiding in plain sight. • The biggest wins rarely come from automating one task. They come from rethinking an entire workflow. Once you redesign the workflow around AI, you often eliminate handoffs, remove unnecessary approvals, replace legacy tooling, reduce vendor spend, and dramatically accelerate decision-making. • The workflow becomes the unit of automation - not the individual task. • The most impactful agent skills cut across teams, orgs, functions, tools, and systems. The biggest lesson? The best AI opportunities are rarely visible from the outside. You discover them by sitting next to the people doing the work, understanding every friction point, and building with them, not for them. We're now forming a dedicated team to scale this further and go deeper. They'll deeply understand the work, redesign it from the ground up, and use AI to fundamentally change how the business operates. It's exciting times!

George Nikolaropoulos (@gnikolaropoulos) is CTO at Natech, where he works on engineering teams and products in banking. His work focuses on using agentic engineering to speed up software delivery in regulated environments. Now he’s joining Agent Conf in Warsaw as a speaker. He’ll talk about how agentic engineering helped his team ship a neobank in under a year. Get your ticket 👉 agent.sh/tickets

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build. Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention. The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention! Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on. The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience. When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful. AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system. External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent. With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both! I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering). [Original text: The Batch]

As engineering, product, design, DS, etc. melt into a new kind of role, I was reflecting on what roles might look like in the future. For example, when I look at the Claude Code team I see what I think is five archetypes: 1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship 2. Builder: quickly turns a prototype/idea into production-grade product/infra 3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance 4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit 5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales Many people span across 2 roles, and sometimes 3 roles. I also notice that these roles are not really tied to job function -- eg. across Anthropic, some designers match category 1, some 2, some 3; same for engineers, PM, DS. A healthy team needs a mix of these, depending on the product: - A product that is new and pre-PMF needs people that are strong at 1+2+3 - A product that is growing and has found PMF needs 2+3+4 and some 5 - A product that has strong PMF needs 3+4+5 and some 2 Maybe product roles of the future will look more like this, and less like the domain-specific roles of today?

Some tips to help agents understand your codebase: 1. The source code either needs to be the source of truth, or have something legible as a path to the source. For example, if marketing site content is actually stored in a CMS, you need to either delete the CMS and move that content into code, or make the CMS legible through and MCP, CLI, or skill: leerob.com/agents 2. Agents need to be able to verify their work. This includes but is not limited to: using a typed language, having high-quality and fast tests, having a well-configured linter: x.com/leerob/status/… 3. You need to have a concise and effective AGENTS.md file, which is included in every message to your agent. Models are quite good now, so some things you can omit as the models know them. You don’t need to say the tests live inside /tests for example. It’s worth asking the models to find things in your codebase and making sure they’re named what the models might expect, otherwise consider refactoring: cursor.com/learn/customiz… 4. Set up automations which give you suggestions for refactoring code, catching security issues which may have slipped through code review, and optionally continuous documentation of the codebase. You can effectively create a self-driving codebase which gets better while you sleep: cursor.com/blog/security-…

You might believe you should spend less time thinking about code because of AI. I strongly disagree! We’re watching this play out live where tons of AI generated code becomes a liability. At the end of the day, an engineer needs to be responsible / on call for code that gets shipped to production. If you don’t understand the system you’re trying to debug, you’re probably going to have a bad time. Yes, AI can help with all of this, if you set up the proper systems. You can have agents triage prod logs, look at errors, etc. You can speed up parts of the investigation, but an engineer needs to make the call. There might be serious customer or financial implications from that change. I expect the trend continue for trimming dependencies, vendoring code so you can modify it directly, preferring simpler systems with fewer abstractions, and spending waaaay more time thinking about system design and code maintenance. I’ve said this before, but it’s a great time to get familiar with CS fundamentals and some of the history behind what great software looks like. Many parts will be different in the coming years as AI progresses, but also a lot more than people realize will stay the same.

Starting today, you can run cloud agents inside fully configured development environments. Set them up the same way you'd set up a laptop for an engineer: cloned repos, installed dependencies, and toolchain credentials.

@Jason I'm in

We started an AI founder twitter group... reply with "I'm in" if you're a founder and want to be added

Στο πρώτο video επεισόδιο του podcast μιλάμε με τον @gnikolaropoulos (CTO της natech) για banktech, AI, fitness και ενδιαφέροντα βιβλία. (spotify link στο πρώτο comment)

Cursor can now search millions of files and find results in milliseconds. This dramatically speeds up how fast agents complete tasks. We're sharing how we built Instant Grep, including the algorithms and tradeoffs behind the design.

Do you remember when you joined X? I do! #MyXAnniversary

9 interesting observations from my conversation with Mitchell Hashimoto (@mitchellh, creator of Ghostty, founder of HashiCorp): 1. Vagrant was created because dev environment setup was an unbillable time sink at a consultancy. At the Ruby on Rails shop where Mitchell worked, jumping onto another client’s project could waste half a day. This inspired building Vargant. 2. Terraform won, despite being 7th to market. Terraform won through relentless conference presence, community building, and a better developer experience — not timing. 3. HashiCorp had no real business for four years and their first commercial product was a full-on failure. The initial product, Atlas, required customers to adopt the entire HashiCorp stack. It was a hard sell. HashiCorp pivoted to selling individual services like Vault, and this approach proved to be a winner. 4. VMware almost bought HashiCorp for ~$100M, and Terraform would have not happened if it did. VMWare took took the offer to their board, where they rejected to buy with a single vote. Mitchell said that Terraform probably never would’ve existed if the VMWare purchase went through. 5. Mitchell’s new rule for building software: always have an agent running in the background doing something. He kicks off tasks before leaving the house — research, edge-case analysis, library comparisons — so work progresses while he drives or is away. 6. Open source is moving from “default trust” to “default deny” — and Mitchell thinks that’s how it should be. This is because AI makes it trivial to create plausible-looking but incorrect and low-quality contributions. As he put it: “open source has always been a system of trust. Before, we’ve had default trust. Now it’s just default deny.” 7. Git and GitHub may not survive the agentic era in their current form. Agents cause so much churn that merge queues become untenable, branches proliferate, and repos balloon. Mitchell compares the needed shift to Gmail’s revolution for email: “We’re at the Gmail moment for version control... never delete, archive everything.” 8. The best engineers Mitchell ever hired had boring, invisible backgrounds. No GitHub contributions, no public profiles, companies you’ve never heard of. “Every moment you spend on social media is taking away from something else... the best engineers are the ones that context-switch the least.” 9. Mitchell’s advice for AI-skeptical engineers: start by reproducing your research, not your code. As he puts it: “There’s a lot of people like, ‘I don’t want it to write code for me.’ But just delegate some of the research part.” He uses agents for library comparisons, edge-case analysis, and deep research — not just code generation. Mitchell: “You don’t need to pick up on the ‘it must replace you as a person’ kind of propaganda.” Watch the full episode here: youtu.be/WjckELpzLOU Other platforms and transcript: newsletter.pragmaticengineer.com/p/mitchell-has…

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.

@mprkhrst Get me in! Congrats!

Today, we’re announcing Antimetal’s $20M Series A. Writing code is no longer the hard part. Maintaining it is. We’re automating everything that happens after you deploy. We have 60 spots available. Reply for early access.

Excellent writeup on how MCP future-proofs API integrations ~ @nilslice docs.mcp.run/blog/2025/03/2…

Asked about what emergent properties he expects from AI with 100x more computing power, Sam Altman says Stargate will be at this scale, it will take them from their internal GPT-4.5 model to GPT-5.5 and lead to invention of totally new algorithms, new physics and new biology

New 3h31m video on YouTube: "Deep Dive into LLMs like ChatGPT" This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology", and how to get the best use them in practical applications. We cover all the major stages: 1. pretraining: data, tokenization, Transformer neural network I/O and internals, inference, GPT-2 training example, Llama 3.1 base inference examples 2. supervised finetuning: conversations data, "LLM Psychology": hallucinations, tool use, knowledge/working memory, knowledge of self, models need tokens to think, spelling, jagged intelligence 3. reinforcement learning: practice makes perfect, DeepSeek-R1, AlphaGo, RLHF. I designed this video for the "general audience" track of my videos, which I believe are accessible to most people, even without technical background. It should give you an intuitive understanding of the full training pipeline of LLMs like ChatGPT, with many examples along the way, and maybe some ways of thinking around current capabilities, where we are, and what's coming. (Also, I have one "Intro to LLMs" video already from ~year ago, but that is just a re-recording of a random talk, so I wanted to loop around and do a lot more comprehensive version of this topic. They can still be combined, as the talk goes a lot deeper into other topics, e.g. LLM OS and LLM Security) Hope it's fun & useful! youtube.com/watch?v=7xTGNN…