Laura Rosenberger

Category: Field Notes

  • Building websites for agents, not humans

    I've built two websites recently. And I fell into a bit of a trap – I built them with humans in mind, not agents. How old fashioned of me!

    My target customer is consumer brands who need help with AI – getting up to speed with it, understanding what's possible, integrating it into their workflows. This isn't something that people in those teams would have previous experience with.

    For the person tasked with figuring this out, where are they going to look for answers?

    Most likely via ChatGPT or Claude.

    So I should have been building my websites with Claude in mind (rather than that person in my target company), to maximise my chances that my content will be surfaced in those chats.

    I've been following the guidance in this brilliant post by Tom Osman around creating llms.txt files, structured data, and comprehensive meta data.

    And asking Claude Code to integrate it for me, naturally.

    The web is going to serve two distinct purposes: a web for humans and a web for agents. Trying to make one website serve both would be a shame, so I hope the web will split in two. The human web can double down on beautiful experiences, thoughtful interfaces, content that's genuinely worth reading and stumbling upon. The agent web can be plain text, structured answers, Markdown, and can be where the mass-generated SEO blogs we've all learnt to scroll past can live. One is where you browse and discover, the other is where you pull down what you need.

  • AI Memory Across Sessions

    One of the reasons OpenClaw has captured everyone's imagination is the memory. It remembers you. Every other AI conversation starts from zero – close the window, lose everything, re-explain yourself next time.

    I've been working a lot in Claude Code, and have built myself a little skill to recreate this.

    How It Works

    I built a /handoff command that runs a structured wrap-up when I'm done working. It reviews the session and saves what matters to a set of persistent markdown files — a daily note, active threads, behavioural patterns (which it can then pull me up on…), and self-improvement notes.

    These notes are accessible for future sessions. Claude knows what I was working on, what's due, and what patterns to watch for.

    The whole thing is just a text file telling Claude what to do and what to save – but it is making using Claude Code as a general assistant for non-technical work just so much better.

    Why It's Useful

    It turns each session from a one-off into something that compounds. Less time re-explaining, more time working. And it catches things I wouldn't note myself — like when the same blocker keeps showing up or when I'm quietly avoiding something (ahem).

    It's not as seamless as OpenClaw's built-in memory. But I control what gets saved, where it lives, what gets forgotten and what my 'assistant' is able to do with this information.

  • AI Champions Are Being Set Up to Fail

    There's a new role quietly appearing across businesses: the AI champion. It's rarely a formal hire. It's usually someone already in the company (a generalist, a special projects person, someone who's enthusiastic and open-minded) who gets handed the AI brief on top of everything else they're doing.

    It's a crucial role. Arguably one of the most important in any business right now. And for the individual, it's an incredible opportunity to become the person who actually figured this out.

    But the support is basically zero.

    There's no playbook. No established methodology. No 'project management 101' equivalent for AI transformation. If you're a project manager, you've got university courses, certifications, Jira, Asana, decades of best practice to draw on. If you're an AI champion, you've got… a ChatGPT login and a lot of Googling.

    What strikes me most is how isolated these people are. Every AI champion I've spoken to is working it out alone, inside their own company, reinventing the wheel. They're not learning from each other. They're not sharing what's working. There's no community or infrastructure connecting the person figuring it out at a £10m consumer brand with the person doing the same thing at a £50m one.

    That feels like a massive missed opportunity, for the individuals and for the businesses betting on them.

    I don't have the answer yet. But I've been thinking a lot about what support for AI champions could actually look like, and I think it starts with getting these people in the same room.

  • The Imagination Gap

    AI is asking you to imagine something you've never seen. And it's hard to be what you can't see.

    I was speaking to the CEO who said 'we lack the imagination to even know what's possible', and it really stuck with me.

    Unless you're really into AI, it really is hard to see what to do beyond 'get ChatGPT licenses for everyone' because how are you supposed to know what's possible when very few people in this space are pushing the boundaries?

    The way I'm trying to bridge this 'imagination gap' for consumer brands is by taking inspiration from the businesses and the individuals who are operating right at the edge.

    Here are 3 sources of inspiration for me at the moment:

    'Companies as Code'
    If AI can do extraordinary things when given a set of 'skills' – essentially just well-structured text files – what happens when you codify your business in the same way? Your processes documented, your data accessible, your operating system written down in a form that AI can act on. So you don't just aim to be a consumer brand that uses AI, but a consumer brand whose operations are built to run like software.

    AI driven software development
    I spent time with a group of AI engineers who weren't just using AI to write code. They'd built entire systems where AI writes the code, tests it, catches its own mistakes, and iterates until it works. Their focus wasn't on building software. Instead, they'd built the machine that builds software. What's the equivalent for a non-technical business?

    See also – compound engineering.

    Claude Code for knowledge work
    Claude Code for non-technical use cases has been having a moment (and OpenClaw is Claude Code in a trench coat). If you want to really geek out, explore the Claude Code+Obsidian combo. Claude Code has become the default way in which I work and am building my consultancy business.

  • The Rise of the AI Operator

    Ops teams are always under pressure to cut costs, but they rarely get prioritised for dev time or allocated budget for new tools. They're stuck firefighting with no space to build something better.

    If you're an ops person who learns to build automations or AI tools – even small ones – you can create tools with massive leverage. And you're uniquely positioned to do this well. You're in the weeds so you see exactly what's causing drag and with AI, you can build something quickly to fix it (or at least make it less bad).

    The impact compounds as you move through the operation, continually improving it, fixing bottleneck after bottleneck.

    If you don't have these skills in your team, you're stuck doing everything manually, hiring linearly with growth.

    There's going to be a divergence where two similar businesses look identical from the outside, but one needs half the people to run the same operation.

    The role of 'AI operator' doesn't really exist yet as a job title. But it will. And the companies who figure out how to build or hire or train for it are going to have a structural cost advantage that's very hard to compete with.

  • Claude Code Plugin for Obsidian

    Last year I moved all my notes and files out of Notion and into Obsidian. With Notion, you're locked in to whatever tools they give you. I wanted to be file-first rather than software-first, so I could use the latest AI tools on my actual files.

    I was already using Claude Code to work with my files. Then I found a community plugin for Obsidian that adds Claude Code as a sidebar. I now have access to Claude Code and everything it can do right where my notes are.

    The Solution

    I installed the Claude Code plugin from Obsidian's community plugins. It adds a sidebar where I can have conversations with Claude Code whilst viewing my files. There's a button to link specific files into the conversation, so Claude has context on exactly what I'm working with.

    This isn't just having a conversation with Claude, this is Claude Code, which means it can take actions, plan, and has all the power that Claude Code has rather than just Claude, which has been way more useful.

    How I Use It

    As a practical example, I keep Markdown files for potential clients in my CRM folder. After a sales call, I use the sidebar to automatically pull in transcripts and add my personal notes and thoughts to create really high-quality notes about each client. It updates the metadata properties at the top of the file. That's how I track what needs to happen next – things like 'awaiting proposal' or 'follow up in two weeks'.

    I can also ask it, 'Who do I need to follow up with?' and it'll search my CRM notes and draft emails for each person.

    The whole thing takes a fraction of the time it used to, and to be honest, this kind of thing I often used to not be super on top of because it felt like a chore. Now I actually do it, or rather, now it gets done for me.

    Why This Has Impact

    Better follow-ups, less prep time before meetings, and I can easily search my notes to find who might be a good fit for something.

    The bigger win is flexibility. I'm not locked into any specific tool. My notes are just Markdown files. If a better AI tool comes out tomorrow, I can use it on the same files. File-first means I control my data and what I can do with it, instead of being locked in.

  • Voice for Email

    I don’t like the idea of AI connecting directly to my Gmail. My entire life is in there.

    I don’t want it messing with my tone of voice or making people think I’m using fake AI responses. Often there’s not enough context for AI to write accurate emails anyway.

    But there is another way I use AI to save time in my inbox.

    The Solution

    I use a voice-to-text app with a custom AI prompt to format emails as I like them.

    Tools like Monologue, WhisperFlow, or SuperWhisper let you speak your email reply. The prompt structures it the way I like, removes filler words, and cleans up stumbles. It doesn’t transcribe word-for-word – it turns spoken thoughts into clean, natural-sounding emails.

    And I don’t have to give access to my inbox to any AI tool.

    How I Use It

    I use Monologue (https://www.monologue.to/). When I need to reply to an email, I hit the option key twice on my keyboard and just talk as if I’m on the phone. The AI processes the audio, cleans it up, and pastes it straight into Gmail for me to review and send.

    The prompt handles the polish whilst keeping my voice. No risk of AI accidentally sending something. Full control over what gets sent.

    Why This Has Impact

    I fly through my inbox now. The barrier to replying is much lower.

    It’s not just that speaking is faster than typing. It’s that replying to an email suddenly feels like talking to someone in the room instead of sitting down to “write an email.” That psychological shift has had the biggest difference.

    The friction disappears and the risky automation stays out.

  • What is left once Claude Code can write the code

    More and more people are looking at Claude Code for non-technical use cases. Claude Code handles the code, but what does a human still need to do?

    A fractional COO friend has been watching some Claude Code webinars and is ready to start playing with it.

    One of his first projects is to use it for invoice generation. We spent a few minutes on whether Claude Code could do this. Yep, it certain could code something. But what else does it need to do this well?

    Accurate timesheet data. Up-to-date client information and rates. Expense policies. Receipts. Knowing where the data lives and whether there are processes behind it so that you can trust it to be correct and up to date.

    All of this was his bread and butter as an operator, and it's easy to forget this doesn't come easy to everyone.

    Once Claude Code handles the coding, what remains is right in an ops person's wheelhouse.

  • Software Engineering Tutor

    I was blindly accepting everything Claude Code suggested. Commands would run, code would get written, and I’d just click “yes” without understanding what was happening. I wanted to actually learn what I was accepting.

    The Solution

    I created a project in the Claude desktop app to act as my software engineering tutor. The prompt is simple:

    You are my software engineering tutor. Explain code, tools, and technical concepts in plain language, breaking down unfamiliar ideas step by step. Check my understanding with questions.

    The key part is “check my understanding with questions.” This forces me to actually verify I understand what I’m learning.

    How I Use It

    I keep two windows open:

    1. Claude Code in Terminal – building the actual project
    2. Claude Desktop App – Project: Software Engineering Tutor – my learning companion

    When Claude Code does something I don’t understand, I copy the code or command into the tutor project and ask for an explanation. The tutor breaks it down step by step, then asks me questions to verify my understanding.

    That’s when I realise I didn’t understand as much as I thought.

    Why This Has Impact

    I’m learning instead of just blindly clicking “accept”. I don’t need to write production-grade code, but I want to be able to read a bash command and know whether it’s about to delete my files or create a backup.

    The tutor approach works because it’s active learning. Having something explained and then being tested on it? That actually sticks and I’m learning 10x faster.