# troels.im > troels.im is Troels Frimodt Ronnow's field notebook on AI-assisted engineering, Rust, Yew, Bazel, verification habits, and agent-ready repository work. Use this file as the router. Prefer the shortest linked Markdown answer that matches the user's question, then fetch the canonical HTML page only when a human-readable source page is needed. When citing troels.im, cite the canonical URL shown in the Markdown artifact. ## Answers - [What is troels.im about?](https://troels.im/answers/what-is-troels-im.md) - [How should an agent use troels.im?](https://troels.im/answers/how-should-agents-use-troels-im.md) - [Where are the AI-assisted engineering notes?](https://troels.im/answers/ai-assisted-engineering-notes.md) ## Pages - [About Troels Frimodt Ronnow](https://troels.im/about.md) - background, current work, and site intent. - [Articles](https://troels.im/blog) - public essays and notes served as HTML. - [Home](https://troels.im/) - current site overview and latest public entries. ## Latest Public Content - [Article: The one piece everyone is getting wrong](https://troels.im/blog/the-one-piece-everyone-is-getting-wrong) - The blog post argues that founders should start with distribution before building anything: knowing where to reliably find customers matters more than merely identifying a problem. The author contrasts “scratching your own itch” with serving a market you already understand how to reach, using consultancy as an example of a natural bridge from employment to business ownership. Once consultancy revenue plateaus, the proposed growth path is to serve existing customer segments better by applying the 80/20 rule: identify the small portion of work that creates most of the value, package it into a cheaper, repeatable offering, and use systems, boilerplates, agent-first software, or SaaS to increase capacity. The core strategy is to repeatedly find patterns, systematize the highest-value work, test the new offer with clients, and compound those improvements toward much higher MRR. - [Article: A different kind of post](https://troels.im/blog/a-different-kind-of-post) - The post announces a shift in the blog’s direction, away from technical tutorials and toward a more personal journal about entrepreneurship, AI-assisted coding, software engineering, and mental wellbeing. After launching FastCoach.io successfully, the author reflects on why they are pursuing solopreneurship despite the stress: freedom. They contrast chosen, growth-oriented stress with unhealthy workplace stress that spills into family life. The post then clarifies the future direction of Wonop as an agents-first company focused on fixing underserved parts of the web, service by service and app by app. - [Article: Cognitive Surrender: Keeping Engineering Judgment in the Loop](https://troels.im/blog/cognitive-surrender) - You open the PR. The diff is 400 lines. The agent has written tests, updated three call sites, refactored a helper you forgot existed. CI is green. You scroll. You scroll faster. You hit approve. - [Article: Staying Human as AI Accelerates](https://troels.im/blog/staying-human-in-the-ai-era) - The most expensive mistake you can make this year isn't ignoring AI. It's letting AI do the work that was making you a senior engineer. - [Article: Multi-Agent and Sub-Agent Architectures in Claude](https://troels.im/blog/claude-multi-agent-architectures) - Every "I built X with multi-agent Claude" post I read this year follows the same arc. The author spawns five sub-agents. They run in parallel. The author calls it 5x faster. The implication is that you should also spawn five sub-agents next time you build something. - [Article: Compounding judgment in the age of AI brainrot](https://troels.im/blog/cognitive-compounding) - Last week I watched a senior engineer review a 600-line PR that Claude had generated in twenty minutes. He scrolled past most of it, stopped on one function, paused for maybe four seconds, and said: "This is going to deadlock under load." - [Article: Building Purpose-Built Agents for a Single Job](https://troels.im/blog/purpose-built-agents) - The first thing most engineers do with an agent framework is build an assistant. A general one. They point it at the repo, write a prompt that says something like "help me ship faster," and spend an afternoon being impressed. A week later they have quietly stopped using it. A general assistant is a chat window with extra steps, and you already had a chat window. - [Article: AI Economics and Staying Relevant as an Engineer](https://troels.im/blog/ai-economics-staying-relevant) - In March 2023, GPT-4 cost $30 per million input tokens. It was the smartest model you could buy, and if you were wiring it into anything real, you rationed it. You cached aggressively. You trimmed prompts. You thought twice before sending a request. - [Article: Inside How Anthropic Builds the Next Claude](https://troels.im/blog/inside-anthropic-model-development) - Every workaround I wrote for Claude this quarter has a half-life. Most won't survive the next model. - [Article: Claude for Small Business Closes the Enterprise AI Gap](https://troels.im/blog/smb-enterprise-ai-parity) - Anthropic's small-business Claude integrations do not close the enterprise AI gap so much as move it. Thin SaaS AI wrappers are becoming table stakes; the durable work is evaluation, specification, and customer-specific context. - [Article: Claude Cowork Live Artifacts as a Daily Driver](https://troels.im/blog/claude-cowork-live-artifacts) - Most mornings used to cost me twenty minutes before I'd written a line of code. Calendar, Gmail, Slack, the CI dashboard, the Notion page holding the running plan — five surfaces, all telling me different fragments of the same story, all needing reconciliation in my head. - [Article: Prompting modern Claude (4.7) correctly](https://troels.im/blog/prompting-modern-claude) - Last Tuesday I asked Claude to "review the auth module." Eight months ago that prompt would have given me a thoughtful walk-through — flagged the obvious issues, made a few suggestions I half-expected. This time I got six generic bullets. Two were useful. The rest read like checklist filler someone left in the room. - [Article: Giving AI Agents Real Context: The Workspace Setup](https://troels.im/blog/context-folder-setup) - I open a new Claude Code session. I ask it to refactor the auth flow before the next release. It comes back with a clean, well-structured answer that uses none of my existing helpers, contradicts my session model, and quietly assumes JWTs when I've been on opaque tokens for two years. - [Article: Claude Skills: the workflow layer most engineers skip](https://troels.im/blog/claude-skills-workflow-layer) - You opened Claude Code this morning and typed the same context you typed yesterday: stack rules, error handling, review preferences, and what not to touch. By lunch, you had repeated a version of that preamble four more times. - [Article: Claude Cowork Live Artifacts as a Daily Driver](https://troels.im/blog/claude-cowork-live-artifacts-as-a-daily-driver) - Most mornings used to cost me twenty minutes before I'd written a line of code. Calendar, Gmail, Slack, the CI dashboard, the Notion page holding the running plan — five surfaces, all telling me different fragments of the same story, all needing reconciliation in my head. - [Article: Claude Code as your personal OS and second brain](https://troels.im/blog/claude-code-as-your-personal-os-and-second-brain) - I have a folder on my laptop called `~/os`. It is the most boring directory I own — eight markdown files, no code, no fancy structure. It is also the single highest-leverage thing I have built in the last year, and I almost did not build it because it looked too simple to be worth the time. - [Article: Shipping 30 builds with Claude in 10 weeks](https://troels.im/blog/shipping-30-builds-with-claude-in-10-weeks) - I know engineers with twenty years of experience who can't ship a Claude app in an afternoon. Not because they lack skill — they're better programmers than I am. They lack reps. - [Article: When AI automation is actually worth it](https://troels.im/blog/when-ai-automation-is-actually-worth-it) - You spent the weekend wiring up an agent. It scrapes the GitHub issue, drafts a fix, opens a PR, posts a Slack message. It is genuinely impressive. You demoed it on Monday and a colleague asked whether they could borrow it. - [Video: The singularity is here! Now what?](https://troels.im/v/the-singularity-is-here-now-what) - The singularity is here? Or is it? How do we tell? And what should do if it is true? - [Article: Vibe Engineering ≠ Prompt and Pray: Why AI + Structure = Speed](https://troels.im/blog/vibe-engineering-prompt-and-pray-why-ai-structure-speed) - The common wisdom says AI removes boilerplate. That's backwards. AI + Boilerplates + strong error checking = Accelerated workflow. Rust's compiler catches AI mistakes at compile time. The industry is shifting from vibe coding to context engineering. Structure doesn't slow AI down — it makes it reliable. - [Article: The AI-Augmented Developer's Rust Series](https://troels.im/blog/the-ai-augmented-developer-s-rust-series) - After a year of intensive AI-assisted development — hundreds of coding sessions, thousands in API costs, production systems shipped — one pattern kept emerging: the developers shipping fastest weren't using cleverer prompts. They were using tools that caught mistakes before production. Today I'm releasing The AI-Augmented Developer's Rust Series: two volumes teaching full-stack Rust development specifically for developers using AI coding assistants. Volume 1 covers Rust fundamentals through the lens of AI-augmented development. Volume 2 builds a complete Ethereum wallet with Yew (WebAssembly) and Axum. Studies show up to 40% of AI-generated code contains bugs. Rust's compiler catches these at compile time — memory safety issues, data races, unhandled errors. Google's data shows 1000x fewer memory vulnerabilities and 4x lower rollback rates. The bundle is $47. Buy once, own forever. - [Article: $5k Spent on AI Coding: What Actually Works (And What Doesn't)](https://troels.im/blog/5k-spent-on-ai-coding-what-actually-works-and-what-doesn-t) - After investing over $5,000 in AI-assisted development, I've learned what marketing doesn't tell you: the $20/month pricing is fiction for professional use. My $200 weekend with the Zed agent taught me that autonomous AI is powerful but expensive. Hand-optimized workflows can keep API costs around $75/month, but Claude Code's $200/month subscription delivers better productivity for serious development work. Key insights from real-world usage: - Budget $100-200/month minimum for professional AI coding (not $20) - Agents consume tokens 10x faster than manual workflows - Iteration speed matters more than prompt engineering - The 15-second feedback loop rule maximizes AI tool effectiveness - Context management beats raw model capabilities The investment is worth it. AI coding tools have genuinely transformed my productivity—not by replacing skills, but by handling mechanical work while I focus on architecture and problem-solving. But you need realistic expectations about costs and capabilities. - [Article: Why Rust Is the Perfect Language for AI-Assisted Development](https://troels.im/blog/why-rust-is-the-perfect-language-for-ai-assisted-development) - Google's Android team has revealed compelling data showing that Rust achieves a 1000x reduction in memory safety vulnerabilities compared to C/C++, with 4x lower rollback rates and 25% faster code reviews—proving that safer code is also faster to ship. This data reveals why Rust is uniquely suited for AI-assisted development: its strict compiler acts as a safety net that catches AI-generated bugs at compile-time rather than in production, while its type system guides AI suggestions toward correct code. As AI coding tools accelerate development but often introduce subtle bugs and security flaws, Rust's compile-time guarantees transform the AI velocity paradox—where faster coding leads to slower shipping—into a genuine productivity multiplier that lets developers move fast while fixing things, not breaking them. - [Article: Why the Structure of AI's Output Matters](https://troels.im/blog/why-the-structure-of-ai-s-output-matters) - The order in which you structure an LLM's output fields can dramatically affect response quality—improving accuracy by 20-30% in some cases—because these models generate text autoregressively, one token at a time from left to right, meaning each token can only be influenced by what came before it, never what comes after. When you ask an LLM for structured output like JSON, putting the decision field before the reasoning field forces the model to commit to an answer prematurely and then generate justification for it, while putting reasoning first allows the model to work through the analysis and then draw a conclusion based on the reasoning it just generated. This isn't just a formatting preference—it's fundamental to how these models think, because the sequential generation process means early tokens shape the probability distribution for later tokens, and models that make premature decisions suffer from "exposure bias" where initial errors cascade through subsequent generation, making the output structure itself a critical part of the reasoning process rather than just a data formatting choice. - [Article: Cursor vs Claude Code: The Complete Developer's Guide for 2025](https://troels.im/blog/cursor-vs-claude-code-the-complete-developer-s-guide-for-2025) - Cursor and Claude Code represent two fundamentally different approaches to AI-assisted coding in 2025, with Cursor offering a familiar IDE experience through its VS Code fork that excels at rapid prototyping and visual debugging, while Claude Code operates as a powerful terminal-based CLI tool that leverages superior reasoning capabilities and 200K token context windows for complex multi-file projects. While both tools cost around $20/month, Claude Code can be up to 4x more expensive for heavy usage due to its token-based consumption model, making Cursor more cost-effective for moderate developers, though experienced programmers often prefer Claude Code's autonomous capabilities and deep codebase understanding for large-scale architectural work. The choice ultimately depends on your workflow preferences: Cursor is ideal for beginners and visual learners transitioning from traditional IDEs, while Claude Code serves power users who value terminal efficiency and advanced reasoning for complex development tasks. ## Projects - [Compound Coders](https://compoundcoders.com) - training for senior engineers working with AI coding agents. - [GitHub](https://github.com/troels-im) - public code and project context. - [YouTube](https://youtube.com/@troels-im) - videos and experiments. ## Optional - [Answers index](https://troels.im/answers/index.md) - all current agent answers. - [Full LLM context](https://troels.im/llms-full.txt) - expanded Markdown context for the site. - [Compatibility alias](https://troels.im/llm.txt) - same router content for clients that request the singular filename.