
📚 Looking for a developer roadmap? Here are 5 FREE Notion templates: 🎨 Frontend ⚙️ Backend 🖥️ Full-Stack 🔬Machine-Learning 🚄 Data-Eng 📦 83 resources, 40 tasks, 40 Cheat Sheets and 500+ practice questions! sesigl.gumroad.com/l/ULTIMAT…

Engineering leader, ex @eBay | Trying to find PMF in education | Free coaching for devs | The Notion learning packs guy | Dad | Marathonist

📚 Looking for a developer roadmap? Here are 5 FREE Notion templates: 🎨 Frontend ⚙️ Backend 🖥️ Full-Stack 🔬Machine-Learning 🚄 Data-Eng 📦 83 resources, 40 tasks, 40 Cheat Sheets and 500+ practice questions! sesigl.gumroad.com/l/ULTIMAT…

💯 This is the part people miss when they say engineering is dying. I barely read diffs line by line anymore. But I spend more time than ever on: - system and contract tests that define what „done“ means - one pass per concern: security, concurrency, performance - boundaries for what agents can merge on their own - cleaning up after merge Reviewing verification instead of code is still engineering. Maybe even more of it. What's the one concern you'd never hand over to an agent? 👇
Disengaging from syntax is not disengaging from engineering. I’m working on a significant project at the moment. It’s in a pre-production state so far. More than a prototype, less than ready for real users. I’ve been making multiple passes over the structure for each of the following concerns: Architecture, coverage, race & concurrency, security, API, etc. Each of these requires significant interrogation and review of verification procedures; but not review of the code. At base are the /ub-mode (GitHub.com/unclebob) rules that keep the agents disciplined as far as coding structure and tests are concerned. But above that it’s me making sure that all the bases are covered well enough to keep my client safe from stupid sloppy mistakes. I am the engineer. I am responsible. The agents are just my tools. They are power tools, to be sure. But power tools in the hands of novices result in missing fingers. So I am very careful.


Your RAG pipeline searches with vectors. So why do so many teams add a keyword formula from the 90s back in? Because sometimes the exact word matters. I'm building search up from the basics, step by step. Part 3 is about BM25: 👇 link in the comments

Once you let an AI agent (successfully) book a trip for you, it’s an incredible relief. A few reasons why: - Public transport UX is usually horrible Comparing different routes and options takes way more time than I want to spend - Personal stats, like how often I actually cancel a trip, can help decide between a cheap non-refundable ticket and a flexible one It’s also great to see how securely modern systems handle this: payment methods are safely stored, but a 2FA prompt is still required to confirm the charge. The perfect human-in-the-loop approval. Good times to be alive 🙌 What has your experience been with personal AI assistants?

Here it is: github.com/sesigl/software-e… Install in Claude Code: /plugin install software-engineering-skills --marketplace sesigl/software-engineering-skills Then just say: "teach me <anything>"

👨🏫AI is the best teacher on earth. Always available. Infinitely patient. Speaks your language. Never tired of "but why?" But by default, it lectures, and looses me half way. So I built a better teach-me skill: 1. Derives from your context of interview first, or rather be concise and not disrupt your flow 2. Starts with the problem 3. One step at a time, layer by layer 4. Feeding it back and a quiz option for more sophisticated learning goals Bonus: works even better if you use your voice instead of typing. Free, MIT. Link 👇

Here it is: github.com/sesigl/software-e… Install in Claude Code: /plugin install software-engineering-skills --marketplace sesigl/software-engineering-skills It also adapts the setup for Codex, Cursor, Copilot, and Gemini CLI. Evals with vs. without the skill are in the README.

Every new repo: re-prompt the same agent setup, forget half of it, and find out the best practices changed again. I put it into a skill instead: 1. Interviews you first 2. Scaffolds specs, rules, guardrails 3. Best practices change? Update the skill once MIT licensed, Claude Code marketplace ready. Link in comments 👇

Great line from the CTO of Proton. I’m paraphrasing and stealing it : Your job is not to use agents to help you write code. Your job is to lead the agents to help them write code.

for claude code users: consider enabling automatic updates after install to always stay up2date.

Free and open source. It works with Claude Code, Cursor, Codex, and OpenCode. Claude Code: /plugin marketplace add sesigl/software-engineering-skills /plugin install software-engineering-skills Other tools: npx skills add sesigl/software-engineering-skills Then say: "walk me through PR #123" github.com/sesigl/software-e…

For crucial PRs, "the AI approved it" is not enough. A human must understand it. I built a skill that walks you through a PR: 1. Why it exists 2. A short map 3. One stop at a time Human + AI = superintelligence 🧠🤖 MIT licensed, Claude Code marketplace ready. Link in comments 👇

💯 Measure before you split. I ran Opus 5.5 with and without Haiku subagents on a real work task: - 48:02m → 29:35m - $10.51 → $6.91 - correctness 6/10 → 5/10 Faster and cheaper, but not for free. Subagents for simple, parallel work. Hard problems stay in the main loop. How do you decide? 👇 x.com/addyosmani/status/2114…
Before adding another subagent ask what problem it's solving. A bloated system prompt is often the issue. Skills and tool search can fix that without splitting context across agents. My rule of thumb is to keep a subagent when the work is parallel, needs fresh context or one agent really can't pick the right tools. Otherwise, fold it into the main loop, turn its prompt into a skill, run your evals and keep whatever wins. Good write-up: claude.com/resources/article…

Your AI agent can ship code. Can it also reduce your family’s bills? I think personal assistants are one of the most underrated uses of AI. We spend hours optimizing development workflows. Meanwhile, insurance documents, tax prep and planning the next family vacation still eat our evenings. Here are 8 ways I use AI to reduce family spending and free up time: 1. Organize finances and insurance Ask your agent to find and organize your documents in cloud storage. Give it scoped access to incoming documents so new ones land where they belong. Sounds boring. But this becomes the foundation for almost everything else. 2. Make tax prep less painful Once your documents are organized, AI can help find missing receipts, review potentially relevant expenses and prepare information for your tax return. Much easier than starting with a folder full of “scan_final_2.pdf”. 3. Find supermarket discounts worth using Teach your assistant what your family actually buys. Let it check offers and build a shopping list around useful discounts. A discount on something you never needed is still spending. Start with suggestions. Add purchasing permissions only when you trust the workflow. 4. Keep health information organized Keep health records, test results and notes in one place. Use AI to prepare questions for appointments, summarize changes and help with scheduling. I want to arrive better prepared and have useful context available when talking to a doctor. 5. Find benefits and reimbursements Subsidies, insurance reimbursements, local programs. There are opportunities you probably don’t know about. I recently discovered I could get 50% back on a battery repair. Let your assistant check relevant programs, flag what might apply and help with the paperwork. 6. Plan the weekend Every week, the same question: what could we do with the family? Weather, nearby events, our calendar, travel time and what our kid enjoys. A Friday email with three realistic options already saves a surprising amount of mental effort. 7. Support your training Connect your activity data and share your goals. Use your assistant to draft training plans, check in regularly and adjust around your actual schedule. The interesting part is continuity. What worked last month? What did you skip? What fits this week? 8. Plan vacations ahead With kids, “let’s book something” quickly becomes a constraint problem. Dates, travel time, budget, accommodation, activities. Teach your assistant your preferences and let it shortlist options, compare total costs and track prices. You still decide. You have less homework. What makes this interesting to me is the compound effect. Organized documents make tax prep easier. Saved preferences make the next vacation search faster. Feedback makes weekend suggestions more useful. The value grows when you stop explaining everything from scratch. But before connecting your whole life, apply the same engineering judgment you would at work: - Understand where your data goes, how the provider uses it and what a breach would expose. - Keep documents and useful context in storage you control and trust. If your assistant disappears tomorrow, you should be able to replace it. - Use dedicated accounts and scoped tokens. Give each workflow only the access it needs. - Separate suggestions from actions. Reading an offer, booking a trip and submitting a tax return need different levels of control. - Think through failure modes. What could go wrong, how would you notice and could you undo it? Pick tools that fit your expertise and risk tolerance. Start with one recurring task and make it reliable. Saving a few hours and reducing recurring bills matters, especially when work and family already fill the week. What have you delegated to a personal agent that actually made your life easier? Share it below 👇

Everyone is talking about AI, which involves: search, embeddings, and sorting. But how does that actually work? What if the perfect result are never shown to you or your agent? No AI model can leverage what it never sees. I’m starting a series on how search actually works, from simple keyword matching to modern AI-powered search. Part 1: Find the words, then sort by date. Let’s start with the basics. sebastiansigl.com/blog/searc…