Alessio Ragni writes about product, AI, and integrations — lessons from a product career spanning LeadsBridge, Workato, and Astika.https://alessioragni.com/https://alessioragni.com/writing/my-skills-collection/https://alessioragni.com/writing/my-skills-collection/The Claude Code skills I actually kept — article drafting, a full deploy pipeline, design-system contracts, self-testing — and the one rule I use to decide when to reuse a pre-built skill versus write my own: who's going to maintain it in six months.Wed, 15 Jul 2026 00:00:00 GMTai-codingai-codingclaude-codellmmcphttps://alessioragni.com/writing/ui-thrashing-reset-protocol/https://alessioragni.com/writing/ui-thrashing-reset-protocol/When AI-driven UI coding turns into an endless loop of micro-tweaks, don't negotiate with the model — kill the session, max the thinking effort, resend everything, and let it plan without more questions.Wed, 15 Jul 2026 00:00:00 GMTai-codingclaude-codeai-codingvibe-codingllmhttps://alessioragni.com/writing/chat-cowork-or-claude-code/https://alessioragni.com/writing/chat-cowork-or-claude-code/The three tiers of working with AI — Claude chat, Claude co-work, and Claude Code — and the exact signal that tells you when it's time to move up a level.Tue, 14 Jul 2026 00:00:00 GMTai-codingllmai-codingclaude-codevibe-codinghttps://alessioragni.com/writing/pocket-ai-recorder/https://alessioragni.com/writing/pocket-ai-recorder/A physical single-button voice recorder turns my runs, my commute, and my meetings into first drafts — no subscription, and a human review still gates everything before it ships.Tue, 14 Jul 2026 00:00:00 GMTai-codingpersonalllmprototypinghttps://alessioragni.com/writing/lightweight-framework/https://alessioragni.com/writing/lightweight-framework/GSD asks a lot up front and forgets what it asked — great for serious multi-phase builds, terrible for rocket-ship mode. Here's the lightweight way of working I reach for instead: high effort, a two-item plan, round-based questions, big-bang execution, and two skills that auto-run the UAT.Mon, 13 Jul 2026 00:00:00 GMTai-codingllmai-codingclaude-codeframeworkshttps://alessioragni.com/writing/mcp-skills-commands-explained/https://alessioragni.com/writing/mcp-skills-commands-explained/A product manager's plain-language explanation of MCP, Skills, Commands, and Agents — revisited with the repo habits that came out of actually living with them: a docs folder as memory, granular Skills over plugins, CLI over MCP where it counts, and picking a model per task.Mon, 13 Jul 2026 00:00:00 GMTai-codingmcpclaude-codecursorllmai-codinghttps://alessioragni.com/writing/my-ai-coding-stack/https://alessioragni.com/writing/my-ai-coding-stack/An evolving, practical AI coding stack — ChatGPT, Cursor, Claude Code, and Lovable — updated with how I now default to the Claude Code CLI, route Opus, Sonnet, and GPT to different jobs, and why I dropped Fable.Mon, 13 Jul 2026 00:00:00 GMTai-codingai-codingclaude-codecursorllmprototypinghttps://alessioragni.com/writing/skill-that-stops-claude-forgetting-tasks/https://alessioragni.com/writing/skill-that-stops-claude-forgetting-tasks/A new skill that turns a raw, unstructured brain-dump into a forced checklist of tasks for Claude — and makes it report back exactly what it did.Mon, 13 Jul 2026 00:00:00 GMTai-codingllmai-codingclaude-codeprototypinghttps://alessioragni.com/writing/stop-comparing-llms-one-shot/https://alessioragni.com/writing/stop-comparing-llms-one-shot/One-shot prompt comparisons between LLMs are everywhere right now, and they're useless. The problem isn't the model — it's that nobody bothered to write a spec.Mon, 13 Jul 2026 00:00:00 GMTai-takesllmproduct-managementculturehttps://alessioragni.com/writing/fable-vs-opus-token-budget/https://alessioragni.com/writing/fable-vs-opus-token-budget/I burned through two paid Max accounts in three days switching to Fable. Here's why I went back to Opus, and where Sonnet actually wins.Thu, 09 Jul 2026 00:00:00 GMTai-codingllmai-codingclaude-codehttps://alessioragni.com/writing/acceptance-criteria-before-ai/https://alessioragni.com/writing/acceptance-criteria-before-ai/A short AI-coding tip: write your acceptance criteria and tests during the plan, before any code gets written — so you never miss a requirement, and AI can test itself.Sat, 30 May 2026 00:00:00 GMTai-codingllmai-codingvibe-codingprototypinghttps://alessioragni.com/writing/let-ai-test-its-own-work/https://alessioragni.com/writing/let-ai-test-its-own-work/The practice I use to have Claude Code test its own work with a UAT file, Playwright, and per-persona .env credentials — then ask it to fix what it finds and retest, almost on its own.Sat, 30 May 2026 00:00:00 GMTai-codingllmai-codingclaude-codeprototypinghttps://alessioragni.com/writing/one-database-one-repo/https://alessioragni.com/writing/one-database-one-repo/A multi-repo split I made for scalability reasons turned into duplicated code and handover files. My rule now: one database, one repo, period.Sat, 30 May 2026 00:00:00 GMTai-codingllmai-codingprototypingintegrationhttps://alessioragni.com/writing/prompt-in-your-own-language/https://alessioragni.com/writing/prompt-in-your-own-language/Prompting an LLM in English when it's not your native language adds a translation layer between your thinking and the model — switch to your own language and that layer disappears.Sat, 30 May 2026 00:00:00 GMTai-codingllmai-codingculturehttps://alessioragni.com/writing/let-them-go/https://alessioragni.com/writing/let-them-go/Personal reflections on letting people go, being let go, and knowing when to leave a company yourself, drawn from the author's PM career.Tue, 26 May 2026 00:00:00 GMTcareersfiringcareersteamsleadershiphttps://alessioragni.com/writing/ai-in-the-middle-of-conversation/https://alessioragni.com/writing/ai-in-the-middle-of-conversation/A WhatsApp voice message and an old failed startup called Alfred got me thinking: what if AI sat between every sender and every receiver, translating each message into the style the other person actually wants?Thu, 14 May 2026 00:00:00 GMTai-takesllmcultureproduct-managementhttps://alessioragni.com/writing/git-github-for-llm-users/https://alessioragni.com/writing/git-github-for-llm-users/A plain-language glossary and workflow guide to Git and GitHub for non-developers using AI coding tools.Wed, 13 May 2026 00:00:00 GMTai-codingvibe-codingai-codingclaude-codecursorhttps://alessioragni.com/writing/gsd-framework-deep-dive/https://alessioragni.com/writing/gsd-framework-deep-dive/A deep dive into the GSD plugin for structuring multi-phase software projects with LLMs, from planning to autonomous execution and testing.Wed, 13 May 2026 00:00:00 GMTai-codingvibe-codingai-codingclaude-codeframeworksprototypinghttps://alessioragni.com/writing/three-modes-vibe-coding/https://alessioragni.com/writing/three-modes-vibe-coding/Three modes of AI coding—auto-edit, planning, and GSD—and how matching the mode to the task drives better results without an engineering team.Wed, 13 May 2026 00:00:00 GMTai-codingvibe-codingai-codingclaude-codecursorprototypinghttps://alessioragni.com/writing/context-is-everything-ai-coding/https://alessioragni.com/writing/context-is-everything-ai-coding/Why saturating a coding agent's context window quietly wrecks its output, and the docs/backlog/handover system I use to give agents real memory across a multi-repo project.Sat, 09 May 2026 00:00:00 GMTai-codingllmai-codingclaude-codeprototypinghttps://alessioragni.com/writing/llms-dont-hallucinate-show-work/https://alessioragni.com/writing/llms-dont-hallucinate-show-work/The reframe that changed how I use AI for anything serious: it's not that the LLM hallucinates, it's that you never asked it to expand its context and prove its work. Here's why it happens — limited context, embeddings picking the closest match instead of the exact truth — and the two-step trick that kills most of it: expand the context, then demand proof for every sentence.Sat, 09 May 2026 00:00:00 GMTai-codingllmai-codingprototypinghttps://alessioragni.com/writing/permission-modes-for-ai-coding/https://alessioragni.com/writing/permission-modes-for-ai-coding/Bypass, auto-edit, and planning are three different gears in Claude Code, not one setting — and knowing when to shift into planning is what saved a deploy bug I couldn't fix any other way.Sat, 09 May 2026 00:00:00 GMTai-codingllmai-codingclaude-codeprototypinghttps://alessioragni.com/writing/transparency-vs-trust/https://alessioragni.com/writing/transparency-vs-trust/A critique of companies that claim transparency as a core value, arguing for being imperfect, candid, and human-first instead, with fact-based feedback.Tue, 28 Apr 2026 00:00:00 GMTunfilteredleadershipfeedbackculturelayoffshttps://alessioragni.com/writing/better-way-layoffs/https://alessioragni.com/writing/better-way-layoffs/A plea to leaders to handle layoffs with honesty, real reasons, time, and help, and advice for those laid off to treat their career like a solo company.Tue, 14 Apr 2026 00:00:00 GMTcareerslayoffsleadershipfeedbackcareershttps://alessioragni.com/writing/ai-poc-vs-product/https://alessioragni.com/writing/ai-poc-vs-product/Why mistaking an AI proof of concept for a production-ready product creates false time estimates and integration problems, and how teams should use AI better.Tue, 31 Mar 2026 00:00:00 GMTai-takesvibe-codingai-codingprototypingproduct-managementhttps://alessioragni.com/writing/faster-than-ai-prototype/https://alessioragni.com/writing/faster-than-ai-prototype/Why validating an idea directly with real customers as a hidden service beats jumping straight into AI-built prototypes.Tue, 17 Mar 2026 00:00:00 GMTproductvibe-codingprototypingbuild-vs-buyproduct-managementhttps://alessioragni.com/writing/ai-wont-save-us/https://alessioragni.com/writing/ai-wont-save-us/AI hype hides the hard work of real products; designers, PMs, and engineers are still needed because making something great is the difficult 90 percent.Tue, 03 Mar 2026 00:00:00 GMTai-takesllmproduct-managementprototypinghttps://alessioragni.com/writing/when-chatgpt-is-not-enough/https://alessioragni.com/writing/when-chatgpt-is-not-enough/Planning an XTerra triathlon revealed why ChatGPT struggles with long projects, and how moving to Claude Code with files and MCP fixed memory and dates.Sun, 22 Feb 2026 00:00:00 GMTai-codingllmclaude-codemcpcursorhttps://alessioragni.com/writing/vibe-coding-master/https://alessioragni.com/writing/vibe-coding-master/A first-person account of building a full-stack app in six hours with AI tools, plus the engineering mindset and patterns that made it work.Tue, 17 Feb 2026 00:00:00 GMTai-codingvibe-codingai-codingcursorprototypinghttps://alessioragni.com/writing/ai-wont-replace-you/https://alessioragni.com/writing/ai-wont-replace-you/Treating AI as a collaborative companion rather than a one-shot replacement, and recognizing its limits to work faster and stay ahead.Tue, 03 Feb 2026 00:00:00 GMTai-takesllmai-codingcursorhttps://alessioragni.com/writing/schools-missing-ai-opportunity/https://alessioragni.com/writing/schools-missing-ai-opportunity/A personal argument that schools should embrace AI to personalize learning for each child, using a five-step study framework as an example.Sun, 25 Jan 2026 00:00:00 GMTai-takesllmframeworksculturehttps://alessioragni.com/writing/over-ownership-problem/https://alessioragni.com/writing/over-ownership-problem/How over-ownership backfired when a PM overstepped his scope, and a framework for involving stakeholders and documenting business cases properly.Tue, 13 Jan 2026 00:00:00 GMTproductownershipproduct-managementleadershipframeworkshttps://alessioragni.com/writing/why-italians-drink-coffee/https://alessioragni.com/writing/why-italians-drink-coffee/A personal reflection on the reasons behind drinking coffee: welcoming others, ritual and focus, work habits, and a feeling of freedom.Tue, 30 Dec 2025 00:00:00 GMTunfilteredculturepersonalhttps://alessioragni.com/writing/facts-vs-projections/https://alessioragni.com/writing/facts-vs-projections/A principle for separating objective facts from the opinions and expectations layered on top, applied to work decisions and relationships.Tue, 16 Dec 2025 00:00:00 GMTproductframeworksfeedbackleadershipculturehttps://alessioragni.com/writing/engineers-fighting-product/https://alessioragni.com/writing/engineers-fighting-product/When engineers fight for your product vision it signals trust, a compelling vision, and true ownership, and what to ask when your team isn't there yet.Tue, 02 Dec 2025 00:00:00 GMTproductteamsleadershipproduct-managementownershiphttps://alessioragni.com/writing/job-finding-framework/https://alessioragni.com/writing/job-finding-framework/A personal, step-by-step framework for finding a job, covering positioning, application quotas, customization, storytelling, and salary negotiation.Tue, 25 Nov 2025 00:00:00 GMTcareerscareersframeworkshiringhttps://alessioragni.com/writing/meeting-documentation/https://alessioragni.com/writing/meeting-documentation/Why writing down and agreeing on meeting decisions prevents repeated discussions, using an offsite lesson and divergent-convergent thinking as examples.Tue, 18 Nov 2025 00:00:00 GMTproductmeetingsframeworksteamshttps://alessioragni.com/writing/feedback-not-enough/https://alessioragni.com/writing/feedback-not-enough/A situation-action-consequence model for giving feedback that is specific, fact-based, and actually useful instead of generic praise.Tue, 04 Nov 2025 00:00:00 GMTproductfeedbackleadershipframeworksculturehttps://alessioragni.com/writing/sprinter-vs-coach/https://alessioragni.com/writing/sprinter-vs-coach/A sprinter-versus-coach mental model for clarifying PM and developer responsibilities, and why AI will shift the ratio toward more coaches.Tue, 21 Oct 2025 00:00:00 GMTproductteamsproduct-managementframeworksleadershiphttps://alessioragni.com/writing/ipaas/https://alessioragni.com/writing/ipaas/A first-hand account of the build-vs-buy integration tradeoff and a breakdown of the iPaaS landscape into key categories for SaaS product leaders.Tue, 07 Oct 2025 00:00:00 GMTproductipaasbuild-vs-buysaasintegration