# productized.tech

> Michael Diestelberg’s personal site: writing, projects, AI model portfolios, curated links, and product-building resources.

Read the linked Markdown directly, or request the HTML page URL with Accept: text/markdown. Markdown includes canonical HTML URLs for citations.

WebMCP: search_site finds editorial content. On /models, find_models and compare_models filter and compare portfolios. On /signals, search_signals and get_signal explore the live archive.

## Start here

- [About Michael Diestelberg](https://productized.tech/about.md): My path from curious kid to product lead and builder.
- [Tech Stack](https://productized.tech/techstack.md): The tools I'm using as my default, and the alternatives I find interesting enough to keep close.
- [Writing](https://productized.tech/writing/index.md): Articles by Michael Diestelberg.
- [Building](https://productized.tech/building/index.md): Projects and things I have built.
- [Models](https://productized.tech/models/index.md): Model portfolios, specifications, and published outputs.
- [Signals](https://productized.tech/signals/index.md): Curated links and saved X posts.
- [productized.tech](https://productized.tech/index.md): Michael Diestelberg — Product Builder · Software Enthusiast

## Writing

- [Introducing ‘Mäuse’: An Expense Tracker for Couples](https://productized.tech/writing/introducing-maeuse-an-expense-tracker-for-couples.md): Mäuse is a local-first expense tracker for couples — capture costs by voice or manually, split them fairly, and settle up at month’s end. Free, open source, and on the App Store.
- [My Tech Stack - July 2026](https://productized.tech/writing/my-tech-stack-july-2026.md): A July 2026 snapshot of the tools I'm using, the ones I'm testing, and the products I'm keeping an eye on.
- [The Innovation Launchpad That Lets Non-Engineers Build Real Apps](https://productized.tech/writing/the-innovation-launchpad-that-lets-non-engineers-build-real-apps.md): How an internal innovation launchpad helps people across the company turn product instincts into working apps, giving customer-facing teams and operators a direct way to shape what gets built.
- [Building My Own Productivity Voice Agent](https://productized.tech/writing/building-my-own-productivity-voice-agent.md): Voice-native AI is shaping up to be one of the biggest opportunities in productivity software. Here's why OpenAI is uniquely positioned to win it, and what I learned building my own version.
- [ChatGPT Agents: When Every Agent Gets Its Own Computer](https://productized.tech/writing/chatgpt-agents-when-every-agent-gets-its-own-computer.md): ChatGPT Agents is a public preview of OpenAI's larger agent platform strategy: every useful agent needs either your computer or its own.
- [It doesn't have to be OpenClaw: Using Claude via Telegram](https://productized.tech/writing/it-doesnt-have-to-be-openclaw-using-claude-via-telegram.md): Anthropic shipped an official Telegram channel for Claude Code. It's more polished than the DIY OpenClaw-style setups, simpler to configure, and uses the Claude subscription you already pay for.
- [Building AI Agents? The AI Is the Easy Part.](https://productized.tech/writing/building-ai-agents-the-ai-is-the-easy-part.md): The models are smart enough. The hard part is everything you build around them — identity, cognition, agency, and interface. A framework for thinking about what actually makes agents work.
- [From Feedback to Feature in Minutes](https://productized.tech/writing/from-feedback-to-feature-in-minutes.md): How connecting in-app prototype feedback to an AI coding agent compresses the iteration cycle from days to minutes.
- [The Age of Mass Intelligence](https://productized.tech/writing/the-age-of-mass-intelligence.md): I ran a 3‑AI experiment after reading Ethan Mollick on "Mass Intelligence." Asked Claude, ChatGPT, and Gemini the same big questions—then compared how each imagines our future. My takeaways and a clear favorite emerge.
- [How to Communicate Better (as a Product Manager)](https://productized.tech/writing/how-to-communicate-better-as-a-product-manager.md): This post highlights why clear communication is essential for Product Manager success and shares actionable advice from entrepreneur Wes Kao's conversation on Lenny's Podcast. Learn specific frameworks to improve your clarity, influence, and impact, based on notes from the episode "Become a Better Communicator".
- [Google Gemini](https://productized.tech/writing/google-gemini.md): Despite less initial buzz compared to competitors, Google's Gemini is poised to dominate due to its mission alignment, tool integrations, vast distribution, search dominance, rapid development, and deep user data access.
- [Productizing AI Technology](https://productized.tech/writing/productizing-ai-technology.md): About the arms race in AI technology and how productizing it just started
- [Why I Write](https://productized.tech/writing/why-i-write.md): Why writing is an essential part of my thinking
- [Maker Time vs. Manager Time](https://productized.tech/writing/maker-time-vs-manager-time.md): Solving the time struggle of the knowledge worker

## Building

- [Insights from Podcasts](https://productized.tech/building/insights-from-podcasts.md): An interactive terminal app to download podcasts, create transcripts and generate insights from those podcasts.

## Collection

- [Building Agents: The Loop](https://productized.tech/the-ai-enabled-product-builder/agent-loop.md): Understand the core loop behind modern AI agents: how models reason, request tools, add results to context, and repeat until they can answer.
- [Bring Your Ideas to Life: Vibe Coding for Product Builders](https://productized.tech/the-ai-enabled-product-builder/vibe-coding.md): Learn how to use AI to build working software through natural language. Vibe coding is the most effective method to bring your product ideas to life.
- [Never Lose an Idea Again: My AI Voice-to-Notes System](https://productized.tech/the-ai-enabled-product-builder/voice-to-notes.md): Capture ideas at the speed they arrive and turn raw voice notes into structured memos using AI-native workflows.
- [Share Your Ideas: Workshop Your Product One-Pagers with AI](https://productized.tech/the-ai-enabled-product-builder/idea-to-product-one-pager.md): Turn scattered ideas into structured product one-pagers through AI-guided workshopping that forces clarity before you invest weeks of effort.
- [Define What You’re Building: Create PRDs with AI as Your Thinking Partner](https://productized.tech/the-ai-enabled-product-builder/workshop-prd-with-ai.md): Spend more time defining what you're building before you build it. Use AI as your thinking partner to workshop requirements and create structured PRDs.
- [The AI-enabled Product Builder](https://productized.tech/the-ai-enabled-product-builder/index.md): Resources, tools, and workflows for product builders.

## Models

- [Gemini 3.8 Flash](https://productized.tech/models/gemini-3-8-flash.md): Google’s high-efficiency Gemini 3 workhorse, bringing Pro-level agentic coding and multimodal execution to the Flash tier.
- [Muse Spark 1.3](https://productized.tech/models/muse-spark-1-3.md): Meta’s multimodal reasoning model for long-horizon agentic and coding workflows, with stronger first-attempt accuracy and cleaner tool use.
- [Claude Fable 5.1](https://productized.tech/models/claude-fable-5-1.md): Anthropic’s update to Fable 5, improving long-running agentic coding, knowledge work, research, and precise unattended execution.
- [DeepSeek V4 Flash Vision Exp](https://productized.tech/models/deepseek-v4-flash-vision-exp.md): DeepSeek’s experimental vision add-on to V4 Flash 0731, adding image understanding while matching the base model on text, agents, and reasoning.
- [Ox Alpha](https://productized.tech/models/ox-alpha.md): A stealth reasoning model on OpenRouter, built for coding and long-horizon agent work, currently free while the vendor stays unnamed.
- [GLM-5.3](https://productized.tech/models/glm-5-3.md): Z.ai’s latest flagship, post-trained from the GLM-5.2 base for complex coding and long-horizon agent work.
- [Gemini 3.7 Flash](https://productized.tech/models/gemini-3-7-flash.md): Google’s latest Flash workhorse, shipped three weeks after 3.6 with stronger coding and agent performance.
- [DeepSeek V4 Pro](https://productized.tech/models/deepseek-v4-pro-0813.md): DeepSeek’s flagship V4 model, now generally available with stronger agent performance as the 0813 checkpoint.
- [Grok 4.6](https://productized.tech/models/grok-4-6.md): xAI’s follow-up to Grok 4.5, tuned for long-running agents and more ambitious interactive and visual work.
- [DeepSeek V4 Flash](https://productized.tech/models/deepseek-v4-flash-0731.md): DeepSeek’s cost-efficient V4 workhorse, re-post-trained for agents as the official 0731 checkpoint.
- [Gemini 3.6 Flash](https://productized.tech/models/gemini-3-6-flash.md): Google’s more token-efficient successor to 3.5 Flash, built for coding, knowledge work, and multimodal agents.
- [Kimi K3](https://productized.tech/models/kimi-k3.md): Moonshot AI’s 2.8T-parameter flagship — native vision, a 1M-token context, and the first open 3T-class model.
- [GPT-5.6 Sol Pro](https://productized.tech/models/gpt-5-6-sol-pro.md): OpenAI’s flagship GPT-5.6 Sol in pro reasoning mode — the highest-capability option for difficult, longer-running work.
- [Grok 4.5](https://productized.tech/models/grok-4-5.md): xAI’s coding- and agent-focused frontier model that made xAI a serious contender in the AI space.
- [Gemini 3.5 Flash](https://productized.tech/models/gemini-3-5-flash.md): Google’s I/O 2026 Flash model — frontier agent and coding performance at Flash speed, with a 1M-token context.