Writing on developer experience, AI-accelerated engineering, and composable platforms.https://timbenniks.deven-ushttps://timbenniks.dev/writing/i-thought-everyone-was-building-tools-for-themselveshttps://timbenniks.dev/writing/i-thought-everyone-was-building-tools-for-themselvesAt ContentCon, I realised building tools for yourself still feels unfamiliar to many developers. Coding agents help, but finding a starting point matters too.Mon, 05 Oct 2026 10:00:00 GMTai-engineeringcraftdeveloper-experiencedevrelhttps://timbenniks.dev/writing/building-mcp-profile-hub-part-3-when-more-reasoning-makes-the-agent-worsehttps://timbenniks.dev/writing/building-mcp-profile-hub-part-3-when-more-reasoning-makes-the-agent-worseThis article explores an unexpected result from evaluating Contentstack’s MCP Profile Hub, where increasing a model’s reasoning effort made straightforward CMS agent tasks slower and less reliable. While enriching tool definitions with account-specific context clearly reduced tool calls, latency, and reasoning tokens, turning up the reasoning setting caused the model to distrust simple, correct tool responses and invent extra work. A control task listing global fields showed high-effort runs repeatedly ignoring a perfect API answer and exhausting their turn budget. The piece argues that reasoning effort must match the shape of the work, that bounded API operations often benefit from lower reasoning, and that agent evaluations should measure behaviour—calls, latency, traces, and early stopping—rather than abstract “intelligence” alone.Wed, 09 Sep 2026 10:00:00 GMTaiapicmscomposablearchitecturewebdevperformancehttps://timbenniks.dev/writing/skills-over-mcp-explainedhttps://timbenniks.dev/writing/skills-over-mcp-explainedHow the new MCP Skills Extension works, from skill discovery and on-demand loading to content verification, workflow guidance, and managed profiles.Mon, 07 Sep 2026 10:00:00 GMTcomposable-architectureai-engineeringapi-designdeveloper-experienceproduct-strategyhttps://timbenniks.dev/writing/building-mcp-profile-hub-part-2-one-mcp-server-is-the-wrong-abstractionhttps://timbenniks.dev/writing/building-mcp-profile-hub-part-2-one-mcp-server-is-the-wrong-abstractionThis article argues that a single, monolithic MCP server per platform is the wrong abstraction, especially for complex systems like Contentstack. Instead, it introduces managed profiles as the right unit of configuration, aligned to jobs, teams, or access boundaries rather than product catalogs. Each managed profile bundles a curated set of tools, Automations, and agents, enriched with account context, while still respecting individual user identities and permissions. Profiles can only narrow what a user can do, never expand their underlying platform permissions. This makes configurations easier to reason about, review, audit, and replicate across environments, and offers a scalable pattern for enterprise platforms with many roles and capabilities.Fri, 04 Sep 2026 10:00:00 GMTcomposable-architectureai-engineeringapi-designfrontendproduct-strategyhttps://timbenniks.dev/writing/building-mcp-profile-hub-part-1-stop-making-the-agent-askhttps://timbenniks.dev/writing/building-mcp-profile-hub-part-1-stop-making-the-agent-askIntroducing MCP Profile Hub. I explain why enriching tool definitions with tenant-specific context dramatically improves agent performance. Instead of exposing generic CMS tools that force models to discover content types, environments, locales, and branches through multiple lookup calls, Profile Hub injects real account data directly into JSON Schemas as enums, defaults, and descriptions. This reduces tool calls, latency, and reasoning tokens while avoiding misleading examples and invalid defaults. The piece also covers the production engineering behind enrichment, how Automations and Agent OS agents are exposed as high-level deterministic tools, and why reusable HTTP-based tool definitions let teams run their own MCP runtimes. The core takeaway is that fewer, richer, context-aware tools beat large generic catalogs for real-world agent workflows.Mon, 31 Aug 2026 10:00:00 GMTcomposable-architectureai-engineeringapi-designfrontendproduct-strategyhttps://timbenniks.dev/writing/claude-desktop-mcp-lifecycle-is-brokenhttps://timbenniks.dev/writing/claude-desktop-mcp-lifecycle-is-brokenClaude Desktop currently launches duplicate local MCP stdio servers for a single configuration, causing two independent OAuth flows, extra browser tabs, and unnecessary resource usage. The bug is masked once credentials are cached, so it silently persists in production while still spawning two processes every time. This is not an mcp-remote or external service issue but a host-level lifecycle problem, likely caused by overlapping legacy and new MCP managers and poor observability for one of the processes. Workarounds like pre-authenticating with mcp-remote mitigate UX pain but do not fix the duplication. The article argues that open-source tools should not shoulder complex coordination logic just to survive a major desktop app’s sloppy process management.Mon, 24 Aug 2026 10:00:00 GMTcomposable-architectureai-engineeringperformancecloud-infrafrontendhttps://timbenniks.dev/writing/buy-the-plumbing-vibe-the-resthttps://timbenniks.dev/writing/buy-the-plumbing-vibe-the-restAI makes it tempting to cancel SaaS tools and prompt your own internal platforms into existence, but that often creates brittle systems that are “a mile wide and an inch deep.” Performance, security, and edge cases quickly become serious problems, and suddenly your team is doing database administration and security engineering instead of solving business problems. A better pattern is to buy robust, headless infrastructure for the hard, invisible parts (content, data, security, scaling) and then use AI to build bespoke experiences on top. With a solid SDK and stable backend services, AI tools like Claude can safely orchestrate UI and workflows instead of guessing at architecture. Pay for the plumbing, and vibe on the interface layer where your differentiation really lives.Sat, 22 Aug 2026 10:00:00 GMTcomposable-architectureai-engineeringfrontenddeveloper-experiencehttps://timbenniks.dev/writing/the-doer-economy-we-are-killing-the-translator-classhttps://timbenniks.dev/writing/the-doer-economy-we-are-killing-the-translator-classThis article argues that AI is collapsing the distance between vision and execution, ushering in a Doer Economy where the primary winners are those who can both imagine and build. The traditional corporate stack of translators (product managers, marketers, and multiple layers of management) is shrinking because executional tasks are increasingly handled by AI. Founders and CEOs are moving closer to product, validating ideas directly with AI-generated scaffolds and modern SaaS primitives. For individuals, the value has shifted from narrow, ticket-driven skills to end-to-end ownership, product thinking, and understanding users. The future belongs to people who ship, iterate quickly, and leverage AI and SaaS platforms to focus on business logic and user experience, rather than those who only manage the builders.Mon, 17 Aug 2026 10:00:00 GMTcomposable-architectureai-engineeringapi-designfrontenddeveloper-experiencehttps://timbenniks.dev/writing/ten-ai-security-problems-hiding-in-plain-texthttps://timbenniks.dev/writing/ten-ai-security-problems-hiding-in-plain-textThis article argues that AI security risks extend far beyond model jailbreaks and prompt engineering, into every piece of text an AI can read. Natural language now behaves like soft code, where logs, documentation, commit messages, wikis, support tickets, web pages, PDFs, and search results can all carry hidden instructions for agents. The author walks through ten concrete scenarios where ordinary text fields become attack surfaces, often with delayed or indirect activation through internal tools and multi agent pipelines. The core message is that information and instruction have blurred, and any text accessible to AI must be treated as part of the security model. Teams need to rethink access, editing rights, retrieval, and agent capabilities accordingly.Wed, 05 Aug 2026 10:00:00 GMTcomposable-architectureai-engineeringcloud-infrafrontendproduct-strategyhttps://timbenniks.dev/writing/the-biggest-risk-to-ai-is-the-enterprise-org-charthttps://timbenniks.dev/writing/the-biggest-risk-to-ai-is-the-enterprise-org-chartThis article argues that the real risk of corporate AI is not rogue superintelligence but how large organizations deploy it, usually in service of cost-cutting rather than creating new value. Big enterprises buy AI like office furniture, wrapped in committees, procurement, and risk matrices, so it ends up optimizing ticket deflection and headcount instead of enabling innovation. The real bottleneck is bureaucracy, not intelligence. In contrast, a roughly 500-person company has enough depth to build serious systems but short enough communication paths that the person with the problem can help build the solution. AI lets domain experts prototype directly, shortening the loop between friction and fix. The key is governance that enables safe experimentation instead of vetoing it, using AI to expand reach rather than just reduce costs.Fri, 24 Jul 2026 10:00:00 GMTcomposable-architectureai-engineeringfrontendproduct-strategycareerhttps://timbenniks.dev/writing/your-linkedin-reads-like-a-robothttps://timbenniks.dev/writing/your-linkedin-reads-like-a-robotTwo free skills can strip the AI tells out of your writing in seconds. Nobody uses them. So every feed is now a slop fest of em dashes, rule-of-three lists, and It's not just X, it's Y. Here is how to spot the patterns and stop shipping them.Mon, 22 Jun 2026 10:00:00 GMTai-engineeringcraftproduct-strategycareerhttps://timbenniks.dev/writing/we-are-thinking-too-smallhttps://timbenniks.dev/writing/we-are-thinking-too-smallAI coding agents are not a threat to developer jobs, they are a fundamental shift in the economics of software creation. Just as the cloud removed the risk and capital cost of infrastructure, AI is removing the cost of writing and refactoring code. This kills the old moats that protected horizontal enterprise platforms and makes rebuilding wide, deeply integrated stacks viable. Instead of spending years stitching together narrow SaaS tools and APIs, teams can let agents generate bespoke services quickly and cheaply. The real risk is using AI only to speed up legacy glue work. Developers who win will treat the cost of reinventing the wheel as effectively zero and pursue much larger, previously impossible product ideas.Sat, 20 Jun 2026 10:00:00 GMTcomposable-architectureai-engineeringcloud-infrafrontendhttps://timbenniks.dev/writing/cursors-moathttps://timbenniks.dev/writing/cursors-moatThe interesting story about Cursor is not which base model it uses, but how deeply it sits inside real software development workflows. Unlike model labs trained only on finished code artifacts, Cursor’s IDE sees every attempt, failure, context switch, and accepted edit as developers ship real software. That environment, with multiple models competing on the same tasks, produces rich feedback signals that are closer to “which path got the work done” than traditional preference data. The piece generalizes this idea beyond coding tools, suggesting that any serious AI product should focus on generating observable traces of work, outcomes, and corrections, and treat the product workflow itself as part of the training system and long-term moat.Wed, 17 Jun 2026 10:00:00 GMTcomposable-architectureai-engineeringfrontenddevrelhttps://timbenniks.dev/writing/contentstack-launched-agent-os-axp-and-the-dev-toolshttps://timbenniks.dev/writing/contentstack-launched-agent-os-axp-and-the-dev-toolsContentstack just made Agent OS generally available, renamed the platform to AXP, and shipped a pile of developer tooling. I helped build the AI side, and I am happily biased about why this one is different.Tue, 09 Jun 2026 10:00:00 GMTcomposable-architectureai-engineeringdeveloper-experiencehttps://timbenniks.dev/writing/the-agentic-spectrum-stop-burning-tokens-on-what-a-script-can-dohttps://timbenniks.dev/writing/the-agentic-spectrum-stop-burning-tokens-on-what-a-script-can-doAI workflows sit on a spectrum, from a single LLM-assisted task to a fully autonomous agent. Most real content work belongs near the low end, yet people keep reaching for the autonomous end and paying for it in tokens.Thu, 04 Jun 2026 10:00:00 GMTai-engineeringcontent-opscloud-infrahttps://timbenniks.dev/writing/the-tool-catalog-is-the-producthttps://timbenniks.dev/writing/the-tool-catalog-is-the-productWe exposed Contentstack MCP tool definitions through a server endpoint as JSON. That sounds small, but it changes the product shape. The hosted MCP server becomes one official implementation of a reusable tool catalog, while developers can build their own MCPs with their own auth, hosting, filtering, and governance. This is what AI-first developer tooling should feel like: polished defaults on top of portable primitives.Wed, 27 May 2026 10:00:00 GMTai-engineeringapi-designdeveloper-experiencehttps://timbenniks.dev/writing/ai-will-not-live-in-one-place-but-trust-has-tohttps://timbenniks.dev/writing/ai-will-not-live-in-one-place-but-trust-has-toEnterprise AI is spreading into every tool where work happens, from IDE agents to browser assistants, but governance, spend control, and brand safety are lagging behind. This article explains a two-layer architecture for solving that tension. Off-platform AI, powered by APIs, MCP, and agent skills, acts as the reach layer that lets developers and teams experiment, prototype, and orchestrate across systems from within their preferred tools. On-platform AI, delivered through Agent OS, Polaris, and AI Credits, is the trust layer that handles permissions, spend visibility, brand context, review workflows, and auditability. Rather than choosing between open access and tight governance, enterprises should use both layers together so external AI gathers context while governed on-platform capabilities execute business-critical work safely.Mon, 18 May 2026 10:00:00 GMTcomposable-architectureai-engineeringapi-designcontent-opsfrontendhttps://timbenniks.dev/writing/the-supply-chain-backlash-will-create-worse-softwarehttps://timbenniks.dev/writing/the-supply-chain-backlash-will-create-worse-softwareSupply-chain attacks like Mini Shai-Hulud will make teams distrust third-party packages. AI makes it easy to react by generating internal replacements for dependencies, SDK helpers, workflow tools, and glue code. That feels safer, but a lot of that code will be vibe coded without threat models, tests, update paths, or security review.Wed, 13 May 2026 10:00:00 GMTcomposable-architectureai-engineeringcloud-infrafrontendproduct-strategyhttps://timbenniks.dev/writing/development-101-for-non-technical-vibe-codershttps://timbenniks.dev/writing/development-101-for-non-technical-vibe-codersWhen folks think they're failing at AI coding, they're usually failing at their laptop. Before you brief an agent well, your machine has to be a predictable place.Mon, 04 May 2026 10:00:00 GMTai-engineeringcraftdeveloper-experiencehttps://timbenniks.dev/writing/the-case-for-boring-setupshttps://timbenniks.dev/writing/the-case-for-boring-setupsMost developers overconfigure their machines and pay for it in ways they don't notice. Every custom alias, every remapped key, every hand-rolled config file is a small tax on your ability to work anywhere other than your own laptop. The same pattern is repeating right now with AI tooling, dozens of MCP servers and stacked skill files that look like leverage and behave like drag. After getting stranded by my own setups more times than I'd like to admit, I've come around to a quieter belief: portability is a skill, and defaults are how you practice it.Mon, 20 Apr 2026 10:00:00 GMTcomposable-architectureai-engineeringcloud-infrafrontenddeveloper-experiencehttps://timbenniks.dev/writing/the-vibe-coded-app-architecture-guidehttps://timbenniks.dev/writing/the-vibe-coded-app-architecture-guideThe AI builds what you describe, not what you need in production. This guide covers the full architecture stack for vibe-coded apps - auth, database security, secrets, GDPR, audit logging, rate limiting, and dependencies - so you can ship fast and stay solid.Thu, 16 Apr 2026 10:00:00 GMTcomposable-architectureai-engineeringcloud-infradeveloper-experiencehttps://timbenniks.dev/writing/i-will-not-log-into-your-vibe-coded-apphttps://timbenniks.dev/writing/i-will-not-log-into-your-vibe-coded-appVibe coding has made it trivially easy to spin up apps that collect user data, handle logins, and store sensitive information. The problem is that most people building these apps have no idea how authentication, database security, or data protection actually work. Defaults on services like Supabase and Firebase are dangerously permissive, GDPR obligations are being ignored entirely, and users are handing credentials to apps built by people who have never heard of row level security. My personal rule now is simple. If it looks vibe coded and asks for username and password, I walk away.Tue, 14 Apr 2026 10:00:00 GMTcomposable-architectureai-engineeringcloud-infrafrontendproduct-strategyhttps://timbenniks.dev/writing/most-cms-migrations-fail-before-the-first-record-moveshttps://timbenniks.dev/writing/most-cms-migrations-fail-before-the-first-record-movesCMS migrations fail not because of the new platform but because nobody cleaned up the mess before packing it into boxes. Bad content models get locked in, integrations get reverse-engineered at midnight, legacy logic resurfaces as unexplainable bugs, and composable architecture without discipline becomes distributed chaos. The only thing worse than a painful migration is a successful one that preserved all your worst decisions.Mon, 30 Mar 2026 10:00:00 GMTcomposable-architecturecmsfrontendproduct-strategyhttps://timbenniks.dev/writing/the-future-of-software-is-bespokehttps://timbenniks.dev/writing/the-future-of-software-is-bespokeThis article argues that generic SaaS dashboards are a legacy compromise from a time when custom software was expensive and slow to build. With modern APIs, solid SDKs, scaffolding, and AI-assisted development, teams can now create focused, bespoke interfaces in days that match their exact workflows, instead of fighting through one-size-fits-all UIs. The platform should be treated as the engine providing authentication, permissions, content modeling, and governance, while product teams own the experience layer tailored to their people. The piece also examines trade-offs like maintenance burden, skills gaps, and fragility, and explains how good scaffolding, community patterns, and developer education can mitigate these risks and make custom tooling a pragmatic default.Thu, 26 Mar 2026 10:00:00 GMTcomposable-architecturecmsapi-designfrontenddeveloper-experiencehttps://timbenniks.dev/writing/we-moved-the-difficultyhttps://timbenniks.dev/writing/we-moved-the-difficultyIn 2013 I built the Need for Speed Rivals launch site from scratch in five weeks - custom router, custom state, custom tweening engine, 35 languages, no framework worth mentioning. I rebuilt it recently for my Vue.js Amsterdam 2026 talk. The contrast broke my brain in the best way, and it clarified something I've been trying to articulate about AI, abstraction, and what "craft" actually means now.Tue, 17 Mar 2026 10:00:00 GMTcomposable-architectureai-engineeringfrontendcraftcareerhttps://timbenniks.dev/writing/the-best-product-decisions-were-never-analyticalhttps://timbenniks.dev/writing/the-best-product-decisions-were-never-analyticalThis article explores how AI changes the balance between research-heavy processes and intuition-driven building, especially in product and technical work. The author reflects on a career of moving faster than surrounding teams, where strong intuition (really compressed experience from shipping many similar things) often clashed with expectations for lengthy research and documentation. As AI makes implementation and iteration dramatically cheaper and faster, the true bottleneck shifts from building to deciding what is worth building. Research still matters for those without established mental models, and for environments where stakeholders need evidence and paper trails. But when iteration costs hours instead of weeks, over-indexing on analysis can become the real drag. The piece argues that, in an AI-enabled world, experienced intuition is not anti-process; for the right people and problems, it is the process.Tue, 10 Mar 2026 10:00:00 GMTcomposable-architectureai-engineeringfrontendproduct-strategycareerhttps://timbenniks.dev/writing/code-is-craft-now-not-laborhttps://timbenniks.dev/writing/code-is-craft-now-not-laborCoding is largely solved. Agents with a great product vision can produce what used to take teams weeks. But the act of writing code by hand isn't dying - it's transforming from a necessity into a craft. Like knitting, you won't need to do it. You'll choose to.Wed, 25 Feb 2026 10:00:00 GMTai-engineeringcraftcareerpersonalhttps://timbenniks.dev/writing/openai-codex-built-a-skill-for-itself-is-mcp-even-a-thing-anymorehttps://timbenniks.dev/writing/openai-codex-built-a-skill-for-itself-is-mcp-even-a-thing-anymoreI gave OpenAI Codex a management token, an API key, some YouTube IDs, and my Contentstack TypeScript schema. It imported all my content flawlessly, then wrote a custom CLI and a skill to do it again. I did not ask it to do that. Now I'm wondering if we've been overcomplicating everything.Fri, 20 Feb 2026 14:30:22 GMTai-engineeringdeveloper-experiencehttps://timbenniks.dev/writing/cosplaying-as-a-product-manager-and-i-think-im-onto-somethinghttps://timbenniks.dev/writing/cosplaying-as-a-product-manager-and-i-think-im-onto-somethingAfter twenty years of engineering, I accidentally ended up running multiple product lines. My approach (build first, spec later, let AI handle the translation) isn't traditional PM work. But it might be where the role is heading. Here's why engineers who produce before they plan might have an unfair advantage in the age of AI.Sat, 14 Feb 2026 10:00:00 GMTcraftproduct-strategycareerhttps://timbenniks.dev/writing/tdd-finally-makes-sensehttps://timbenniks.dev/writing/tdd-finally-makes-senseAI coding tools have removed the old excuse that test driven development is too slow or too costly. When AI can generate both implementation and test scaffolding in minutes, the time cost of writing tests first collapses, turning TDD into an obvious quality and productivity win. The real risk now is vibe coding, where developers ship AI generated code that looks fine but crumbles under real edge cases. By using AI for planning, then encoding that thinking as tests and letting the AI implement against them, teams get faster feedback, more reliable code, and fewer hotfixes. In an AI assisted world, the competitive advantage shifts to defining behavior and edge cases up front, and TDD becomes the discipline that makes that thinking explicit.Wed, 11 Feb 2026 10:00:00 GMTcomposable-architectureai-engineeringfrontendproduct-strategycareerhttps://timbenniks.dev/writing/when-output-is-cheap-taste-is-everythinghttps://timbenniks.dev/writing/when-output-is-cheap-taste-is-everythingThis article explores how AI has radically reduced the cost of producing things, creating an intoxicating sense of limitless output for ambitious people. But when building becomes almost frictionless, the real bottleneck shifts from implementation to judgment. The author argues that taste (the ability to choose what is worth building) and genuine rest become the true sources of leverage. AI is an exceptional how engine, but deciding what and why remains a deeply human responsibility. Without rest, our judgment degrades, and we risk building more but meaning less. The piece encourages pairing curiosity and experimentation with discipline, restraint, and strategic downtime.Sun, 08 Feb 2026 10:00:00 GMTcomposable-architectureai-engineeringproduct-strategycareerpersonalhttps://timbenniks.dev/writing/ai-is-not-replacing-developers-it-is-exposing-everyone-elsehttps://timbenniks.dev/writing/ai-is-not-replacing-developers-it-is-exposing-everyone-elseFor the last year, the dominant narrative has been that AI will replace developers. I think that narrative has it backwards. AI doesn't replace developers - it raises the bar for everyone else to justify their seat next to someone who can now ship at absurd velocity.Wed, 04 Feb 2026 10:00:00 GMTai-engineeringdeveloper-experiencehttps://timbenniks.dev/writing/do-we-still-need-sdks-in-the-age-of-ai-agentshttps://timbenniks.dev/writing/do-we-still-need-sdks-in-the-age-of-ai-agentsWith good APIs and OpenAPI specs, AI agents can generate production-ready clients in seconds. This challenges everything we know about SDK development and distribution. But are we ready to let go?Thu, 29 Jan 2026 10:00:00 GMTai-engineeringapi-designdeveloper-experiencehttps://timbenniks.dev/writing/devrel-success-metrics-that-actually-matterhttps://timbenniks.dev/writing/devrel-success-metrics-that-actually-matterWhen the market stops buying, vanity metrics stop mattering. Here's how to measure DevRel impact in ways that executives understand and that correlate with real business outcomes like ARR growth.Tue, 27 Jan 2026 10:00:00 GMTdeveloper-experiencedevrelhttps://timbenniks.dev/writing/your-legacy-patterns-are-technical-debt-in-modern-architecturehttps://timbenniks.dev/writing/your-legacy-patterns-are-technical-debt-in-modern-architectureDeveloper teams migrating from legacy to modern architecture often bring old habits that become technical debt. Executive pressure and budget constraints drive rushed migrations without adapting to new paradigms. Success requires stopping to discover how modern systems actually work, designing ideal workflows without legacy constraints, and recognizing that migration is about transforming how you model and manage content, not just moving it between systems.Mon, 26 Jan 2026 10:00:00 GMTcomposable-architecturecmscrafthttps://timbenniks.dev/writing/the-pragmatic-guide-to-coding-with-ai-agentshttps://timbenniks.dev/writing/the-pragmatic-guide-to-coding-with-ai-agentsAI agents are extremely capable coding assistants, but they are not magical autonomous engineers. Treat them like very fast junior developers who need clear scope, clean environments, and strong guardrails. Avoid context gluttony by limiting inputs to only the files and details needed for the task, and rely on search instead of dumping entire repositories. Skip over engineered MCP setups and excessive plugins in favor of simple, well understood tools. Fix your project environment so builds and checks run cleanly from the root. Use planning steps, a project specific “gotchas” file, tests as guardrails, and tightly scoped tasks to keep agents effective, predictable, and safe in real-world production work.Sun, 25 Jan 2026 10:00:00 GMTai-engineeringfrontendhttps://timbenniks.dev/writing/want-to-be-better-at-vibe-coding-become-a-better-coderhttps://timbenniks.dev/writing/want-to-be-better-at-vibe-coding-become-a-better-coderThe promise of AI-powered development is seductive, but here's the reality check nobody's talking about - the better you understand code, the better your AI-generated results will be. LLMs code like humans with high IQs and unstoppable work ethic. Treat them as junior developers and learn the fundamentals to multiply your vibe coding power.Mon, 12 Jan 2026 15:00:00 GMTai-engineeringapi-designcloud-infracraftdeveloper-experiencehttps://timbenniks.dev/writing/mcp-fragmentation-context-efficiency-and-the-rise-of-curated-skillshttps://timbenniks.dev/writing/mcp-fragmentation-context-efficiency-and-the-rise-of-curated-skillsThe Model Context Protocol (MCP) was supposed to be a universal way to connect AI models to tools, but in practice it is fragmenting fast across vendors and implementations. Tool catalogs are extremely context-hungry, making naive MCP setups expensive, slow, and unreliable, especially with cheaper models. Developers are compensating with application-layer tricks like curated tool subsets, OAuth-based selection, Claude Skills style abstractions, and wrapping deterministic automation platforms such as Contentstack Automate. These patterns improve cost, reliability, and debuggability but highlight protocol-level gaps in context efficiency, determinism, and interoperability. The ecosystem is replaying past standards wars, and no clear winner is visible yet. The pragmatic move is to design flexible systems that can adapt when consolidation and better standards eventually emerge.Fri, 09 Jan 2026 10:00:00 GMTcomposable-architectureai-engineeringapi-designperformancecloud-infrahttps://timbenniks.dev/writing/cursor-rules-and-my-vibe-engineer-workflowhttps://timbenniks.dev/writing/cursor-rules-and-my-vibe-engineer-workflowI released my Cursor rules and commands as a public repo because Cursor is not magic, it is leverage. By turning it into a constrained system with explicit rules, reusable commands, and real project context, you can make it behave like a senior engineer on SaaS projects. The real win is not speed, but trust at speed.Tue, 16 Dec 2025 10:00:00 GMTai-engineeringfrontenddeveloper-experienceproduct-strategyhttps://timbenniks.dev/writing/ai-native-composability-needs-real-api-first-dnahttps://timbenniks.dev/writing/ai-native-composability-needs-real-api-first-dnaAI exposes which platforms were truly built API first and which ones only marketed it. As brands move into AI native workflows, the only viable path is a system that treats agents, events, and automation as composable building blocks. Contentstack's agentOS shows what happens when you start with API first DNA instead of bolting AI onto a monolithic core. This piece explains why AI native composability is the next logical layer of MACH and why brands should judge vendors by the architecture of their agents, not the slideware that surrounds them.Tue, 02 Dec 2025 10:00:00 GMTcomposable-architectureai-engineeringcmsapi-designcontent-opshttps://timbenniks.dev/writing/the-experience-factory-01-why-experience-is-the-real-flagshiphttps://timbenniks.dev/writing/the-experience-factory-01-why-experience-is-the-real-flagshipMany brands think they're digitally mature, yet their experience operations are fragmented. Here's how to spot it and start orchestrating.Mon, 01 Dec 2025 10:00:00 GMTcomposable-architecturecmsapi-designcontent-opsfrontendhttps://timbenniks.dev/writing/the-mach-monolith-in-2026https://timbenniks.dev/writing/the-mach-monolith-in-2026The 2022 diagnosis was right. Composable architectures need orchestration or they collapse. But the form factor was wrong. Teams rejected standalone orchestration layers as too heavy, another vendor, contract, and critical path. The 2026 reality is platforms that integrate orchestration directly, staying API-first and modular while providing built-in coordination. The shift isn't about more tools, but smarter platforms that reduce complexity fatigue without losing flexibility.Mon, 17 Nov 2025 10:00:00 GMTcomposable-architectureai-engineeringcmsapi-designcontent-opshttps://timbenniks.dev/writing/devrel-oshttps://timbenniks.dev/writing/devrel-osDeveloper Relations is most effective when treated not as marketing, not as community management, and not as evangelism, but as a disciplined operating system for improving the developer journey. DevRel succeeds when it brings clarity to complexity, reduces cognitive load, and creates repeatable success for developers. To do that, teams need frameworks, not just intentions.Sat, 08 Nov 2025 10:00:00 GMTdevrelhttps://timbenniks.dev/writing/its-time-to-think-of-llms-as-having-abilities-not-protocolshttps://timbenniks.dev/writing/its-time-to-think-of-llms-as-having-abilities-not-protocolsTL;DR Don't over-engineer standards around protocols. Instead, treat your large-language-model as a toolbox of abilities (like search, translate, query, generate) that you plug into your system. By thinking of LLMs as modular and composable abilities rather than monolithic protocols, AI becomes accessible, practical and aligned with how engineering and product teams already build.Fri, 07 Nov 2025 10:00:00 GMTcomposable-architectureai-engineeringcmsapi-designcontent-opshttps://timbenniks.dev/writing/the-age-of-the-super-t-product-personhttps://timbenniks.dev/writing/the-age-of-the-super-t-product-personAI is dissolving silos and creating a new kind of product person who thinks like a system, connects disciplines, and prototypes ideas before lunch.Tue, 07 Oct 2025 10:00:00 GMTai-engineeringproduct-strategyhttps://timbenniks.dev/writing/the-future-of-cms-from-content-management-to-context-managementhttps://timbenniks.dev/writing/the-future-of-cms-from-content-management-to-context-managementThe CMS is evolving from static publishing to dynamic context management, where AI agents adapt every experience in real time. Welcome to the Context Economy.Sun, 05 Oct 2025 20:37:36 GMTcomposable-architectureai-engineeringcmspersonalizationcontent-opshttps://timbenniks.dev/writing/ai-chat-interfaces-will-replace-web-appshttps://timbenniks.dev/writing/ai-chat-interfaces-will-replace-web-appsA firsthand look at how AI-driven chat interfaces could reshape SaaS and user interaction.Sat, 04 Oct 2025 20:37:36 GMTcomposable-architectureai-engineeringcmsapi-designcontent-opshttps://timbenniks.dev/writing/build-context-aware-mcp-not-api-wrappershttps://timbenniks.dev/writing/build-context-aware-mcp-not-api-wrappersMCP servers shouldn't just expose endpoints, they should adapt to their environment, using project context to guide AI reasoning and execution.Sat, 04 Oct 2025 20:37:36 GMTcomposable-architectureai-engineeringapi-designperformancedeveloper-experiencehttps://timbenniks.dev/writing/the-nuanced-impact-of-ai-we-should-not-overlookhttps://timbenniks.dev/writing/the-nuanced-impact-of-ai-we-should-not-overlookAI's impact on the tech industry is more nuanced than often claimed, offering modest productivity improvements while blurring role specializations and fostering a more versatile, holistic approach to development.Tue, 04 Feb 2025 13:05:48 GMTai-engineeringcareerhttps://timbenniks.dev/writing/we-have-collectively-forgotten-what-monoliths-arehttps://timbenniks.dev/writing/we-have-collectively-forgotten-what-monoliths-areExploring the misconception of modern CMS platforms as monoliths and clarifying the distinctions between true monolithic systems and today's flexible, API-driven content management solutions.Fri, 10 Jan 2025 13:05:48 GMTcomposable-architecturecmsapi-designfrontendproduct-strategyhttps://timbenniks.dev/writing/universal-cms-the-wheel-we-are-reinventinghttps://timbenniks.dev/writing/universal-cms-the-wheel-we-are-reinventingUniversal CMS reshapes CMS by blending headless and traditional, empowering developers and content creators. But are we reinventing the wheel here?Wed, 13 Nov 2024 13:05:48 GMTcomposable-architecturecmsapi-designfrontenddeveloper-experiencehttps://timbenniks.dev/writing/sdks-use-them-or-nothttps://timbenniks.dev/writing/sdks-use-them-or-notExplore the significance of Software Development Toolkits (SDKs) in modern development, their advantages, and when you might want to skip them. From enhancing productivity to integrating complex functionalities seamlessly, the right SDK can accelerate your projects. But what about GraphQL-based systems or the flexibility of headless architectures? Dive into the pros and cons to make an informed decision.Sun, 29 Sep 2024 12:05:48 GMTcomposable-architecturecmsapi-designperformancefrontendhttps://timbenniks.dev/writing/different-approaches-to-visual-editinghttps://timbenniks.dev/writing/different-approaches-to-visual-editingThis article compares different approaches to visual editing in headless CMS platforms, outlining the benefits and tradeoffs of options ranging from basic previews to full WYSIWYG editors.Thu, 25 Jul 2024 10:32:48 GMTcomposable-architecturecmsapi-designfrontendhttps://timbenniks.dev/writing/how-i-supercharched-my-websites-speedhttps://timbenniks.dev/writing/how-i-supercharched-my-websites-speedIn this blog post, I want to share how I transformed my website into the fastest site I've ever built. I'll walk you through the steps, my unconventional decisions, and the tools I used to achieve this feat.Mon, 01 Jul 2024 13:05:48 GMTperformancecloud-infrafrontendhttps://timbenniks.dev/writing/choosing-the-right-visual-editorhttps://timbenniks.dev/writing/choosing-the-right-visual-editorThis post explores two main types of visual editors platform-first and code-first. I compare their functionalities, pros, and cons to help you choose the right solution for your development needs.Fri, 28 Jun 2024 13:05:48 GMTcomposable-architecturecmsapi-designfrontenddeveloper-experiencehttps://timbenniks.dev/writing/team-is-key-when-going-headlesshttps://timbenniks.dev/writing/team-is-key-when-going-headlessPeople's choices, ability to roll with the punches, and how well they play in the sandbox together bring the magic of headless technology to life.Mon, 29 Apr 2024 13:05:48 GMTcomposable-architecturecmsapi-designfrontendproduct-strategyhttps://timbenniks.dev/writing/page-builder-cms-vs-data-modeler-cmshttps://timbenniks.dev/writing/page-builder-cms-vs-data-modeler-cmsExplore the differences between page builder and data modeler CMSs, their unique features, and how they cater to varying organizational needs.Tue, 12 Mar 2024 13:05:48 GMTcomposable-architecturecmscontent-opsfrontendproduct-strategyhttps://timbenniks.dev/writing/the-content-graph-is-the-futurehttps://timbenniks.dev/writing/the-content-graph-is-the-futureContent management is as essential as it is complex, especially at scale. As brands grow, they often...Tue, 05 Dec 2023 10:40:00 GMTcomposable-architecturecmsapi-designperformancefrontendhttps://timbenniks.dev/writing/what-type-of-content-organization-do-you-needhttps://timbenniks.dev/writing/what-type-of-content-organization-do-you-needDifferent ways of working require different approaches to content design. In this post, I will...Sun, 12 Nov 2023 09:03:33 GMTcomposable-architecturecmsapi-designcontent-opsfrontendhttps://timbenniks.dev/writing/the-real-deal-about-content-management-buzzwordhttps://timbenniks.dev/writing/the-real-deal-about-content-management-buzzwordBuzzwords are labels that describe tech approaches that become so commonplace over time that the...Thu, 28 Sep 2023 14:43:37 GMTcomposable-architecturecmsapi-designcloud-infrafrontendhttps://timbenniks.dev/writing/the-future-of-headless-cms-content-federation-with-graphqlhttps://timbenniks.dev/writing/the-future-of-headless-cms-content-federation-with-graphqlFederation is a popular topic of conversation these days, and for good reason. With the ever-growing...Thu, 28 Sep 2023 14:39:16 GMTcomposable-architecturecmsapi-designcontent-opscloud-infrahttps://timbenniks.dev/writing/new-job-alerthttps://timbenniks.dev/writing/new-job-alertAfter an exciting journey at Uniform, it's time for a new adventure. At Uniform, we thrived during...Wed, 16 Aug 2023 13:42:10 GMTcmsproduct-strategydevrelhttps://timbenniks.dev/writing/this-is-headless-20https://timbenniks.dev/writing/this-is-headless-20That’s a bold title, but it’s high time to change how we work with headless technology. I wrote about...Tue, 11 Jul 2023 07:48:19 GMTcomposable-architecturecmsapi-designperformancefrontendhttps://timbenniks.dev/writing/the-lost-promise-of-headlesshttps://timbenniks.dev/writing/the-lost-promise-of-headlessIn recent years, headless technology, which boosts performance, developer experience, and...Mon, 26 Jun 2023 18:18:19 GMTcomposable-architecturecmsapi-designperformancefrontendhttps://timbenniks.dev/writing/level-up-your-collaboration-game-developer-insights-for-winning-with-marketing-prohttps://timbenniks.dev/writing/level-up-your-collaboration-game-developer-insights-for-winning-with-marketing-proBuilding outstanding user experiences takes, first and foremost, effective collaboration between...Wed, 03 May 2023 15:49:29 GMTperformanceproduct-strategydevrelhttps://timbenniks.dev/writing/how-to-get-your-webcam-to-look-decent-in-a-few-simple-stepshttps://timbenniks.dev/writing/how-to-get-your-webcam-to-look-decent-in-a-few-simple-stepsIf you have used a webcam before you know what it means to look like shit on camera. Even the most...Mon, 20 Mar 2023 13:01:35 GMTcontent-opsdeveloper-experiencedevrelmedia-productionhttps://timbenniks.dev/writing/why-i-didnt-run-the-2016-marathonhttps://timbenniks.dev/writing/why-i-didnt-run-the-2016-marathonAfter four and a half months of full on training I’ve decided not to run the Amsterdam marathon on...Sat, 18 Mar 2023 22:52:37 GMTpersonalhttps://timbenniks.dev/writing/the-2015-paris-marathohttps://timbenniks.dev/writing/the-2015-paris-marathoExactly one year ago, when we had just moved to Paris, the marathon passed by our apartment in Rue...Sat, 18 Mar 2023 22:45:48 GMTpersonalhttps://timbenniks.dev/writing/my-fitness-storyhttps://timbenniks.dev/writing/my-fitness-storyFrom fat and sick to slim and happy Aside from a short period in high school I have always...Sat, 18 Mar 2023 22:39:46 GMTpersonalhttps://timbenniks.dev/writing/make-the-web-greener-luxury-editionhttps://timbenniks.dev/writing/make-the-web-greener-luxury-editionIf the internet were a country, it would be the world’s sixth biggest polluter. The...Sat, 18 Mar 2023 22:30:27 GMTcomposable-architecturecmsperformancecloud-infrafrontendhttps://timbenniks.dev/writing/how-to-dynamically-stream-videohttps://timbenniks.dev/writing/how-to-dynamically-stream-videoBuild it yourself or use Cloudinary Dynamic video streaming is a video delivery technique...Sat, 18 Mar 2023 21:56:45 GMTperformancecloud-infrafrontenddeveloper-experiencedevrelhttps://timbenniks.dev/writing/uniform-is-nuxt-3-readhttps://timbenniks.dev/writing/uniform-is-nuxt-3-readWe are excited to announce that the latest iteration of the Uniform SDK is fully compatible with Vue...Sat, 18 Mar 2023 13:10:06 GMTfrontendhttps://timbenniks.dev/writing/digital-experience-platforms-the-old-versus-the-newhttps://timbenniks.dev/writing/digital-experience-platforms-the-old-versus-the-newDigital experience platforms (DXPs) and the more modern digital experience composition platforms...Sat, 18 Mar 2023 13:05:48 GMTcomposable-architecturecmsapi-designcontent-opscloud-infrahttps://timbenniks.dev/writing/uniform-dxcp-the-what-why-and-howhttps://timbenniks.dev/writing/uniform-dxcp-the-what-why-and-howNowadays, you’re hard pressed to find an application with all the functionalities you need for...Sat, 18 Mar 2023 13:03:16 GMTcomposable-architectureperformancehttps://timbenniks.dev/writing/how-to-sniff-out-the-glue-monsterhttps://timbenniks.dev/writing/how-to-sniff-out-the-glue-monsterEven though you don’t see it, glue code is everywhere. Since the pendulum swung from monolithic...Sat, 18 Mar 2023 13:00:21 GMTcomposable-architecturecmsapi-designperformancefrontendhttps://timbenniks.dev/writing/the-future-of-managing-projects-at-agenciehttps://timbenniks.dev/writing/the-future-of-managing-projects-at-agencieCalling for a revolution in how agencies run tech projects I spent a lot of time working...Sat, 18 Mar 2023 12:56:10 GMTcomposable-architectureproduct-strategyhttps://timbenniks.dev/writing/fast-personalized-pages-with-vercel-edge-middleware-and-uniformhttps://timbenniks.dev/writing/fast-personalized-pages-with-vercel-edge-middleware-and-uniformTo maintain an engaging relationship with your audience and increase conversions to your site, you...Sat, 18 Mar 2023 12:49:56 GMTcomposable-architecturecmsapi-designpersonalizationperformancehttps://timbenniks.dev/writing/the-move-from-monolithic-to-composable-architectureshttps://timbenniks.dev/writing/the-move-from-monolithic-to-composable-architecturesSuccess in business can be attributed to many factors, notably team talent and efficacy of products...Mon, 13 Mar 2023 20:42:55 GMTcomposable-architecturefrontendhttps://timbenniks.dev/writing/mach-versus-monolithic-suiteshttps://timbenniks.dev/writing/mach-versus-monolithic-suitesToday, with consumers fast becoming digitally advanced, companies realize that old technologies are...Mon, 13 Mar 2023 20:37:36 GMTcomposable-architecturefrontendhttps://timbenniks.dev/writing/the-mach-monolithhttps://timbenniks.dev/writing/the-mach-monolithFor years, the headless concept went through the nerd vine at boardrooms, pushing execs to take...Mon, 13 Mar 2023 20:20:45 GMTcomposable-architecturefrontendhttps://timbenniks.dev/writing/the-future-of-jamstack-is-composablehttps://timbenniks.dev/writing/the-future-of-jamstack-is-composableThis post is either for developers who want an “at-scale” overview of modern architecture or for...Wed, 23 Feb 2022 13:04:08 GMTcomposable-architecturecontent-opshttps://timbenniks.dev/writing/create-a-performant-youtube-embed-with-a-native-web-componenthttps://timbenniks.dev/writing/create-a-performant-youtube-embed-with-a-native-web-componentIn this Media Jam you will learn how to create a native web component that replaces the default YouTube iframe embed.Thu, 20 May 2021 13:05:48 GMTfrontendmedia-productionhttps://timbenniks.dev/writing/creating-a-custom-video-player-in-vuehttps://timbenniks.dev/writing/creating-a-custom-video-player-in-vueIn this Media Jam you will learn how to create a video player with custom controls and event handling in Vue.js.Tue, 18 May 2021 13:05:48 GMTfrontendmedia-production