{"type":"writing","count":12,"results":[{"type":"writing","title":"Building MCP Profile Hub part 2, one MCP server is the wrong abstraction","date":"2026-09-04","description":"This 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.","tags":["composable-architecture","ai-engineering","api-design","frontend","product-strategy"],"url":"https://timbenniks.dev/writing/building-mcp-profile-hub-part-2-one-mcp-server-is-the-wrong-abstraction","md":"https://timbenniks.dev/writing/building-mcp-profile-hub-part-2-one-mcp-server-is-the-wrong-abstraction.md"},{"type":"writing","title":"Building MCP Profile Hub, part 1: Stop making the agent ask","date":"2026-08-31","description":"Introducing 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.","tags":["composable-architecture","ai-engineering","api-design","frontend","product-strategy"],"url":"https://timbenniks.dev/writing/building-mcp-profile-hub-part-1-stop-making-the-agent-ask","md":"https://timbenniks.dev/writing/building-mcp-profile-hub-part-1-stop-making-the-agent-ask.md"},{"type":"writing","title":"Claude Desktop MCP lifecycle is broken","date":"2026-08-24","description":"Claude 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.","tags":["composable-architecture","ai-engineering","performance","cloud-infra","frontend"],"url":"https://timbenniks.dev/writing/claude-desktop-mcp-lifecycle-is-broken","md":"https://timbenniks.dev/writing/claude-desktop-mcp-lifecycle-is-broken.md"},{"type":"writing","title":"Buy the plumbing, vibe the rest","date":"2026-08-22","description":"AI 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.","tags":["composable-architecture","ai-engineering","frontend","developer-experience"],"url":"https://timbenniks.dev/writing/buy-the-plumbing-vibe-the-rest","md":"https://timbenniks.dev/writing/buy-the-plumbing-vibe-the-rest.md"},{"type":"writing","title":"The Doer Economy - we are killing the translator class","date":"2026-08-17","description":"This 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.","tags":["composable-architecture","ai-engineering","api-design","frontend","developer-experience"],"url":"https://timbenniks.dev/writing/the-doer-economy-we-are-killing-the-translator-class","md":"https://timbenniks.dev/writing/the-doer-economy-we-are-killing-the-translator-class.md"},{"type":"writing","title":"Ten AI security problems hiding in plain text","date":"2026-08-05","description":"This 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.","tags":["composable-architecture","ai-engineering","cloud-infra","frontend","product-strategy"],"url":"https://timbenniks.dev/writing/ten-ai-security-problems-hiding-in-plain-text","md":"https://timbenniks.dev/writing/ten-ai-security-problems-hiding-in-plain-text.md"},{"type":"writing","title":"The biggest risk to AI is the enterprise org chart","date":"2026-07-24","description":"This 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.","tags":["composable-architecture","ai-engineering","frontend","product-strategy","career"],"url":"https://timbenniks.dev/writing/the-biggest-risk-to-ai-is-the-enterprise-org-chart","md":"https://timbenniks.dev/writing/the-biggest-risk-to-ai-is-the-enterprise-org-chart.md"},{"type":"writing","title":"Your LinkedIn reads like a robot wrote it","date":"2026-06-22","description":"Two 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.","tags":["ai-engineering","craft","product-strategy","career"],"url":"https://timbenniks.dev/writing/your-linkedin-reads-like-a-robot","md":"https://timbenniks.dev/writing/your-linkedin-reads-like-a-robot.md"},{"type":"writing","title":"We are thinking too small","date":"2026-06-20","description":"AI 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.","tags":["composable-architecture","ai-engineering","cloud-infra","frontend"],"url":"https://timbenniks.dev/writing/we-are-thinking-too-small","md":"https://timbenniks.dev/writing/we-are-thinking-too-small.md"},{"type":"writing","title":"Cursor's moat","date":"2026-06-17","description":"The 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.","tags":["composable-architecture","ai-engineering","frontend","devrel"],"url":"https://timbenniks.dev/writing/cursors-moat","md":"https://timbenniks.dev/writing/cursors-moat.md"},{"type":"writing","title":"Contentstack launched Agent OS, AXP, and the dev tools I have been itching to talk about","date":"2026-06-09","description":"Contentstack 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.","tags":["composable-architecture","ai-engineering","developer-experience"],"url":"https://timbenniks.dev/writing/contentstack-launched-agent-os-axp-and-the-dev-tools","md":"https://timbenniks.dev/writing/contentstack-launched-agent-os-axp-and-the-dev-tools.md"},{"type":"writing","title":"The agentic spectrum: stop burning tokens on what a script can do","date":"2026-06-04","description":"AI 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.","tags":["ai-engineering","content-ops","cloud-infra"],"url":"https://timbenniks.dev/writing/the-agentic-spectrum-stop-burning-tokens-on-what-a-script-can-do","md":"https://timbenniks.dev/writing/the-agentic-spectrum-stop-burning-tokens-on-what-a-script-can-do.md"}]}