Articles on structural chat — applications that pause for user input with rich UI controls.https://structural.chat/https://structural.chat/articles/programming-in-markdown/https://structural.chat/articles/programming-in-markdown/Amidst a rising sea of AI hype, we see LLMs being used in situations where it makes no sense. Instead of describing business processes with regular code, companies encode logic with elaborate Markdown prompts passed to LLMs. This is effectively programming in Markdown, using the world's slowest and least reliable interpreter, an LLM, running at 10,000x the cost and latency and with dramatically worse privacy and security.Wed, 03 Jun 2026 00:00:00 GMThttps://structural.chat/articles/llm-prompt-injection/https://structural.chat/articles/llm-prompt-injection/This post introduces the pervasive problem of prompt-injection in LLMs and walks through three poor solutions for addressing it. Two are security theatre non-solutions that do nothing against a determined attacker, and the third technically works but generally makes the use of LLMs pointless. After covering these, we'll discuss the problem from first principles and introduce the only actual solution.Tue, 02 Jun 2026 00:00:00 GMThttps://structural.chat/articles/llm-free-bots/https://structural.chat/articles/llm-free-bots/This post introduces a new approach to creating LLM-free support bots. In addition to providing a great user experience, these bots are reliable, speedy, hallucination free, and overall cheaper, simpler, and safer to operate than bots based on LLMs. They are immune to prompt-injection attacks and the possibility of leaking personal information to third-party AI model providers. There _are_ no prompts or prompt-tuning and these bots ship do not ship _any_ data off to an AI model. Many products may be better served by a bot built with these techniques.Thu, 14 May 2026 00:00:00 GMThttps://structural.chat/articles/nlds/https://structural.chat/articles/nlds/NLDs ("Natural Language Disambiguators") can be used in place of LLMs or SLMs when disambiguating among a set of structured commands. They run in milliseconds, fast enough for real-time filtering and autocomplete on the front-end, and are robust to differences in phrasing, reordering of tokens, and extraneous tokens that don't affect semantics. ("I want to return my order", "order return", and "my order has a problem, I'd like to return it" can all be parsed by the same NLD spec).Wed, 13 May 2026 00:00:00 GMThttps://structural.chat/articles/beyond-static-uis-and-chatbots/https://structural.chat/articles/beyond-static-uis-and-chatbots/Applications of the future will no longer be limited to static UI hierarchies, but will be dynamically assembled based on context, serving the long tail of user goals that either aren’t well-handled by existing UIs, or which are flat-out impossible. This essay introduces the basic idea and shows a number of examples.Thu, 26 Mar 2026 00:00:00 GMT