LLM-assisted coding can enable “software for one”: small, personalized applications and extensions that address users’ long-tail needs without forcing every feature into a product’s default interface. The proposed model for web applications combines a stable, accountable core with user-created code that can react to events, run on schedules, add views, transform data, and automate tasks. Potential uses include tailored AI agents, internal corporate tools, support-ticket workflows, and custom observability visualizations. Extensions could be generated from natural-language requests and shared with other users. Running user code inside web services requires low execution cost, fast cold starts, strict resource limits, tenant isolation, and controlled access to data and external actions. The author argues that narrow capability-based interfaces are safer than giving extensions API keys or unrestricted network access: code receives only specific approved functions or bindings, limiting data exposure and possible actions. Salesforce has operated a multi-tenant programmable platform since 2007 through its Apex language and event-driven customization model. The source identifies interpreters, V8 isolates, microVMs, and WebAssembly with WASI as possible execution technologies. It highlights Cloudflare Dynamic Workers as a production-oriented option, citing built-in observability, tenant-scoped storage, durable workflows, source control, and hosted LLM access. The author discloses employment at Cloudflare.