5 posts
Formspec's Assist specification defines a standard protocol for AI agents, browser extensions, and accessibility tools to help people understand, complete, and reuse data across complex forms — without requiring an LLM.
Formspec's References and Ontology specs create a dual context layer — meaning plus evidence — that lets AI agents auto-fill, explain, and support form completion with grounded, domain-accurate answers instead of plausible-sounding hallucinations.
Formspec's new semantic layer gives form fields stable, machine-readable concept identity — the missing ingredient that turns AI data engineering from guesswork into something you can actually trust.
We built a Claude Code skill that spawns five AI personas — from a nervous admin assistant to an API-first developer — to stress-test our form-building MCP server. Here's the pipeline and what we found.
Most AI code generation is freeform text you review line by line. Formspec's approach is different — structured MCP tool calls, JSON Schema validation, and static linting mean AI-generated forms are verified automatically.