DEV Community

Lovanaut  profile picture

Lovanaut

founder building FORMLOVA — 127 MCP tools for chat-first form operations. Spent 4 months designing server-enforced safety harnesses for LLM-driven workflows. Previo after the form goes live.

Location Japan Joined Joined on  Personal website https://formlova.com twitter website

Work

Solo developer — building FormLova, Lovai, and Sapolova

Google Forms + Apps Script Is a Workflow, Not Just a Notification

Google Forms + Apps Script Is a Workflow, Not Just a Notification

6
Comments
6 min read

Want to connect with Lovanaut ?

Create an account to connect with Lovanaut . You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Designing Post-Submit Form Workflows as a State Machine

Designing Post-Submit Form Workflows as a State Machine

5
Comments
8 min read
AI Form Builders Are Becoming Table Stakes. MCP Form Operations Are the Hard Part.

AI Form Builders Are Becoming Table Stakes. MCP Form Operations Are the Hard Part.

6
Comments
7 min read
Don't Build Your MCP Server as an API Wrapper

Don't Build Your MCP Server as an API Wrapper

6
Comments 1
7 min read
Beyond CAPTCHA: Building an AI Filter for Contact Form Spam

Beyond CAPTCHA: Building an AI Filter for Contact Form Spam

7
Comments
5 min read
Running LLM Classification After the Response: Next.js after() + OpenRouter at $0.0002 per Call

Running LLM Classification After the Response: Next.js after() + OpenRouter at $0.0002 per Call

5
Comments
8 min read
From Form Response to Figma Wireframe: MCP Orchestration in Practice

From Form Response to Figma Wireframe: MCP Orchestration in Practice

6
Comments
6 min read
127 MCP Tools, 4 Safety Levels: Building a Server-Enforced Form Ops Layer

127 MCP Tools, 4 Safety Levels: Building a Server-Enforced Form Ops Layer

6
Comments 7
6 min read
Designing a CLI Skill That Structures AI Sessions into Posts -- Architecture, Security, and Implementation Decisions

Designing a CLI Skill That Structures AI Sessions into Posts -- Architecture, Security, and Implementation Decisions

5
Comments 3
7 min read
Anthropic Proved AI Can't Evaluate Its Own Work. Here's How I Rebuilt My Claude Code Setup Around That.

Anthropic Proved AI Can't Evaluate Its Own Work. Here's How I Rebuilt My Claude Code Setup Around That.

6
Comments
5 min read
OpenRouter Structured Output Broke Before Translation Quality Did — 3 Layers of Defense for Production

OpenRouter Structured Output Broke Before Translation Quality Did — 3 Layers of Defense for Production

6
Comments
9 min read
loading...