DEV Community

Lovanaut profile picture

Lovanaut

Solo founder building FORMLOVA — 118 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

Pin Pinned

Your Form Response Just Created a GitHub PR: Cross-Service Orchestration With MCP
lovanaut55 profile

Your Form Response Just Created a GitHub PR: Cross-Service Orchestration With MCP

#ai #automation #mcp #productivity
7
Comments 2
7 min read
Stripe Closed My Connect Account. Here's What Actually Fixed It in 24 Hours.
lovanaut55 profile

Stripe Closed My Connect Account. Here's What Actually Fixed It in 24 Hours.

5
Comments
10 min read
Beyond CAPTCHA: Building an AI Filter for Contact Form Spam
lovanaut55 profile

Beyond CAPTCHA: Building an AI Filter for Contact Form Spam

#ai #security #tutorial #webdev
5
Comments
5 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.

Create Account
Already have an account? Sign in
Running LLM Classification After the Response: Next.js after() + OpenRouter at $0.0002 per Call
lovanaut55 profile

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

#ai #llm #nextjs #webdev
5
Comments
8 min read
From Form Response to Figma Wireframe: MCP Orchestration in Practice
lovanaut55 profile

From Form Response to Figma Wireframe: MCP Orchestration in Practice

#automation #design #llm #mcp
6
Comments
6 min read
127 MCP Tools, 4 Safety Levels: Building a Server-Enforced Form Ops Layer
lovanaut55 profile

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

#ai #architecture #mcp #security
6
Comments 7
6 min read
Designing a CLI Skill That Structures AI Sessions into Posts -- Architecture, Security, and Implementation Decisions
lovanaut55 profile

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

#showdev #ai #architecture #cli
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.
lovanaut55 profile

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

#ai #llm #testing #tooling
6
Comments
5 min read
OpenRouter Structured Output Broke Before Translation Quality Did — 3 Layers of Defense for Production
lovanaut55 profile

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

#api #architecture #javascript #llm
6
Comments
9 min read
loading...