AI-native business development
We build the AI architecture behind business growth.
Eddy Tools designs and ships AI-driven systems for lead generation, sales operations and growth: agents, automations and data pipelines that run in production, not just in demos.
Our architecture
Six layers. One system that runs your growth.
Every engagement is designed against the same reference architecture, so agents, workflows, services and data fit together and stay maintainable.
Interface layer
Experience & agents
Where people and AI assistants meet your systems: dashboards, apps and MCP endpoints that let Claude, ChatGPT or Cursor act on your tools.
- Next.js
- React + Vite
- Flutter
- MCP servers
- Claude · ChatGPT · Cursor
- PDF reports
Model layer
Intelligence
LLM inference, reusable prompt and skill libraries, and AI analysis that turns raw data into drafts, scores and recommendations.
- Claude
- Prompt & skills library
- AI personalization
- AI-SEO analysis
Workflow layer
Orchestration
Event-driven automation that connects your tools, triggers agents and routes work, with schedules, retries and human approval steps.
- n8n
- Webhooks & schedules
- MCP tool servers
- Human approval steps
Service layer
Services & APIs
Purpose-built backends: multi-tenant APIs, background jobs and content services, each with scoped access keys.
- Go
- FastAPI
- Node.js
- Strapi CMS
- REST & MCP endpoints
- Scoped API keys
Data layer
Data
Operational and analytical stores with clear ownership, plus the analytics sources your growth decisions depend on.
- PostgreSQL
- MySQL 8
- Redis
- GA4 · Search Console
Infrastructure layer
Platform & operations
Boring, reliable infrastructure under everything else, so the clever parts stay up.
- Docker Compose
- nginx
- systemd
- Let's Encrypt TLS
- Self-hosted on your VPS or ours
The tools above are the ones we build and run in our own platforms. We choose the right stack per project instead of forcing one.
What we build
AI systems for business development
/01
AI agents & MCP integrations
Give Claude, ChatGPT or Cursor safe, scoped access to your CRM, content and analytics through MCP servers, so agents can actually do work.
/02
Workflow automation
Self-hosted n8n workflows that connect your tools, qualify and route leads, and keep a human in the loop where it matters.
/03
Lead generation & nurturing systems
Funnels, landing pages and behaviour-driven email nurturing with AI personalization, wired to your data.
/04
AI-SEO & growth analytics
GA4 and Search Console data pulled through MCP, analysed with Claude and delivered as clear reports your team can act on.
Platforms from our own lab
We build products of our own on this architecture. They are where we test patterns before they reach client work.
/01
Funnel Pages
A landing-page and funnel builder with an MCP endpoint, so AI agents can publish live pages to your projects.
- Go
- MySQL
- Next.js
- MCP
/02
NurturingMail
Multi-tenant, behaviour-driven email nurturing: workflows with delays and branches, segmentation, tracking and AI personalization.
- Go
- MySQL
- Redis
- React
/03
RankDeck
MCP-powered SEO and AI-SEO reporting: GA4 and Search Console data, Claude analysis and PDF reports per client.
- FastAPI
- PostgreSQL
- MCP
- Claude
/04
MagnetApp
A factory for subscription quiz apps: configure the quiz, report and paywall, and a Flutter shell builds the native app.
- Flutter
- TypeScript
- Config schema
How we work
/01
Discover
Map your workflows, data and goals, and find where AI will actually pay off.
/02
Architect
Choose the layers and tools, and define guardrails, access and ownership up front.
/03
Build
Ship in small, visible releases so you see working systems early and can steer.
/04
Operate
Monitor, tune and hand over with documentation, so your team owns the result.
Ready to design your AI architecture?
Book an architecture review. We will map your workflows and show where agents and automation fit.