Skip to content

We respect your privacy

We use cookies to keep the site running and collect optional metrics. You can review your choices at any time.

View Cookie Policy
2025·In Progress

AI-Powered Personal Portfolio

Researcher & Implementer

Dynamic portfolio conceived as a proof of concept for coordinating multiple AI agents and collaborative tools in web development.

Overview

Personal project that served as a lab for testing the coordination of multiple AI agents in web development. The goal was not just to build a portfolio, but to understand where each tool adds value, where it falls short and how human oversight remains central throughout the process — from prototyping to content refinement, through accessibility and SEO practices.

Challenge

Develop a responsive, professional portfolio in a short timeframe using AI and no-code/low-code tools while ensuring robustness, scalability and good accessibility and security practices.

Solution

– Orchestration of AI agents and collaborative tools (ChatGPT Agent, Lovable.ai, Manus, Devin, Claude, GitHub Copilot, VS Code Copilot) for development and problem-solving.

– Content refinement with ChatGPT-4, ChatGPT-5, Perplexity, Gemini and Notebook LM.

– Vercel deployment.

– Version control on GitHub.

– Monitoring with Google Analytics.

Results

  • Hands-on experience with 10+ AI tools (Claude, ChatGPT, Copilot, Lovable, Devin) in a single workflow
  • Understanding of agent differences — each AI has distinct strengths in code generation, review and content
  • Iterations in minutes rather than hours, significantly accelerating the development cycle
  • Human validation proved essential: AI accelerates but does not replace design and architecture decisions
  • Replicable working model for future projects with multi-agent orchestration

Technologies and Methods

ChatGPT AgentLovable.aiManusDevinClaude (Anthropic)GitHub CopilotVS Code CopilotChatGPT-4ChatGPT-5PerplexityGeminiNotebook LMNext.jsVercelGitHubVS CodeGoogle AnalyticsLighthouseSEO ToolsFigmaResponsive DesignLow-Code/No-CodeCI/CDUsability TestingSEO Optimisation

Detailed Implementation

01

Planning & Setup

Defined goals, selected AI tools and prepared the collaborative pipeline.

02

Accelerated Prototyping

Used agents and no-code/low-code tools to build prototypes and quickly validate flows.

03

Integrated Development

Built the portfolio with Next.js and Vercel, integrating translations, blog and analytics.

04

Monitoring & Evolution

Configured metrics with Google Analytics and Lighthouse and performed continuous performance and SEO optimisations.

Impact Quantified

10+

AI tools explored in a real development context

3 phases

Prototyping, development and refinement with distinct agents

Minutes

Iteration cycles that would conventionally take hours

Lessons Learned

  • Coordinated use of multiple AI agents accelerates development and raises delivery quality
  • Tool orchestration requires clear planning to avoid redundancies
  • Different AIs bring complementary perspectives and improve content refinement effectiveness
  • Human validation is essential to ensure consistency, compliance and brand alignment
  • The experience strengthened skills in UX/UI, API integration and agile deployment

Next Steps

  • Test integration with autonomous agents for automatic content updates
  • Create a blog section dedicated to project management and enterprise architecture topics, focusing on business architecture
  • Integrate the blog with email marketing strategies to increase reach and audience engagement
  • Implement automation for content distribution and optimisation to maximise impact and relevance
  • Expand to a multilingual version targeting international markets