Ideas, tutorials and processes
I publish analysis, tutorials and experiments about AI automation, iOS development, FinTech and technical SEO. All content is original.
The goal of the blog is to leave a trace of how I think and build: real problems, technical decisions, constraints, results and lessons for developers, clients or teams that want to apply technology with judgment.
AI automation
Real cases with n8n, LLMs, APIs and workflows that reduce manual work without losing control. I focus on architecture, maintenance and measurable results.
iOS development
Notes on SwiftUI, privacy, App Store and technical decisions from building my own apps. I include product, performance and publishing lessons.
FinTech and data
Backtesting, risk metrics and quantitative analysis explained through auditable projects. The goal is to separate intuition, data and bias.
SEO and GEO
Structure, rich data and content prepared for classic search engines and generative engines. I work on canonicals, sitemap, schema and semantic clarity.
NexaVision AI: from loose automations to an AI product for SMBs
How I am shaping NexaVision AI as an AI automation product for SMBs: support, leads, internal processes, content, n8n and LLMs.
AI model ranking in July 2026: value for money and China's rise
A practical July 2026 ranking of AI models: GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, GLM and MiniMax by value for money.
Agentic search and GEO in 2026: what changes for portfolios, brands and automation
Analysis of agentic search in 2026: Google Search, workspace agents, Claude Sonnet 5, GEO, AI SEO and LLM-powered automation.
Applied AI strategy: from idea to roadmap with real use cases
A practical guide to prioritising AI use cases, defining roadmaps, building MVPs, measuring impact and avoiding demos with no business value.
From scattered data to useful dashboards: business analytics with Python, SQL and automation
How to turn scattered data into business dashboards: sources, cleaning, SQL, Python, KPIs, Power BI, automation and documentation.
AI process architecture: turning manual work into measurable workflows
A practical guide to turning manual processes into AI workflows with BPM, KPIs, SLAs, runbooks, n8n, validation and human review.
Deepfakes, impersonation and identity verification in the AI era
A defensive analysis of deepfakes, synthetic documents and AI identity verification: risks, KYC, detection, liveness and human review.
My Bitcoin analysis: from the 126K top to the 2026 cycle correction
A review of my October and December Bitcoin videos: 122K-126K resistance, EMAs, regression, seasonality, cycles and the current BTC situation.
AI automation in regulated environments: banking, insurance and operational control
How I would design AI automations for banking, insurance and regulated companies: data, permissions, traces, validation and human review.
AI news June 2026: agents, search and enterprise control
Analysis of recent AI updates: managed agents, AI search, Claude Opus 4.8, enterprise controls and real-world automation.
Versioning prompts and workflows for AI agents
How I version prompts, n8n workflows and AI agents in production with changelogs, evaluation, rollback, traces and safe deployments.
Observability for AI agents in production
How I design observability for AI agents: traces, logs, metrics, costs, errors, privacy and continuous improvement.
Human-in-the-loop for AI agents and business automation
How I design human-in-the-loop flows for AI agents: autonomy levels, approvals, confidence, risk, traceability and escalation.
Multi-tenant architecture with n8n and AI agents
How I design multi-tenant architecture for n8n automations, AI agents, isolated credentials, VPS deployments and traceability.
How I evaluate AI agents before putting them into production
A practical guide to evaluating AI agents with datasets, tools, guardrails, traces, cost metrics and human review before production.
Security and privacy for enterprise AI agents
A practical checklist for building secure enterprise AI agents: permissions, data, PII, secrets, logs, tools and human review.
RAG, web search, fine-tuning or rules: choosing for an LLM system
A guide to choosing between RAG, web search, fine-tuning and deterministic rules when building assistants and LLM automations.
From demo to production: how I design reliable AI automations
A practical guide to production AI automation with idempotency, retries, validation, observability and human review.
OSINT with LLMs: turning web search into verifiable evidence
How I design OSINT systems with LLMs and web search: sources, evidence, confidence, security, evaluation and human review.
19 fragrances I previously owned
An archive of the 19 fragrances I previously owned and what this journey explains about the evolution of my current collection.
34 fragrances I want to own in my collection
My target fragrance collection: 34 bottles I want to own, the flankers I would compare and the order in which I would add them.
My fragrance collection: what I wear in warm and cold weather
A personal guide to my 23 fragrances: scent profiles, approximate longevity, prices and which bottles work best in warm or cold weather.
49 fragrances I want to sample: my wishlist and comparisons
My reasoned fragrance wishlist: 49 scents to sample, comparisons with my collection and a prioritized first sampling round.
n8n, FastAPI or Spring: how I choose architecture for AI automation
A practical guide to choosing n8n, FastAPI, Spring or a hybrid architecture when building reliable AI automations and agents.
What working at Mango and Zara taught me about customer service AI agents
How my experience at Mango and Zara shapes the way I design reliable AI agents with context, guardrails, tools, evaluation and human escalation.
GymTracker: how I published my first iOS app with SwiftUI and CoreData
How I designed, built and published GymTracker: a native iOS app with SwiftUI, CoreData, offline-first architecture and zero data collection.
Restaurant booking system with AI, WhatsApp and n8n
How I built a restaurant booking system with WhatsApp, n8n, AI, Google Calendar, capacity checks, email confirmations and cancellations.
Croissant Adventure: how I built a full web game in vanilla JavaScript
How I built Croissant Adventure, a vanilla JavaScript web game with a central world, minigames, characters, AI chat, Firebase and a custom engine.
FadeChain: how we built a private blockchain voting system with zero-knowledge
FadeChain explained: private voting on Ethereum Sepolia with zk-SNARKs, Merkle trees, a relayer and time-weighted votes.
How I found an internship in one week by automating LinkedIn and ranking offers with data
How I used Selenium, analysis of 10,000 LinkedIn job offers and reverse engineering of ATS filters to get 10 interviews from only 15 emails.
The Python algorithm I built to get SEPE appointments
How I built a Python bot to automate SEPE appointment checks, why it had impact and what I learned about ethical automation, PyAutoGUI and public services.
The AI systems I have built for NexaVision AI
A technical and product overview of the AI systems I have built for NexaVision AI: agents, leads, content, calls, HR and business automation with n8n.
NexaVision AI: what I am building and why it is one of my most important projects
How I am building NexaVision AI with Roger Pumarola: AI agents, n8n, business automation and product lessons.
Welcome to the blog: why I am launching it and what you will read here
Introduction to Gorka Hernandez's personal blog: AI automation, iOS development, FinTech and technical SEO with practical judgment.