AI & Automation Stack · FreeMalta
Rank on Google. Get cited
by AI. Trust the LLMs.
A beautiful website nobody finds is an expensive business card. In 2026, visibility means three things: ranking on Google (SEO), being cited by AI answer engines (AEO), and being trusted by LLMs (GEO). Firecrawl collects the data. Diginius finds the gaps. Emergent deploys the agents.
6,000+Indexed pages
40Articles/day
210K+Internal links
2–4hIndex time
Collect
Firecrawl
Web data
Analyse
Diginius
SEO intel
Orchestrate
N8N
Automation
Deploy
Emergent
AI agents
The strategy
Three fronts. One stack.
Why you need all of them.
SEO
Search Engine Optimisation
Google · Bing
Rank pages for specific keywords. Get clicks from traditional search results. Still the largest traffic source in 2026.
AEO
Answer Engine Optimisation
Perplexity · ChatGPT · AI Overviews
Get cited in AI-generated answers. The user asks, the AI answers and cites your page. The citation is the new backlink.
GEO
Generative Engine Optimisation
Claude · GPT · llms.txt · MCP
Make your content trusted by LLMs. Structured data, clear authorship, llms.txt. The frontier of web visibility.
Step 1 — Collect
Clean web data for Claude API.
No HTML noise. No maintenance.
Web Data Collection · Markdown Output
Firecrawl
Any URL → clean markdown → Claude API ready
Firecrawl converts any URL into clean markdown — no HTML noise, no JavaScript rendering issues, no bot detection problems. Claude API receives content it can actually read. News Beast uses Firecrawl to monitor 8+ Malta news sources every 2 hours, passing clean content straight to Claude for categorisation and rewriting.
How FreeMalta uses it — News Beast
Every 2 hours: Cloudflare cron triggers Firecrawl across 8 Malta news sources. Each article returns as clean markdown in under 3 seconds. Claude API receives it, categorises by topic (
The pipeline runs without maintenance. No scraper to update. No HTML parser to fix. Firecrawl handles the web's messiness so Claude API never sees it.
iGaming / Business / Politics), rewrites in editorial voice, generates slug and SEO metadata.The pipeline runs without maintenance. No scraper to update. No HTML parser to fix. Firecrawl handles the web's messiness so Claude API never sees it.
Works well when
Feeding clean data directly to Claude API
Monitoring competitor or news sites at scale
High-frequency scraping without maintenance
Enriching company profiles from websites
Watch out
Charges per page crawled — budget your usage
Some sites actively block crawlers
Not for real-time data (30s+ latency)
Step 2 — Analyse
Produce content that targets
gaps, not guesses.
SEO · PPC · Competitor Intelligence
Diginius
Keywords · Rankings · Paid search signals
Diginius tracks which keywords your competitors are ranking for, how rankings move week over week, and where paid search budgets are concentrated. Instead of guessing what to publish, Diginius surfaces real gaps — queries with volume where competitors are weak. Feed those into n8n, trigger a Claude content brief, and your programmatic SEO pipeline targets the right queries.
Real scenario — knowing what to rank for
A competitor's ranking jumps significantly on a keyword FreeMalta targets. Diginius flags the change via webhook → n8n catches it → passes the keyword to Claude API for a content brief → checks if FreeMalta has a page targeting that term → if not, triggers the programmatic content pipeline to create one.
Intelligence without action is just data. Diginius connected to n8n turns SEO signals into automated responses.
Intelligence without action is just data. Diginius connected to n8n turns SEO signals into automated responses.
Works well when
Monitoring competitor keyword movements weekly
Identifying PPC opportunities before scaling spend
Finding ranking gaps your content doesn't cover yet
Pairing with Firecrawl for full competitor picture
Watch out
Intelligence is only useful if you act on it
Data lags real-time — strategic not tactical tool
Combine with your own GSC data for full picture
Step 3 — Deploy
Agents that monitor, decide
and act. Without supervision.
Autonomous AI Agents · No-Code · Deploy
Emergent
Research → decide → execute. Without constant supervision.
Emergent builds and deploys autonomous AI agent workflows — agents that monitor sources, research topics, make decisions and execute actions across multiple steps without waiting for human input at each one. In a web intelligence workflow, Emergent handles the deployment layer: taking intelligence from Firecrawl and Diginius and acting on it autonomously.
Emergent · AI agent platform demo · freemalta.com
Real scenario — autonomous competitor monitoring
An Emergent agent monitors 12 competitor domains weekly. It scrapes via Firecrawl, identifies new content published, passes to Claude API for analysis — what topic, what angle, what keywords targeted. If a competitor publishes on a topic FreeMalta doesn't cover, the agent creates a content brief, logs it to Supabase, and sends a Slack notification.
No cron job to maintain. No workflow to trigger manually. The agent researches, decides and notifies. You review and approve.
No cron job to maintain. No workflow to trigger manually. The agent researches, decides and notifies. You review and approve.
Works well when
Multi-step research that runs without triggers
Competitor monitoring at scale
Content intelligence pipelines
No-code agent building — no dev team needed
Watch out
Agents need clear objectives — be specific
Review outputs before acting on them
Start simple, add complexity once stable
The architecture
How News Beast publishes 40 articles/day
for under €20/month.
Full News Beast pipeline
Cloudflare cron (every 2h) → Firecrawl (8 sources → markdown) →
Claude API (categorise + rewrite + slug + metadata) →
Supabase D1 (store at edge) → Cloudflare KV (cache) →
Cloudflare Worker (serve · ~80ms TTFB) → IndexNow (ping Google · <1s)
Claude API (categorise + rewrite + slug + metadata) →
Supabase D1 (store at edge) → Cloudflare KV (cache) →
Cloudflare Worker (serve · ~80ms TTFB) → IndexNow (ping Google · <1s)
NewsArticle schema injected per article automatically. Dynamic sitemap rebuilds from D1 on every request. Google sees new content within 2–4 hours. Total cost at current traffic: under €20/month. Scale 10x — still under €50/month.
Indexing speed
IndexNow + dynamic sitemap.
Indexed in hours, not days.
# Article stored → IndexNow submits URL immediately
→ await fetch('https://api.indexnow.org/indexnow', {
body: JSON.stringify({ host: 'freemalta.com', urlList: [articleUrl] })
})
✓ Submitted to Bing + Yandex (+ Google via partnership) in <1s
# Dynamic sitemap — always current, no manual updates
→ GET /sitemap-news.xml
→ SELECT slug, category, generated_at FROM articles ORDER BY generated_at DESC
✓ Sitemap reflects current content · regenerated on every request from D1
Programmatic SEO
One template. Thousands of pages.
How FreeMalta scales content.
| Property | Page structure | Example URL | Scale |
|---|---|---|---|
| Pharmacy Tool | 1 template × locality × pharmacy × hours | /pharmacies/sliema | 400+ pages |
| Markets / Garage | 1 template × company × sector + categories | /markets/company-stories/acme-igaming | 300+ pages |
| News Beast | 1 template × article × category × date | /news/igaming/article-slug | 40/day · growing |
| Hub Partners | 1 template × partner × category | /hub/partners/deel | 71 pages |
| Hub Stacks | 1 template × stack × FAQ schema | /hub/outbound-sales | 10+ pages |
Structured data
Schema markup — what FreeMalta
implements and why.
Schema is injected via PHP template, not manually per page. Write once. Generate a thousand times.
BreadcrumbList
Shows page hierarchy in Google results. Users know where they are before clicking.
Used on: Every hub page, partner page, stack page
FAQPage
Surfaces Q&A in Google results. Heavily used by AI answer engines to extract structured answers for citations.
Used on: All hub, partner and stack pages
NewsArticle
Eligible for Top Stories carousel and News tab. Critical for News Beast indexing speed.
Used on: Every News Beast article
LocalBusiness + Pharmacy
Powers rich results for local searches — opening hours, location, on-duty status.
Used on: All 400+ pharmacy pages
AggregateRating
Displays star ratings in search results. Increases CTR by 15–30%.
Used on: Company profiles, Garage listings
Organization
Establishes entity identity for Google's Knowledge Graph. Critical for AI model trust signals.
Used on: About page, partner detail pages
The AI frontier — GEO
llms.txt and MCP.
Being found by AI, not just Google.
In 2026, an increasing share of information retrieval happens through AI interfaces. The sites that get cited are the new page 1.
llms.txt is an emerging standard (analogous to robots.txt) that tells LLMs what content on your site is available and how it's structured. MCP (Model Context Protocol) — Anthropic's open standard — goes further: it allows AI agents to directly query your database or APIs without scraping your website.
FreeMalta's 6,000+ indexed pages of unique Malta-specific data are exactly what AI answer engines need — specific, verifiable, regularly updated, with clear authorship. The citation is the new backlink.
FreeMalta's 6,000+ indexed pages of unique Malta-specific data are exactly what AI answer engines need — specific, verifiable, regularly updated, with clear authorship. The citation is the new backlink.
llms.txt
Declares your content structure to LLMs. Ensures AI engines understand and correctly cite your site.
MCP (Anthropic)
Allows Claude and other agents to query your database directly — live data, not cached web content.
Full stack
Every tool in the
web intelligence pipeline.
Firecrawl
Collect
Any URL → clean markdown → Claude API ready. Powers the News Beast scraping pipeline.
Get Firecrawl →
Diginius
Analyse
SEO, PPC and competitor intelligence. Surface keyword gaps before your competitors fill them.
Get Diginius →
Emergent
Deploy
Autonomous agents that monitor, research and act. No constant supervision required.
Get Emergent →
n8n
Orchestrate
Connects Firecrawl, Diginius, Claude API and Supabase into one automated pipeline.
Get n8n →
Claude API
Process
Categorise, rewrite, generate metadata and schema. The intelligence layer of every pipeline.
Get API →
Cloudflare
Serve
Workers + D1 + KV + R2. The edge infrastructure that serves FreeMalta at ~80ms TTFB.
Get Cloudflare →
Frequently Asked Questions
What is the difference between SEO, AEO and GEO?
SEO (Search Engine Optimisation) is optimising for traditional search engines like Google — getting pages to rank for specific keywords. AEO (Answer Engine Optimisation) is optimising for AI-powered answer engines like Perplexity, ChatGPT Search and Google AI Overviews — these extract and synthesise answers, and cite sources. GEO (Generative Engine Optimisation) is optimising for Large Language Models that generate responses — making sure your content is trusted, structured and citable by AI systems. In 2026, a serious web strategy needs all three.
What is programmatic SEO and how does FreeMalta use it?
Programmatic SEO is creating large numbers of unique, data-driven pages at scale — each targeting a specific search query. FreeMalta uses this across every property: the Pharmacy tool generates pages for every locality and pharmacy in Malta (400+ pages), Markets and Garage cover company profiles and categories (300+ pages), and News Beast publishes 40 new indexed articles every day. Each page has its own URL, metadata and schema — generated automatically from structured data.
What is Diginius and how does it fit into a web intelligence stack?
Diginius is a digital marketing intelligence platform for SEO, PPC and competitor analysis. In a web intelligence workflow, it sits between data collection (Firecrawl) and automation (n8n) — surfacing which keywords competitors are ranking for, how paid search budgets are being allocated, and where ranking opportunities exist. Instead of manually monitoring competitor sites, Diginius tracks it automatically and flags changes. You act on intelligence, not guesswork.
What is IndexNow and why does it matter for News Beast?
IndexNow is a protocol that allows websites to instantly notify search engines when content is published — rather than waiting for a crawler to discover it. News Beast publishes 40 articles per day. Without IndexNow, Google might take days to discover new articles. With IndexNow, each article is submitted to search engines within seconds of publication. FreeMalta articles typically appear in Google Search Console within 2–4 hours of being published.
What is llms.txt and why does it matter in 2026?
llms.txt is an emerging standard that tells Large Language Models what content on your site is available and how it's structured. As AI answer engines like Perplexity, ChatGPT and Claude increasingly serve answers by reading and citing web content, a well-structured llms.txt ensures your site is correctly understood and cited. FreeMalta's 2,000+ indexed pages contain unique Malta-specific data that AI answer engines increasingly surface when users ask Malta-related questions. The citation is the new backlink.
What does Emergent do in a web intelligence workflow?
Emergent is a platform for building and deploying autonomous AI agent workflows. In a web intelligence context, Emergent handles the deployment layer — taking the intelligence gathered by Firecrawl and Diginius, processed by n8n, and turning it into autonomous agents that act on it: publishing content, updating pages, triggering alerts, or running competitor response workflows. Multi-step agents that research, decide and execute without constant human supervision.
What schema markup does FreeMalta use?
FreeMalta implements six schema types: BreadcrumbList (every hub and partner page), FAQPage (all content pages — heavily used by AI answer engines for citation), Organization (brand identity), NewsArticle (every News Beast article — eligible for Top Stories), LocalBusiness/Pharmacy (pharmacy pages with opening hours and ratings), and AggregateRating (company profiles). Schema is implemented automatically via PHP templates — not manually per page.
Other stacks
FreeMalta earns a commission if you sign up through our links — at no cost to you. Pricing verified at time of writing — always confirm current plans directly with each provider.