BUILT BY AX DIGITAL · RUNNING ON A REAL SITE RIGHT NOW

Everything you’ve published.
Everything you’re missing.

Axific crawls a real site, clusters what’s actually been published, and diffs it against real search demand, real competitors, and its own internal links — so you know exactly what to build next, not just that “content is a gap.”

No demo dataset. No lorem ipsum. axdigital.com.au, crawled today.
real hop-distance layout = gap
56
real pages crawled
18
real topic clusters
(Jaccard + Louvain)
94
real gaps found
across 3 detection modes
4
real competitors
crawled & diffed
94
content briefs
generated
How it works

Five real phases. Each one feeds the next.

Not a feature list — an actual pipeline. Each phase’s output is the next phase’s real input, run in this order, against a real database.

01

Crawl

Sitemap-first with a BFS fallback, robots.txt-respecting. Never touches CMS internals — crawlSite.mjs treats a WordPress site, a Shopify store, or a hand-coded page exactly the same way a real visitor’s browser would.

02

Extract

Claude reads every real page and pulls its actual entities, primary topic, and search intent — not keyword string-matching.

03

Cluster

Jaccard similarity across real entity sets, then Louvain community detection groups content by what it’s actually about — deterministic, explainable, no black-box embedding.

04

Diff

Three independent, real gap types: question-gap (real search demand nothing answers), competitor-diff (a real competitor covers it, you don’t), link-gap (it exists, but nothing real links to it).

05

Brief

Every gap becomes a brief someone can write from today — real word-count targets from real comparable pages, real internal links chosen from real candidate pages. Never an invented URL, never a fabricated case study.

The output

See the whole site as a map, not a spreadsheet.

Every node is a real page or a real gap. Position is real BFS hop-distance from the homepage — not a random force-directed guess. Four markers tell you what you’re looking at before you even click:

🏠 / 📁 Home, or a real archive/index page
🔌 Orphaned — a real page nothing real links to
📝 A gap with a full brief already written
Ring colour How many real clicks from home
DOGFOODED, NOT DEMOED

Built by AX Digital. Proven on AX Digital first.

Before this runs on anyone else’s site, it had to survive running on ours. Every number on this page came from a real crawl of axdigital.com.au — no seeded dataset, no cherry-picked example.

The competitor-diff step was the real test: the first time this crawler had ever pointed at a domain that wasn’t axdigital.com.au. It held up across all four.

  • 13→2 of 17 “hub” pages turned out to have zero real inbound links — a false signal, found and fixed before it shipped
  • 58 real gaps found against Shout Digital, Clearwater Agency, StudioHawk, Temerity Digital
  • 3 low-value false positives (a staff bio, a podcast mention) caught and pruned on review, not left in

Want this running on your own site?

This is still early — validating internally before it’s offered more broadly. If you want to talk about what it’d take to run this on your site, get in touch.

Get in touch
Curious what the live data actually looks like first? Head to the demo above.