Corridors: 200 origins × 199 destinations, roughly 400,000 pages
VFS Travel
Intelligence Engine
VFS Global
360 Labs
September 2026
Anyone can generate an answer
Corridors, 4.6% of the universe. Where production starts
Corridors crawled end to end. Proof of mechanism, not of scope
Capability
Sources are scattered and change with no notice, no changelog and no API. Discovery never finishes.
Cost
Naive crawling and extraction at 40,000 corridors costs more than the answers are worth.
Governance
Models hallucinate. A named person still decides what reaches a traveller.
Ownership
The intelligence, the registry and the review decisions have to stay VFS property.
What is live today
Across 67 destinations, every line quoted from its source
1,338 read through the VFS content API, across 63 destinations and 161 origins. 53 destinations are 100% grounded.
Pairs answered from a government or VFS source
17.3% of all pairs, and half of VFS’s own: 6,328 of the 12,672 pairs inside VFS’s 86 destinations.
510 of 512 claims carried verbatim evidence
The 2 that did not were dropped automatically. Compression before extraction: 8.97M tokens to 6,718, with 16 of 16 probe facts recovered.
How it works
Discover
Find, validate, qualify, then a human ratifies the source
Fetch
Cheapest rung first: HTTP, in-country IP, browser, stealth only if flagged
Harmonise
Rules where the source is typed, a model only where it is not
Ground
A verifier outside the model drops any line it cannot find verbatim
Knowledge base
A graph of facts with source, authority and fetch time
Serve
Database read. Zero model calls when a traveller asks
Effort tracks change, not corridors
At 400,000 pages: 94% unchanged after a week, ~5.7% hash change a day, and only 0.12 to 0.23% material, which is 480 to 920 pages and 16 to 31 reviewer hours a day.
VFS owns the intelligence layer
Corpus, knowledge graph, source registry, prompts and every review decision. The model provider and the cloud are replaceable suppliers.
The live prototype
Live prototype
The sandbox could not be loaded here. It may be offline, or you may have no network connection.
Open chancery.360labs.tech/sandboxCommercials and next steps
| Option 1 · Build and handover | Option 2 · Build and maintain | |
|---|---|---|
| 360 Labs build fee | $26,000 | $26,000 |
| Team and timeline | A 4-person pod for 2 months: AI-native engineering lead, PM and 2 full-stack AI engineers. | The same team, scope and timeline. |
| After the build | Structured handover; your team runs it. | $2,500 a month for 2 engineers: maintenance, source growth and improvements. |
| Infrastructure, paid by VFS | ~$90 a year for the VFS estate, rising to ~$32,300 at full global coverage. Today’s running range: US$550 to 1,450 a month. Optional GPU cluster: ~US$11,000 one-time. | |
Gold-set review
You pick the corridors; we show the answers, quotes and sources.
Consular review
Your team checks jurisdiction and district handling.
Scheduled monitoring
Turn the daily loop on for an agreed set and watch what it catches.
Scoping call
Confirm priorities and access, then start the pod.