PRIVATE BETAJoin the waitlist →
QuantyQuantyBETA
COMING SOON · AI FOR LOGISTICS PAPERWORK

Freight paperwork in.
Answers out.

The AI sheet that reads handwritten CMRs, customs papers and carrier invoices, verifies them against registries, and shows its work.

Join the waitlistSee how it works ↓
Beta members are first in line and always keep our best offer
Freight invoice auditemail-connected
3 AI columns running
▤ File
T Carrier
# Amount
◎ Vs rate card AI
◎ Documents AI
44
BaltiqTrans_inv_0455.pdfvia email · just now
BaltiqTrans
€2,240.00
41
Nordhaul_inv_2214.pdfvia email
Nordhaul AS
€1,890.00
matches card
✓ POD · CMR filed
42
TransNova_inv_301.pdfvia email
TransNova Sp. z o.o.
€2,340.00
+€310 over card
◦ POD missing
43
Freight_inv_0921.pdfuploaded
Veloxa Spedition
€980.00
matches card
✓ POD · CMR filed
✉ freight+invoices@in.quanty.app → appends herelast write 4 min ago · undoable
CMR filed → SH-1204stamp and signature found · 0.99weights agree · CMR ↔ invoice ↔ scaledetention flagged · over contractPOD missing → reminder draftedcustoms file complete · SH-1188VAT check passed · biała listalow confidence → human reviewCMR filed → SH-1204stamp and signature found · 0.99weights agree · CMR ↔ invoice ↔ scaledetention flagged · over contractPOD missing → reminder draftedcustoms file complete · SH-1188VAT check passed · biała listalow confidence → human review
ONE SOURCE OF TRUTH

Many inputs. One source of truth.

Carrier emails, CMR scans, invoices and TMS exports pour in. Quanty reads them all and keeps one verified table your dispatch and finance can trust.

Join the waitlist
THE SHIPMENT FILE

One shipment. One file. One status.

A transport order opens the file. Documents flow in on their own: from email, from the customs agent, from driver photos. Quanty reads them, checks them against each other and against state registries, and the signed POD closes the loop straight into invoicing.

SH-1204Hamburg → Poznań · FTLReady to invoice
Documents
PDFZlecenie_0917.pdfemail
JPGCMR_signed.jpgdriver photo
PDFFaktura_2214.pdfemail
XLSXPacking_list.xlsxemail
JPGKwit_wagowy.jpgdriver photo
42fields extracted · every one cited
documents7/7complete
cross-checks6/6all agree
registry checks3/3biała lista · VIES · EORI
POD signed14:28geotagged at the ramp
Checks
Gross weight · CMR ↔ invoice ↔ weighbridge24,120 kgagree
Pallets · CMR ↔ packing list33 EURagree
Carrier VAT · biała listaPL 9491924611pass
InvoicingPOD filedreleased same day
Road freight playbookGroups incoming documents into shipments, keeps the expected-documents checklist, and alerts before the border, not at it.
ASK YOUR DOCUMENTS

Chat with every document at once.

Describe a job, pick a model, and Quanty shows a plan first. Every answer cites the pages it came from.

Good morning, Dawid.

Describe a job, or pick up where you left off.

Ask anything, or describe a workflow, e.g. "check June carrier invoices from @Freight 2026 against the rate cards"
+ files▣ library▤ templates
⏎ shows a plan first · nothing runs unreviewed
HOW IT WORKS

Just a spreadsheet. Until you add a column.

This is the actual grid: rows are documents, columns are properties you define, everything one click deep.

Home / Freight invoice auditEmail-connected · watching +freight@
Chat with AIExport
+ Add row+ Add columnFilter rows…
1,204 rows · 8 columnsCompletedRecompute stale (12)Review3PipelineRun
File
T Carrier AI
# Amount AI
Invoice date AI
Payment terms AI
Edit column
Recompute all cells
Duplicate column
Compare models (A/B)
Pin column
Hide column
Delete column
# Δ vs rate card PY
+
1
Nordhaul_inv_2214.pdf
Nordhaul AS
€1,890.00
2026-07-02
Net 30 p.2
0.00
2
TransNova_inv_301.pdf
TransNova Sp. z o.o.
€2,340.00
2026-07-04
Net 60 p.4stale
+120.50
3
Freight_inv_0921.pdf
Veloxa Spedition
€980.00
2026-07-05
Net 14edited
0.00
4
BaltiqTrans_inv_0455.pdf
BaltiqTrans
€2,240.00
2026-07-08
processing
5
CMR_SH-1204_scan.pdf
HanzaTruck Sp. z o.o.
zł4,520.00
2026-07-09
Net 30 p.1
0.00
Page 1Q3 freight audit+ Add Page
or email +freight@
1
Every row is a documentDrop in PDFs and scans, or let email feed the sheet. Rows that arrived on their own carry a small bolt.
2
Every column is a propertyPick a type: text, number, date, select, JSON. Write a prompt in plain language and AI, Python or Web fills it for every row.
3
Click a column to work itRecompute stale cells, compare models A/B, pin or hide. Uncertain values queue for human review instead of writing themselves.
BUILT FOR LOGISTICS

Hours of reading. Minutes of reviewing.

Forwarders, carriers and customs teams run the same pattern: Quanty does the reading, your team does the judging.

See the full logistics page →
Freight audit45× faster
1€1,890matches rate card
2€2,340over rate card
3€980matches rate card
4€1,120no shipment
Carrier invoices checked against rate cards
Every charge line lands next to the rate that governs it. Disagreement is loud.
Order intake38× faster
Inbox
38 orders
Extract
route · rate · dates
Clause check
penalties · pallets
Review
3 exceptions
Export
TMS / CSV
Transport orders become rows on arrival
Route, rate, deadlines and the clauses that bite, extracted from every emailed order.
POD & CMR30× faster
1SH-1204complete
2SH-1210POD missing
3SH-1213complete
4SH-1218CMR illegible
No proof, no payment, no surprises
Each shipment shows which documents arrived and which are still on the road.
Customs32× faster
01EUR.1 missing · request drafted
02Weights disagree with CMR
03Incoterms consistent · DAP
Customs files checked before the border
Completeness and consistency checks on the customs documents of every shipment.
Carrier vetting20× faster
1TransNovavalid to 03/27
2BaltiqTransexpires in 14d
3RoadServsum too low
4HanzaTruckpass
Licences and insurance, watched for you
Expiry dates and insurance sums extracted and monitored for every subcontractor.
From the road15× faster
CMR_SH-1210.jpgPOD_scan_0417.jpgKwit_paletowy_112.jpg
Documents photographed at the ramp
Driver links, in development: CMRs and PODs filed to the shipment in seconds. No app.
45×
faster invoice checking
4 min
from email to a checked row
0
values without a source
AI COLUMNS

The column is the interface.

A column is a prompt in plain language: pick an output type, write the question, test on one row, run on every document.

Freight invoice audit
Run all
▤ File
# Amount
◎ Payment terms ←
1
Nordhaul_rates_2026.pdf
€1,890
Net 30 p.2
2
TransNova_contract.pdf
€2,340
Net 60 · flagged p.4
3
Veloxa_rate_card_Q3.pdf
€980
Net 14 p.1
4
BaltiqTrans_annex_v2.pdf
€1,820
→ human review · 0.61 ·
1,204 rows · avg 0.8s per row
Payment terms
Type
TextSelectNumberDate
Model
claude-haiku
Prompt@ references other columns
Extract the payment terms from @File. Flag anything longer than Net 45.
Grounding · citations
links every value to its source page
Confidence gate< 0.90 → human review
TEST ON ONE ROW
◰ Nordhaul_contract_2026.pdfNet 60 · flaggedp.40.94
Save · run on 1,204 rows
same prompt, same format, same model · on row 1 and row 10,000
EVERY VALUE HAS A SOURCE

Click a cell. See the proof.

Every AI-filled cell opens the exact quote, its page and a confidence score. Approve, fix or rerun, one click each.

▤ File
◎ Doc type
# Detention rate
1
◰ Nordhaul_contract_2026.pdf
Carrier contract
€40 / h p.4
#Detention rate· Nordhaul_contract_2026.pdf
€40 / hconf 0.94
p.4 §7.1 · Waiting time and detention
"…two (2) hours of free waiting time at loading and unloading; thereafter EUR 40 per commenced hour shall apply…"
Open in source viewer →
✓ Approve✎ Edit↻ Rerun
COMING TO QUANTY

Type a NIP. Get registry proof.

Phantom carriers are the fastest-growing fraud in road freight. Soon every carrier and counterparty is checked against live state registries, not just the document. Try it now: one NIP, three registries and an official evidence ID you keep.

Verify
or try an example: 7740001454
Biała lista VAT
Ministry of Finance · wl-api.mf.gov.pl
·
VIES
European Commission · ec.europa.eu
·
KRS
National Court Register · api-krs.ms.gov.pl
·
ALSO ON THE WAY

Registries prove them. The open web completes them.

Verification is just the start. Describe the companies you need and Quanty fills the sheet from the open web: size, locations, people, news, funding. A full profile for every counterparty, not just a VAT status.

Food wholesalers in Wielkopolska, 20 to 200 employees
Complete · 24 companies · 6 columns
COMPANY
CITY
EMPLOYEES
LATEST SIGNAL
Agrohurt Wielkopolska
Poznań
120
opened a cold storage site
FreshLine Trade
Kalisz
45
expanding EU exports
Polfood Serwis
Leszno
80
won a public tender
Danex Dystrybucja
Konin
35
new contract in Germany
+ 20 more rows

In Quanty this runs as a column: every carrier and every invoice verified automatically, every result logged with proof.

Join the waitlist
live demo · real registries · nothing you type is stored
UNDER THE HOOD

Every answer comes with context.

Quanty links documents, counterparties and values into a knowledge graph. Every cell it fills draws on the context of your whole system, not just one file.

Invoice 0921
Nordhaul AS
Order ZL-0917
Rate card Q3
Email thread
CMR SH-1204
POD SH-1204
Shipment SH-1204
Customs file
Commercial invoice
Packing list
EUR.1 certificate
Detention clause
Invoice 0924
issued bymatchesgoverned byarrived viadelivered underproven bypriced bybelongs tocleared bysigned withdeclared inconfirmed bylisted infollowsprices
AUTOMATIONS

Forward an email. That's the whole setup.

Rules read like sentences: mail arrives, decide what it is, act. Anything uncertain waits for a human. Nothing writes on its own.

← Automations
Carrier invoice intake● Active
Send test emailSave changes
TRIGGER · email arrives
Inbound email
+invoices@in.quanty.app
Only allowlisted senders · PDF attached
CLASSIFY · AI decision
What is this email? AI
Decide: carrier invoice, POD or CMR, something else.
Confidence < 0.8 → human review
BRANCHES · then do
carrier invoicesave file → append row → run AI columns → reply "received"
POD or CMRfile to its shipment · completeness chip flips → notify #dispatch
something elsehold in Needs review · no writes
dry run passed · nothing is written until you activate
INTEGRATIONS

Email and Google Sheets today. Your whole stack next.

The beta starts with inbound email and Google Sheets: every sheet gets its own address, and any Google spreadsheet can sync rows in or out. TMS and ERP connectors follow: fireTMS, interLAN, Comarch, SAP Business One.

Emailin betaGoogle Sheetsin betaGmailcoming soonOutlookcoming soonfireTMScoming sooninterLANcoming soonComarch ERPcoming soonSAP Business Onecoming soonGoogle Drivecoming soon
END TO END

Every source in. Every deliverable out.

Point Quanty at a quarter of shipments and it reads everything at once. Out come audits, dispute packs and alerts in the systems you already use.

Order archive
SharePoint
Email inbox
invoices & PODs
TMS export
shipments
Rate cards
CSV / XLSX
Carrier contracts
OCP & annexes
Quanty
cross-document reasoning
Freight_audit_Q3.xlsx
created
Claims_summary.pptx
drafted
Carrier red-flag report
saved to Drive
Dispute email to carrier
drafted
#dispatch
notified
WHY NOT JUST A CHATBOT?

One prompt. Two very different answers.

Ask the same question about the same PDF, twice. On the left, a plain chatbot. On the right, the same model inside Quanty.

The full story: why LLMs need this →
What are the payment terms in ◰ Nordhaul_contract_2026.pdf ?
Without Quanty · plain chatbot
RUN 1
"The payment terms are Net 60. Payment is due within 60 days of the invoice date."
RUN 2 · same question again
"Payment is generally due within about two months of invoicing."
A different phrasing every run. Impossible to sort or audit.No source. You verify by rereading the PDF yourself.Sounds equally confident when it is wrong.
With Quanty
RUN 1
NET_60⚑ flagged · over policyp.4 §2.10.94
RUN 2 · same question again
NET_60identical · served from cache, zero tokens
p.4 §2.1 · "…payments shall be due sixty (60) days from the date of invoice…"
The same typed answer every run: pinned prompt, format and model.Cites page and section. The quote is one click away.Below 0.90 confidence it goes to human review, not into your data.
WHY QUANTY

AI finally reads your paperwork.
Quanty makes it trustworthy.

Pasting your paperwork into a chatbot fails in three predictable ways. Quanty keeps the reading ability and engineers away the rest.

01 · CONTEXT

A model can't hold your filing cabinet in its head.

Paste 300 invoices into a chat and attention thins out: document 214 blends with 209, the key clause slips by, and the tone stays confident.

✕ ONE GIANT PROMPT
Document 3 · read correctly
Document 214 · blended with 209
Document 288 · clause missed entirely
All 300 documents compete for the same attention. Errors hide in the middle.
✓ ONE ROW, ONE DOCUMENT
Row 3 · its own focused read
Row 214 · its own focused read
Row 288 · its own focused read
Quanty gives the model one document and one question at a time. Accuracy does not depend on where the file sits in the pile.
02 · REPEATABLE TASKS

A chat forgets your procedure. A column is the procedure.

In a chatbot you re-explain the task every Monday and get slightly different answers. In Quanty the task is a column: same prompt, same format, same model, on row 1 and row 10,000.

✕ RE-TYPED EVERY TIME
MON "Net 30"
TUE "30 days from invoice date"
WED "about a month"
Three days, three phrasings. You can't sort, filter or audit that.
✓ SAVED AS A COLUMNv4 · pinned
MON NET_30
TUE NET_30
WED NET_30
Same document, same answer. Today and in next year's audit.
03 · TRUST

Confidence is not evidence.

A chatbot answers fluently, right or wrong, and checking means rereading everything yourself. In Quanty every value carries its own proof.

✕ A FLUENT GUESS
"The contract renews automatically on March 1st with a 5% uplift."
No source. No score. Wrong, and it reads exactly like the truth.
✓ A CITED CELL
Renews April 15, 2027 · uplift 3%
◰ Umowa_MSA.pdf · p.12 §9.2confidence 0.98
Click the citation, see the page. Below your confidence bar, it goes to a human instead of the sheet.
IN SHORT

Same model. Different discipline.

A CHATBOT
QUANTY
CONTEXT
All your documents in one prompt, competing for attention
One document, one question per cell
PROCEDURE
Re-typed every time, drifting a little each day
Saved as a column: pinned prompt, format and model
OUTPUT
Prose that changes shape on every run
Typed values that sort, filter and export
PROOF
None. You reread the documents to verify
Every value cites its page; one click to check
WHEN UNSURE
Guesses confidently anyway
Goes to a human review queue, not into your data
RE-RUNS
Full re-read, full cost, new answers
Cached results; only stale cells recompute
LAUNCHING FALL 2026

Be there before everyone else.

Join the waitlist and get first access as seats open. Whatever we charge later, beta members always keep the better offer.

By submitting this form I confirm I have read and accepted Quanty’s Privacy Policy.

First in lineAlways our best offerDirect line to the team
no spam · one email when your seat opens
QuantyQuanty© 2026 Pluscode Sp. z o.o.
ProductFor logisticsPricingWhy QuantyPrivacy PolicyTerms of Service