Skip to content

Gap analysis

Gap analysis of invoiced prices with AI: where gaps come from, what they cost, which to handle first

Gap analysis starts from the price gaps already found between your invoices and your agreements, and answers three questions: what causes them, with which supplier and in which category they concentrate, and which are worth handling first. Zylio’s Exception agent classifies, aggregates and prioritises; the decision to recover or renegotiate remains yours.

The problem

A list of gaps is not an analysis

Systematic invoice control produces gaps. Many. One cent on a common reference, a discount forgotten on an order, a delivery charge on a shipment that should have been free. Taken one by one, none justifies a claim; taken together, they add up to an amount nobody knows. The list exists; the analysis does not.

Without analysis, you handle in order of arrival. The large isolated gap is disputed because it is visible; the small gap repeated a thousand times is accepted because it is tiring. You do not know whether the problem comes from the supplier who never updated its price list, the buyer who ordered off catalogue, or the contract whose revision clause is ambiguous. And the following year, renegotiation starts again from the theoretical price.

Gap analysis makes the list readable: by cause, by supplier, by category, by site, by period. It says where the money concentrates, what repeats, and what is easy to recover. It does not decide; it makes deciding possible.

The typology

Six causes of price gaps, and what each one implies

Two gaps of the same amount are not handled the same way. The cause determines the outcome: claim, internal correction or renegotiation.

  • The base price not updated

    The supplier invoices the old price, or a price that was never in the schedule. Supplier-side cause, simple claim, often recurring on every line of a reference.

  • The discount not applied

    Volume tier reached and not reflected, category discount forgotten, discount calculated on the wrong amount. Contractual cause, claim argued with the clause.

  • The revision outside the clause

    Increase applied before the scheduled date, on the wrong index, or at a rate higher than agreed. Contractual cause, sometimes disputable, often to clarify in the next amendment.

  • Ancillary charges outside the agreement

    Delivery, packaging, handling, urgency, invoiced against the contract or with no clause at all. Mixed cause: sometimes the supplier, sometimes an order placed without restating the terms.

  • The off-catalogue purchase

    An equivalent reference existed in the contract; another was ordered at a free price. Internal cause, no claim possible, but a signal for procurement.

  • Drift over time

    A price compliant at the start that moves away month after month, with no amendment. No single line is plainly wrong; the trend is. Visible only when aggregated.

The mechanism

How the Exception agent analyses gaps

  1. 01

    Gather the gaps found

    Those the Compliance agent raised by confronting prices with the contract, those the Matching agent raised between order, receipt and invoice. Each arrives with its line, its clause and its amount.

  2. 02

    Classify by cause

    Each gap is tied to one of the causes in the typology, with a confidence level. When the cause is ambiguous (revision or price not updated?), the agent says so, and shows both readings.

  3. 03

    Aggregate

    By supplier, by spend category, by site, by period. The repeated cent becomes an amount; the drift becomes a curve; the supplier concentrating half the gaps appears.

  4. 04

    Prioritise and report

    Amount at stake, recurrence, ease of recovery, clause that can be invoked: each group of gaps receives a rank and a suggested outcome. The deliverable is a file per supplier, each figure tied to the lines that make it up.

ERP exception management with AI

The pillar: what the Exception agent takes on, and what it never decides.

Prioritising

Where to start, and why it is not always the largest gap

Intuition says start with the highest gap. Analysis often says otherwise. A one-cent base price gap on a reference ordered ten thousand times a quarter weighs more than an isolated error of several hundred euros, and it is easier to recover: one claim, one clause, one correction at the supplier that holds for every line to come.

Likewise, a volume discount not applied by one supplier is claimed once, with the contract tier as evidence; an off-catalogue purchase is not claimed, but corrected internally. The agent suggests the order and the outcome. Your teams decide, supplier by supplier, knowing the amount, the evidence and the effort.

Zylio hides no calculation. No black box: every gap is traced back to its source.

What it changes

What changes with a gap analysis you can defend

The claim becomes a file rather than a conversation. Per supplier: the lines, the clause, the cumulative amount, the period. On the scope analysed, between 1 and 7% of margin recovered: recovered because documented and claimed by your teams, never automatically.

Renegotiation starts from reality. The price actually invoiced over twelve months, its drift, the discounts never applied: that is the basis of the next amendment, in place of the theoretical price. Price history, tied to every invoice, stops being individual memory.

Time changes in nature. 15 to 45% of time handed back to teams, per FTE, depending on the scope and the maturity of the data: the time spent compiling gaps in a spreadsheet is returned; the time spent deciding what to claim, and from whom, remains. The 3-week diagnostic, on your data, produces this analysis a first time, before any commitment.

The history of invoiced prices

Every price tied to its invoice and its contract, queryable over time.

Where this page sits

Find, resolve, analyse: three pages for the same gap

Checking invoiced prices finds the gap: one line, one clause, one amount. AI invoice reconciliation resolves it: cause, proposal, decision, closure. Gap analysis, this page, steps back: it groups hundreds of gaps to say where they come from and which ones matter. All three work on the same lines, tied to the same evidence; only the scale changes.

Checking invoiced prices

Upstream: every line compared with the negotiated price, the gap quantified.

Exception

Invoices without a purchase order, multi-order invoices, duplicates: handled.

Takes on what fits into no standard workflow, instead of sending it back to the team.

The queue of blocked cases stops growing.

What Exception detects

  • Invoices without a purchase order
  • Several purchase orders on one invoice, one purchase order across several invoices
  • Exact and disguised duplicates
  • Credit notes missing or never applied
  • Off-contract spend
  • Cost allocation entered as free text
  • IBAN invalid or diverging from the reference data

Nothing is lost. Everything can be checked, everything can be proven.

  • The contract clause and the invoice line, highlighted side by side.
  • Every extracted value stays linked to the exact place in the document where it was read.
  • The same case produces the same decision, today as in six months: the rules are applied deterministically.
  • No discrepancy is set aside in silence. Anything that matches no rule is raised, with its reason.
  • The agent records what it did, in the order it did it: who, what, how much, when.

Frequently asked questions

What is the difference between gap analysis and checking invoiced prices?

Price checking produces the gaps, line by line, by comparing the invoice with the contract. Gap analysis takes them all together to classify them by cause, aggregate them by supplier and category, and say which to handle first. One works at line level, the other at scope level.

Does the agent propose corrective actions?

It suggests an outcome per group of gaps (claim, internal correction, point to renegotiate), with the amount and the evidence. It carries out no action: no letter to the supplier, no credit note, no hold. The decision and the action remain with your teams.

How does the analysis handle a gap whose cause is ambiguous?

It says so. When two readings are possible, an early revision or a price never updated, the agent presents both, with the clause and the supplier’s history, and leaves the classification to a person. No gap is filed in a box by default.

Can gaps be analysed on a single spend category?

Yes, and that is often how the 3-week diagnostic begins: one category, one or two suppliers, one contract and a few months of invoices. The analysis is the same at small or large scale; the platform absorbs more than 12,000 price lines per framework contract.

Measurable impact in every environment

More than 5 million procurement documents analysed

Between 1 and 7% of margin recovered

on the scope analysed

From 15 to 45% of time given back to teams, per FTE

depending on the scope and on data maturity

Zylio fits into your existing ecosystem.

The ERP runs the process. Zylio handles the exception and recovers the value that escapes it: invoices without a purchase order, line-by-line price discrepancies, duplicates and overbilling, off-contract spend.

  • SAP
  • Sage
  • Oracle
  • NetSuite
  • Microsoft Dynamics 365
  • Pennylane
All integrations

Your data under high security.

Zylio meets the most demanding standards, and nothing is committed without your approval.

Certifications
SOC 2 Type II · ISO 27001
Hosting
Hosted in France
Encryption
End-to-end AES-256 encryption
Access
Enterprise SSO · multi-factor authentication · Zero Trust approach
Security and compliance

See what this looks like on your own data

Twenty minutes, on a spend category of your choosing. We show you what the agents detect, with the evidence behind it.

  • No commitment, on your own data
  • Result in 3 weeks
  • 20 minutes, no sales pitch
  • Your data stays hosted in France
  • No change of tool or process