Insight
Connect your procurement data to Power BI, without copying it out
Connecting your procurement data to Power BI does not mean copying it out. Insight feeds your BI (business intelligence) tool datasets that are already resolved: reconciled entities, converted units, dated prices, every line tied back to its source document. You keep the reporting tool you have.
The problem
The report is not the problem. What it is fed is
A BI tool does exactly what it is asked: it aggregates what it receives. Feed it an extract where the same supplier appears under five legal names, where litres and pallets are added together, and where prices carry no validity period, and it will produce a wrong chart: cleanly, on time, in the right brand colours.
So the question is not where to steer, but what reaches the tool. We do not centralise your data to make you look at it in our screens: we also feed your Power BI or your Tableau, with the same material Insight queries live.
No forecast is promised here. Certainty about the past comes first: a wrong figure is not corrected by a projection, and a report built on unresolved entities does not become right because a trend line was added to it.
What a clean dataset contains
This is not a connector question. A connector carries; what matters is what travels through it.
- Resolved entities
- One supplier, once. Multiple legal names are grouped under their supplier group, duplicates merged, item references aligned from one supplier to the next. Your report’s “supplier” filter stops showing five rows for a single point of contact.
- Converted units
- Litre, kilo, pallet, linear metre: brought back to a comparable unit, with the conversion factor used. A sum of quantities becomes a sum that means something again.
- Dated prices
- Every price carries its validity period and the contract that grounds it. A price is not an attribute of an item: it is a fact valid between two dates, for a given entity and a given supplier.
- Every line tied to its document
- The source document reference, its page and its line travel with the data. A suspicious figure in a report can be walked back to the invoice that produced it, without reopening a case or emailing anyone.
- Explicit currencies and rates
- The original amount, the currency, the rate applied and its date stay visible next to the converted amount. A multi-entity consolidation stops being a black box nobody can reproduce.
- Timestamped facts, continuous updates
- Facts are not overwritten, they are timestamped. Last month’s report stays replayable as it was, and the historical series is not rewritten at every refresh.
These datasets are produced by the procurement graph: it did the entity resolution, the unit conversion and the tie back to the document. Insight does not clean up at export time; it exposes what has already been reconciled.
The dataset is published on a chosen rhythm (daily, weekly, at close) and your tool connects to it as it would to any other source. Nothing is copied by hand, nothing is dropped on a file share, nothing travels through a mailbox. The published scope is defined with you: categories, entities, depth of history.
The schema is stable and documented: columns do not change name from one delivery to the next, and every change is versioned. That is the condition for a report built once to keep working, and for the person who built it not to be the only one who knows what each field holds.
What this changes
The delay between the question and the answer. A buyer preparing a renegotiation no longer waits for a slot with the data team.
Keep your tool. Power BI and Tableau are reporting tools: if your committees run on them, that is where the data must land. Insight produces what they consume and does not try to replace them with one more screen.
- Existing reports stay in place: they change source, not shape. The work already done on your visuals does not have to be redone.
- Between two report versions, the question goes straight to Insight. Many questions are not worth a development: you ask, you get the answer, you move on.
- A figure challenged in a committee opens onto the lines that make it up, then onto the document. The discussion is about the decision, no longer about whether the extract can be trusted.
- The same figure has the same value in the native dashboard and in your report: both read the same source, on the same schema, under the same calculation rules.
Read only
Insight reads, it does not write. No writing into the ERP (enterprise resource planning system), no commitment made, no data sent outside: the datasets stay in your environment, hosted in France, and are never used to train a model.
What Zylio does not do
Procurement intelligence · Insight
Ask the question. It builds the analysis, and shows where every figure comes from.
Translates a question asked in plain language into a query over the graph and the procurement database, computes, and returns the useful form: a figure, a table, a curve, a dashboard. It reads, it does not write. Every value opens onto the lines that make it up, and every line onto its source document.
The delay between the question and the answer. A buyer preparing a renegotiation no longer waits for a slot with the data team.
What Insight detects
- A category whose price has been drifting for months
- A contract coverage rate falling, by category and by entity
- Credit notes outstanding, with whom and for how long
- A single-source reference with no alternative on record
- A gap between the budget for a cost line and what was actually invoiced
- An increase driven by mix or volume rather than price
- A missing figure: declared as missing, never estimated
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
Do we have to replace our Power BI?
No, keep it. Insight produces the clean datasets it consumes, and in the meantime answers the questions that are not worth a report development. We feed your Power BI or your Tableau rather than asking you to steer from somewhere else.
What does a clean procurement dataset contain?
Resolved entities (one supplier, once), units of measure converted with their factor, dated prices tied to the contract that grounds them, explicit currencies and rates, and for every line the document key, page and line it came from. Facts are timestamped, not overwritten.
Does Zylio replace my ERP?
No. Your ERP runs the process and remains the source of truth. Zylio handles the exception, on top of it, and feeds the results back. No additional development inside your system.
Is my data used to train models?
No, never. It is not shared between clients and stays hosted in France.
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.
Your data under high security.
Zylio meets the most demanding standards, and nothing is committed without your approval.
- Certifications
- Hosting
- Encryption
- Access
Read next
- Procurement intelligenceInsight: on-demand procurement analysis, verifiable figure by figure.
- The questions to ask about your procurementThe twelve real questions, and what has to be connected to answer them.
- The contract coverage rateHow much of your spend is genuinely governed by a contract.
- Price-volume-mix analysisIsolating the price, volume and mix effects behind an increase.
- Procurement analysis in-house or by a consulting firmWhat changes when the answer arrives the same day.
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