One chat across every SAP system you run — ECC, S/4HANA, BTP and beyond. Grounded in your landscape, not rented from public tools.
Your SAP landscape doesn’t stop at the cloud. Neither should your AI. Ireya connects with SAP ECC and modern SAP systems, bringing intelligence to the entire enterprise landscape.
Your people already use AI every day — through tools that know nothing about your business.
Everyone buys the same models. Nobody can buy a live connection to your systems, data and processes. That connection is the moat.
Available to any company. The AI itself is not a differentiator.
A live link to your own landscape, ECC or S/4HANA. No public tool can offer it.
Reading real ABAP code and SAP objects in a live landscape today.
Eight questions in one thread — understand, predict, decide, and finish holding a document you can send. Capabilities are real; names and figures are examples, not one customer's system.
What are we working on?
ZFGLEU001 is a month-end GL reconciliation report. It reads the FI documents posted for a company code and fiscal period, compares them against the general ledger balances, and lists every difference it finds.
| It reads | It writes |
|---|---|
BKPF, BSEG — document header and line items | A spool list, one line per difference |
SKAT — GL account descriptions | ZFI_RECON_LOG — a run history |
One selection screen, no user interaction, and it runs nightly in the background. In short: it is the report someone checks on the first working day of the month before they will sign anything off.
14 purchase orders created today, across three company codes, totalling MYR 486,200.
| PO | Vendor | Co. code | Net value | Created by |
|---|---|---|---|---|
4500018842 | Sime Industrial Supply | 1000 | MYR 128,400 | SITI.R |
4500018843 | Northgate Engineering | 1000 | MYR 96,750 | SITI.R |
4500018844 | Delta Valve & Fitting | 2000 | MYR 61,300 | A.KUMAR |
4500018845 | Perdana Logistics | 3000 | MYR 44,900 | A.KUMAR |
Showing four of fourteen. Three were raised against a vendor with no active contract — worth a look before they go for approval.
Scored 312 open items against the payment behaviour of everything cleared in the last 18 months. Forty-one carry a high risk of running past their due date.
| Document | Vendor | Due | Risk | Why |
|---|---|---|---|---|
1900004471 | Northgate Engineering | in 6 days | High | Last six invoices cleared 12 days late on average |
1900004488 | Delta Valve & Fitting | in 9 days | High | Blocked for price variance, unresolved 11 days |
1900004502 | Perdana Logistics | in 14 days | Medium | Goods receipt posted, invoice not yet matched |
1900004510 | Sime Industrial Supply | in 21 days | Low | Consistently cleared early |
This is a pattern drawn from your own cleared history, not a rule — treat it as the queue to work first, not a verdict on any one invoice.
Three systems checked. Two dumps in Production, none in QAS, seven in Dev.
| System | Dumps | Most frequent |
|---|---|---|
| Production | 2 | CX_SY_ZERODIVIDE in a nightly job |
| QAS | 0 | — |
| Dev | 7 | CX_SY_OPEN_SQL_DB — all from one developer's test run |
The two in Production are the ones that matter: both came from the same scheduled job, and it failed silently — the job finished green because the dump was caught and swallowed.
Nine custom programs sit in Dev with no counterpart in Production. Four were changed in the last 90 days, so they are still live work; the rest have not moved in over a year.
| Program | Dev | QAS | Prod | Last changed |
|---|---|---|---|---|
ZFI_REBATE_CALC | ✓ | ✓ | — | 11 days ago |
ZMM_PO_UPLOAD_V2 | ✓ | ✓ | — | 2 months ago |
ZRPT_LEGACY_001 | ✓ | — | — | 3 years ago |
ZSD_QUOTE_FIX | ✓ | — | — | 2 years ago |
Showing four of nine. The three-year-old entries are the interesting ones — code that was built, never shipped, and is still being carried.
Nothing references it, nothing runs it, and it never reached Production — so the recommendation is to retire it. The two checks on the right are the ones a where-used list genuinely cannot answer, and they are worth five minutes before anyone deletes anything.
ATC finished across 34 objects. Findings by priority:
| Priority | Findings | What they are |
|---|---|---|
| P1 — critical | 7 | Statements not permitted in ABAP Cloud |
| P2 — high | 23 | Direct access to tables that are no longer released |
| P3 — medium | 61 | Naming, performance and obsolete syntax |
Only the seven P1 findings actually block the move. The 61 P3s can wait — telling those apart is usually the difference between a three-week remediation and a three-month one.
Written up per object — what is wrong, the released replacement, and an effort estimate — with the seven P1 findings first.
Say the word and the same content comes out as a deck for the steering committee.
That is one thread. It answers a great many more.
What people actually ask it.
Your people, ireya running inside SAP BTP, and the systems you already own. Everything inside the dashed line is your landscape — the question, the data and the answer stay in it.
Opened in a browser with the company sign-on. Questions in plain language — nothing new to learn.
Holds the conversation, works out which systems to read, and records what was accessed.
Where the model runs — the commodity part, called from inside your own subaccount.
The controlled door in. Only the systems and clients you choose to open, under your own access rules.
Live ABAP code, SAP objects and business data — Dev, QAS and Production, from the one chat.
No public AI endpoint appears anywhere on this diagram — which is the whole point of building it inside.
One central ireya AI chat, more AI apps around it, and one shared SAP connection underneath.
The same pattern lets any team ask questions against their own systems, SAP or not.
live ABAP & SAP objects, ECC or S/4HANA
SAP + reporting tools
plant & ops systems
their own products
ireya does not add another tool to learn — it removes the slow ends of SAP work: hunting for answers at the start, writing them up at the finish. What is left is the judgement your people are paid for.
Connect your system and the landscape answers for itself from day one. Your people ask in plain language instead of searching through transactions, screens and old documents.
Extraction and spreadsheets are work nobody wants to spend days on. Removing it gives your SAP team their time back for analysis and decisions that matter.
Specifications, object inventories and remediation plans come out in Word and Excel as the work happens, not in the fortnight after it.
The same platform serves developers today and can be pointed at finance, operations and any other team’s systems tomorrow. One place to ask, instead of an assistant per system.
Built by SAP developers with twenty years in the landscape — every capability started as something that cost them a week of their own. Built against a live S/4HANA system, not a sandbox, because the awkward parts only show up when it is real.
Commercial terms are open by design: the right fit for your landscape is a conversation, not a price list.
It is a made word. It does not describe SAP, it does not describe chat, and it does not describe whatever the platform happens to do this quarter — which is the point. A name that describes today's product has to be explained away the first time the product grows past it.
Five letters, one obvious pronunciation, and nothing else in the enterprise software market already answering to it.
Nothing in the word ties it to developers, to SAP, or to a single system — so nothing has to be renamed when it reaches the next team.
It is more than a chatbot — an intelligent companion that helps people:
ireya stands for clarity, intelligence and trusted guidance in every conversation.
The only AI chat wired into your live SAP landscape, ECC or S/4HANA.
Book a live demo →Opens your email app. Thirty minutes on a live landscape answers more than any document can.