Skip to content
AnrilX

Insights

What we measured, not what we assumed

Notes from building an AI platform over a live ERP: the architecture decisions, the failures that produced them, and the numbers behind both.

Latest · 4 min read

An AI that widens access is a different product

The useful question is not whether an AI over SAP is secure. It is whose authorisations it reads with, and what it does at the edge of them.

Read
· 4 min

The second source of truth you did not mean to build

The extract was supposed to take load off SAP. It became a system of record with a dashboard, and month end is where you find out.

reportingarchitectureoperations
· 4 min

What bulk creation should mean in SAP

Forty WhatsApp messages becoming forty sales orders is the easy half. The phrase makes an SAP controller assume nobody is in the path, and usually they are right.

governancesapoperations
· 4 min

Why an SAP AI has to be implemented

A generic assistant pointed at SAP knows how SAP ships. It does not know what your pricing procedure was extended to do in 2014, and no reasoning recovers that.

saparchitecturetrust
· 3 min

What an AI should say when it fails

Most of the risk in an AI system is not what it does when things work. It is what it reports when a read came back short or the system was unreachable.

governancearchitecturetrust
· 3 min

The dashboard that froze, and nobody noticed

Eight saved dashboards carried hardcoded date ranges. Nothing errored, no alert fired, and the titles still said last 30 days. Here is why that happens.

dashboardsarchitecturereporting
· 3 min

Every figure should carry its source

A number without provenance is an assertion. Printing the entity, field, filter and period under every figure is cheap to build and changes what a figure is for.

governancetrustreporting
· 3 min

The SAP report backlog is a symptom, not a workload

Every custom report request is a question somebody could not ask. Clearing the queue faster does not help, because the underlying demand has no bottom.

sapreportingoperations
· 4 min

Why we never let a model write the SAP query

A plausible query against the wrong entity returns a plausible number, and nothing downstream can tell it is wrong. Here is what we do instead, and what it costs.

architecturegovernancesap

Subscribe by RSS

Bring the question your reports cannot answer

Thirty minutes against a live SAP system we provide: no access to yours, nothing to set up. If it cannot answer, you find that out in half an hour rather than three months into a pilot.