In the chat you pick a role for each request. A role is both a full methodology and an access boundary: read-only roles physically receive only SAP read tools and cannot change anything. Every Support and Consulting role is read-only; only Development roles write, and only on a development-tier system. An admin can override any role or add their own.
Implements a requirement end to end: understand → explore the current state → reuse what exists → plan → lock + set source → syntax check + tests/ATC → activate → report.
A finished, activated change in your approach, rather than a draft of code.
Delivers a solution design, writes no code.
A considered plan before anyone touches the system.
Reviews against your standards; findings ordered by priority (Critical / Major / Minor) with exact locations and fixes.
A second, independent pass, with no risk the reviewer “accidentally” rewrites something.
Writes/extends ABAP Unit tests; never changes production logic to “force” a test green.
Test coverage without distorting the business logic.
Runs the ABAP Test Cockpit, returns findings ordered by priority; fixes only if you explicitly ask.
ATC-standard quality under your control.
Runs ATC and fixes findings methodically, category by category, behaviour-preserving.
Findings closed without changing what the code does.
Investigates and answers with evidence, can run SQL queries against the data.
Fast, well-founded answers about the system, with no risk to it.
Turns a client's raw specification into Makion's internal standardized format, cross-checking against the live system.
A chaotic requirement becomes an ordered, testable spec.
Sizes a development from its spec: every object rated S / M / L with an hour range, plus the assumptions and unknowns behind the number. Delivers an estimate document.
A defensible effort figure before you commit, rather than a gut feel.
Designs and builds CDS data models in SAP’s VDM style: interface and consumption view entities, associations, annotations and access control (DCL), created and activated on your system.
A clean, layered data model your reports and apps build on, rather than a one-off SELECT.
Builds RESTful ABAP (RAP) business objects end to end: CDS model, behavior definition and behavior class, projection and OData service binding, activated and ready to consume.
A real transactional service on your system, not a diagram of one.
Makes a service Fiori-Elements-ready: the @UI annotations and metadata extensions that drive a List Report / Object Page, plus the OData service binding. Then honestly hands off the UI app-shell deploy to your tooling.
Your data one step from a Fiori app, the whole annotation layer done for you.
Takes one custom object, finds what breaks on S/4HANA (deprecated APIs, direct table access, old syntax) and proposes a minimal fix for each; you approve, it applies and activates, and for risky changes it writes a pin-down test first.
Custom ABAP made S/4HANA / Clean-Core ready, one object at a time, on your own ECC.
The analysis half of migration: reads your custom code and its usage to map the S/4HANA effort. What is used, what breaks, what to fix first. It never connects to production.
A prioritised migration picture before anyone changes a line.
Reads an existing SAP Adobe Form and applies a structural change (add / remove / reorder / rebind a column), returning a paste-ready XDP for the SFP “XML Source” tab, with geometry and data bindings guaranteed by a deterministic engine.
Edit Adobe Forms by describing the change instead of by hand in LiveCycle.
Audits clean-core compliance: released APIs, no standard-table reads, extensibility. Read-only.
A clean-core verdict per object before the migration plan is written.
Triages an incident across ST22 dumps, SM37 jobs, SLG1 logs, SM13 updates, IDocs and tRFC, and returns ranked root causes with a single typed next action.
From “it's broken” to a ranked cause and next step, read-only.
A morning sweep of the system: stuck IDocs, failed jobs, tRFC/qRFC backlog and fresh dumps. The health picture before users report it.
Problems found before the first ticket lands.
A deep-dive on IDoc failures: status records, control data and segments (EDIDC / EDIDS / EDID4), to explain why one failed and what to do. Reprocessing stays a handoff.
The real reason an IDoc failed, not just a status number.
Current-state analysis in a fixed shape: finding → evidence → impact → recommendation → effort / risk. Reads the system and code, changes nothing.
An honest picture of where things stand, backed by evidence.
Derives the authorizations a program actually needs from its code, compares them to what is granted, and flags gaps and over-grants.
Least-privilege reasoning grounded in the real code.
Inventories the integration landscape (RFC, ALE, IDoc, OData) from configuration and code (static, not runtime), so nothing is missed on a migration or audit.
A complete interface map, read from the system itself.
Assembles an engagement deliverable (findings, roadmap and a GO / NO-GO verdict) from the work done across the other consulting roles.
A client-ready report, not a pile of notes.
Read-only roles can't write at the tool level, not just at the prompt level. An admin can override any role's methodology or add new ones. Every role belongs to a product, and every role outside Development is read-only at the tool level. The same governed AI, the same official ADT channel, the same read-only guarantees, packaged as three products — all three included in one licence.
Your SAP, your standards, your terms.
Several developers or a client rollout? Teams & enterprise