70% faster dispatch & billing workflows with AI
A critical SAP dispatch and billing workload was accelerated by 70% through autonomous, HANA-aligned optimization without changing business logic, touching production manually, or introducing risk.
Key batch jobs routinely ran for over 72 minutes, delaying downstream operations.
A large steel manufacturer was struggling with extremely long-running SAP jobs tied to dispatch, billing, and logistics reconciliation.
These programs processed high-volume transactional data, including billing documents, gate entries, pricing conditions, delivery details, and audit trails, all tightly coupled to business-critical workflows.
The root cause was deeply embedded legacy ABAP logic:
- Heavy nested loops over large internal tables
- Repeated database reads inside loops
- Inefficient handling of change document (CDPOS/CDHDR) data
- Full table scans where indexed or sequential access was possible
Manual optimization was risky. Any functional change could impact billing accuracy, audit trails, or statutory compliance - making traditional refactoring slow, expensive, and high-risk.
Automated ABAP Optimization with Zero Functional Risk
Sookti AI deployed autonomous agents to analyze and optimize the steel manufacturer’s most performance-critical SAP programs - without altering business logic, to enable deterministic, predictable performance.
The agents:
All changes were self-documented, regression-tested automatically, and validated to ensure identical results to the legacy programs.
Data-driven improvements measured on live production workloads.
Sookti AI eliminated severe SAP performance bottlenecks in dispatch and billing workflows, delivering a 70% runtime reduction while preserving 100% business accuracy without manual effort, production risk, or disruption to live operations.
O(1) Access with Hashed Tables
LOOP AT it_bill INTO wa_bill.
" Extremely slow nested DB hits
SELECT SINGLE * FROM cdpos INTO @DATA(wa_cdpos)
WHERE objectid = @wa_final-aubel
AND fname = 'LIFSK' AND value_new = '61'.
SELECT SINGLE udate FROM cdhdr INTO @DATA(wa_cdhdr)
WHERE changenr = @wa_cdpos-changenr.
ENDLOOP." Optimization: Use Hashed Tables for O(1) instant lookups
DATA: lt_cdhdr TYPE HASHED TABLE OF ty_cdhdr
WITH UNIQUE KEY changenr.
" Preload Change Headers in bulk
IF lt_changenr IS NOT INITIAL.
SELECT changenr, udate, utime FROM cdhdr
INTO TABLE @lt_cdhdr
FOR ALL ENTRIES IN @lt_changenr
WHERE changenr = @lt_changenr-table_line.
ENDIF.
LOOP AT it_bill INTO wa_bill.
" O(1) lookup: No searching required, direct hash hit
READ TABLE lt_cdhdr INTO wa_cdhdr
WITH KEY changenr = wa_cdpos-changenr.
IF sy-subrc = 0.
wa_final-udate = wa_cdhdr-udate.
ENDIF.
ENDLOOP.Agents identify when key access is unique and refactor logic to use hashed tables, providing instant data retrieval regardless of table size.
“The optimized programs delivered exactly the same results-but in a fraction of the time. What would have been a high-risk manual exercise was completed safely without disrupting production workflows.”
Aspect Details
Ready to See Similar Results?
Start with a pilot on your most challenging programs. See what autonomous AI can do in weeks.
