Up to 99% faster SAP reporting through AI-led ABAP optimization
Autonomous AI agents optimized multiple business-critical ABAP programs for a leading consumer products manufacturer, resolving timeouts, cutting runtimes up to 99%, and delivering results with zero manual ABAP intervention.
Under production-scale workloads, critical SAP programs were timing out or crashing, creating operational risk and threatening system stability.
Our client, one of India's largest footwear manufacturers, was running SAP ECC with a large inventory of custom ABAP programs spanning production planning, procurement, logistics, finance, and warehouse management. With an S/4HANA migration on the horizon, performance issues that had accumulated over years could no longer be deferred.
The immediate problem was operational. Across several programs covering MIS reporting, transport flow tracking, purchase registers, customer aging, article master creation, and more, programs were either timing out with maximum runtime errors, crashing with short dumps due to memory exhaustion, or running for minutes before producing results. Month-end reporting cycles were strained and business teams were forced to work around system instability.
Manual remediation was estimated at months of iterative code review and testing, an effort that was neither available nor acceptable given the migration timeline and the scarcity of ABAP expertise.
“Traditional remediation estimates came back at months of developer effort with no guarantee of consistent quality across all programs.”
Autonomous AI-driven ABAP Optimization Across Production Programs
Sookti AI deployed autonomous agents across all programs simultaneously. Each agent analysed the full codebase, identified performance bottlenecks, and applied targeted technical fixes without touching business logic or functional output.
The agents:
Data-driven improvements measured on live enterprise workloads. Results below represent a subset of optimized programs from a broader SAP performance initiative.
Programs previously timing out on full production datasets now complete within seconds to minutes. Results were validated with 100% functional parity before delivery. The transformation restored system stability in production while preserving clean-core principles.
From SELECT-in-Loop to Bulk Retrieval with Binary Search
Agents identify repeated database access patterns inside loops and refactor them to bulk retrieval with binary search, delivering O(log n) lookup performance regardless of dataset size.
LOOP AT t_final ASSIGNING <l_fs_final>.
" Performance Anti-pattern: DB hit in loop
SELECT SINGLE audat FROM vbak
INTO(audat)
WHERE vbeln = <l_fs_final>-sono.
ENDLOOP.IF t_final IS NOT INITIAL.
" Bulk Retrieval using FOR ALL ENTRIES
SELECT vbeln, audat FROM vbak
INTO TABLE @DATA(lt_vbak)
FOR ALL ENTRIES IN @t_final
WHERE vbeln = @t_final - sono.
SORT lt_vbak BY vbeln.
ENDIF.
LOOP AT t_final ASSIGNING <l_fs_final>.
" O(log n) read instead of DB call
READ TABLE lt_vbak INTO DATA(ls_vbak)
WITH KEY vbeln = <l_fs_final>-sono
BINARY SEARCH.
ENDLOOP.“Sookti AI resolved timeouts we had been living with for years, across 10 programs, in a single batch, without touching a line of code manually.”
Engagement Details
Ready to Unlock Similar Performance Gains?
Run a controlled pilot on your most critical SAP workloads and validate measurable results before scaling enterprise-wide.
Book a call with us or write to: aditya@sookti.ai | tanushree@sookti.ai
