Operational Impact

Operations leaders measure it in restored sleep.

Progull translates directly into faster recovery, fewer escalations and a knowledge base that finally compounds — measured against the workloads you already run.

92%

Of recurring abends auto-resolved without human touch

85%

Reduction in mean time to recovery on overnight batch

70%

Fewer Sev-2 escalations to senior mainframe SMEs

100%

Audit-grade trace of every agent decision in ServiceNow

Before vs after

Same batch window. Different team.

Before Progull

Human-driven, reactive

Detection
Operator notices, pages SME
Triage
Manual SDSF / JES spool hunt
Diagnosis
Tribal knowledge, war-room
Remediation
Hand-typed JCL resubmit
Closure
Hours later, sparse worknote
MTTR
Hours, sometimes a full shift
With Progull

Agent-driven, governed

Detection
Sub-second from JES event
Triage
Telemetry auto-attached
Diagnosis
Explainable agent narrative
Remediation
Policy-approved playbook
Closure
Auto-closed with full trace
MTTR
Minutes — typically <3
Where the value lands

Downstream of the agent, the whole org benefits.

Operations

Fewer overnight pages. SLA breaches drop. Run-books become living code.

Engineering

Senior SMEs stop being the human dispatch system. Their expertise compounds into playbooks.

Business

Payroll runs on time. GL closes. Cut-offs are met. The mainframe stops being the bottleneck.

Impact by abend family

Where the lift actually shows up.

Auto-resolution rates on the families that dominate overnight batch — measured across customers in production.

Family
Auto-resolved
MTTR
Notes
S0C7 · Data exception
96%
2m 14s
Packed-decimal overflow; clean-resubmit playbook
S322 · Time exceeded
78%
4m 02s
Step-split + capacity escalation on outliers
SB37/SD37/SE37 · Space
94%
3m 12s
Reallocate + extents PRIMARY=+200
SQLCODE-911 · Deadlock
99%
0m 48s
Exponential backoff retry, max 3
S913 · RACF access
41%
Escalates to access request — by design
AICA · CICS runaway
88%
1m 56s
Purge TRAN; cycle region on repeat
Customer cohort

What a typical 90-day rollout looks like.

The arc most customers actually run — from shadow mode on a single LPAR to autonomous coverage across the overnight window.

  1. Days 0–14

    Shadow on top abends

    Agents observe the top 10 recurring abends on one LPAR. Operators read traces; zero action on z/OS.

  2. Days 15–45

    Recommend across batch

    Agents draft worknotes and remediation in ServiceNow. Operators execute. MTTR drops 40–60%.

  3. Days 46–90

    Autonomous, scoped

    Approved playbooks execute under surrogate IDs. SMEs review the trail weekly; long tail becomes the focus.

Case in numbers

One Tier-1 bank. One quarter.

A representative slice from a Fortune-100 banking customer running Progull in autonomous mode across overnight payroll and GL batch.

11,402

Abends handled in Q3

94.6%

Auto-resolved without paging an SME

2m 41s

Median MTTR across all abend families

$3.1M

Avoided cost of escalation and SLA breach

What stops being a meeting

The org chart gets quieter.

Progull retires entire categories of standing calls — the war-rooms, the post-mortems on repeat causes, the 7am hand-offs.

  • The nightly batch stand-up reading run-book status to a roomful of people.
  • The Friday RCA on the same recurring S0C7 that everyone already knows.
  • The Sev-2 escalation that wakes up the senior SME for a 90-second fix.
  • The hand-off email at 7am explaining what the on-call did and why.
  • The quarterly capacity review that surfaces issues already fixed.
  • The audit prep sprint that re-derives evidence the agent already attached.