Task-Boundary Mode
How task-instance boundaries are drawn from the event stream. Applies to every Task SoP, Step SoP, and Variants view.
Narrative
📝 Task SoP
Mined from 62 instances
Review Narrative
How 10 analysts execute this task across 56 cases — auto-generated Standard Operating Procedure with adherence scoring.
83.4
Avg Adherence Score (0-100)
Median 82.5 · Range 62.5–97.5
163.7 min
Avg Task Duration
1.1 min median
3.4
Avg Sub-Steps per Instance
82.5% have multiple sub-steps
1.6%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
1.6% of instances follow this exactly
Review Narrative — Mined SoP
The most common sub-step sequence observed across 63 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Narrative
1.5s
0.3 edits
Veeva Safety
100%
2
View Submissions
0.0s
Veeva Safety
13%
Variant Explorer
Reference
Review Narrative Reference Path
1 instances · 1 analysts
This is the mined reference path — 1 instances across 1 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Review Narrative.
Genuine Complexity
Complex-Case Execution Path
11 instances · 5 analysts
· Δ adherence +4.5
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
×
View Submissions
skipped — this reference step was not executed
Genuine Complexity — this sequence differs from the reference path (1 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 88.0 vs reference 83.4 (delta +4.5). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
7 instances · 4 analysts
· Δ adherence +6.6
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Preview English Narrative
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 90.0 vs reference 83.4 (delta +6.6). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
4 instances · 3 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
2 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View System Section
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 2 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -1.7
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View Entry Phase
extra step (reference ends at step 2)
4
Select Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
Submit Cancel Workflow
extra step (reference ends at step 2)
7
Cancel Workflow
extra step (reference ends at step 2)
8
Select Start Case Entry
extra step (reference ends at step 2)
9
Select Generate Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (9 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 81.7 vs reference 83.4 (delta -1.7). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Generate Narrative
reference at this step: View Submissions
3
View Validation Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +1.4
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Select Cancel Workflow
extra step (reference ends at step 2)
4
Submit Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
View Submissions
extra step (reference ends at step 2)
7
Select Start Case Entry
extra step (reference ends at step 2)
8
View Reference Numbers
extra step (reference ends at step 2)
9
View Contacts
extra step (reference ends at step 2)
10
View Patient
extra step (reference ends at step 2)
11
View Medical History
extra step (reference ends at step 2)
12
View Case Details
extra step (reference ends at step 2)
13
Select Unknown Value
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (13 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 84.8 vs reference 83.4 (delta +1.4). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Preview Japanese Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Products
reference at this step: View Submissions
3
Select Patient
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Show More Details
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Product: Pembrolizumab
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Open Case Assessment Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Veeva Safety | 194 | 91.1% | 100.0% |
| Microsoft Word | 7 | 3.3% | 0.0% |
| Acrobat | 4 | 1.9% | 0.0% |
| collaboration.merck.com | 4 | 1.9% | 0.0% |
| Microsoft Outlook | 3 | 1.4% | 0.0% |
| Microsoft Excel | 1 | 0.5% | 0.0% |
Top Cross-App Transitions (within task instance)
Consecutive events that cross application boundaries within a task instance — the signal where swivel-chair patterns live.
| From | To | Transitions |
|---|---|---|
| Veeva Safety | Microsoft Word | 6 |
| Microsoft Word | Veeva Safety | 3 |
| Veeva Safety | Acrobat | 3 |
| Veeva Safety | Microsoft Outlook | 2 |
| Microsoft Outlook | Veeva Safety | 2 |
| Veeva Safety | collaboration.merck.com | 2 |
| Microsoft Word | Microsoft Outlook | 1 |
| collaboration.merck.com | Acrobat | 1 |
| Acrobat | Veeva Safety | 1 |
| Microsoft Excel | Veeva Safety | 1 |
On-Case Application Journey (±15 min around anchor)
Apps the same analyst touched on the same case within ±15 minutes of the task anchor. Captures work that spans task boundaries — the Veeva/Acrobat/Outlook/Word context surrounding the anchor click.
Case counts per app are not mutually exclusive — a case that touched Veeva AND Phobos in this window is counted in both rows. Overlap reflects real cross-app work, not double-counted cases.
Veeva Safety DOM 1,290 events 56 cases 17.8 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
99×
pyzeClick
<div>
"Narrative"
65×
pyzeClick
<div>
"Case Assessment Results"
44×
pyzeClick
<a>
"Show more"
44×
pyzeClick
<span>
"Adverse Events"
35×
pyzeClick
<button>
"Save"
33×
pyzeClick
<div>
"Case Assessments"
33×
pyzeClick
<span>
"Products"
32×
Phobos DOM 130 events 26 cases 3.2 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<button>
"Proceed"
21×
pyzeClick
<button>
"Send to process"
19×
pyzeClick
<button>
"Advance"
14×
pyzeClick
<td>
"2345469 (v5.1) Japanese (Japan)"
12×
pyzeClick
<td>
"2352671 (v0.1) Japanese (Japan)"
10×
pyzeClick
<button>
"Save Comments"
10×
pyzeClick
<button>
"Login"
9×
pyzeClick
<td>
"2347576 (v2.1) Japanese (Japan)"
6×
Acrobat App 29 events 9 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
349 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Word Document 29 events 12 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
V-Narrative 549550 (English) (26643764_0_1_347593)
354×
file
V-Narrative 523977 (English) (26234010_0_2_341403)
116×
file
V-Narrative 549428 (English) (26642399_0_2_349187)
88×
file
V-Narrative 531855 (English) (26362027_0_1_346062)
84×
file
Narrative 481786 (English)
84×
file
V-Narrative 524568 (English) (26241711_0_2_343144)
34×
file
V-Narrative 540056 (English) (26485638_0_3_344672)
31×
file
V-Narrative 533936 (English) (26397592_0_1_338360)
25×
Microsoft Teams App 23 events 12 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
293 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Excel Document 15 events 7 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
Case tracking list
42×
file
ICHICSR-EVHUMAN_10020278639 (1)
33×
file
All PV Smart Submissions 28-NOV-2025 PM
12×
file
2355984 (v0.1)
12×
file
2354547 (v0.1)
9×
file
Query 21-NOV-2025
9×
collaboration.merck.com App 11 events 10 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Microsoft Outlook Message 9 events 7 cases
Message-level capture
Task Mining captures email subjects. Case numbers frequently appear in the subject line.
evocpr01.apps.americas.cf.merck.com App 5 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
TextInputHost App 3 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.07
Swivel Rate
events in non-primary app / total
0.80
Zero-Edit Visit Rate
inspection-only clicks
1.03
Avg Revisit Depth
max repeats of any activity
0.00
Cross-App Time Share
time outside primary app
Meta Score Distribution
Instance count in each 10-point adherence bucket. Right-skewed = healthy execution; long left tail = concentrated pain points.
0
10
20
30
40
50
60
70
80
90
Top Concern Vector
Zero-Edit Visit Rate — current value 0.80
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Vector Contribution to Adherence Loss
Each vector's weighted contribution to lost adherence. The top row is your highest-leverage fix.
Zero-Edit Visit Rate
value 0.80
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.03
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.07
Reduce cross-app hops by surfacing the secondary-app data inline (API integration or pre-fetched context panel).
Cross-App Time Share
value 0.00
Time outside primary app dominates this score. Identify which secondary app(s) and whether their function can be in-lined.
Lowest-Adherence Instances
The 5 task instances that scored lowest. These are the concrete cases worth investigating to understand the worst patterns.
| Case | Analyst | Score | Duration | Sub-Steps | Swivel | X-App | Revisit |
|---|---|---|---|---|---|---|---|
| 2354472 | Analyst 12 | 62.5 | 6.9m | 3 | 0.67 | 0.00 | 1 |
| 2355984 | Analyst 09 | 64.5 | 2.1m | 5 | 0.60 | 0.00 | 1 |
| 2342905 | Analyst 09 | 67.5 | 1.2m | 4 | 0.50 | 0.00 | 1 |
| 2354895 | Analyst 05 | 67.5 | 0.1m | 2 | 0.50 | 0.00 | 1 |
| 2351742 | Analyst 12 | 67.5 | 5.0m | 2 | 0.50 | 0.00 | 1 |
Users on This Task
10 analysts executed this task during the pilot. Scatter plots productivity (instances per active day) against adherence (meta score). Top-right = healthy high-volume analysts; bottom-right = firefighters; top-left = careful low-volume; bottom-left = struggling.
Adherence (meta score) →
Productivity (instances / active day) →
07
15
14
02
12
09
10
03
01
05
User-by-User Breakdown
Click any analyst to see their dominant sequence vs the reference SoP.
| Analyst | Instances | Inst / Day | Adherence | Weakest Vector | Swivel | X-App | Min | |
|---|---|---|---|---|---|---|---|---|
| ▸ | Analyst 07 | 1 | 1.0 | 97.5 | Revisit Depth | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 07's Dominant Sequence
— 1 of 1 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 15 | 2 | 2.0 | 88.8 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 15's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
View Narrative Preview Header
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 14 | 8 | 4.0 | 86.8 | Zero-Edit Visits | 0.00 | 0.00 | 13 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 14's Dominant Sequence
— 3 of 8 instances
1
View Narrative
2
Preview English Narrative
· reference: View Submissions
This analyst exhibits 6 distinct sequences across their 8 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 02 | 2 | 1.0 | 84.4 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 02's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Open Details Section
· reference: View Submissions
3
Create New Item
4
Save
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 12 | 11 | 1.8 | 83.9 | Zero-Edit Visits | 0.14 | 0.00 | 10,211 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 12's Dominant Sequence
— 4 of 11 instances
1
View Narrative
This analyst exhibits 8 distinct sequences across their 11 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 09 | 27 | 2.1 | 82.6 | Zero-Edit Visits | 0.07 | 0.00 | 50 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 09's Dominant Sequence
— 2 of 27 instances
1
View Narrative
This analyst exhibits 24 distinct sequences across their 27 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 10 | 6 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 25 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 10's Dominant Sequence
— 2 of 6 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
This analyst exhibits 5 distinct sequences across their 6 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 03 | 3 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 03's Dominant Sequence
— 3 of 3 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 01 | 1 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 01's Dominant Sequence
— 1 of 1 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
|
||||||||
| ▸ | Analyst 05 | 2 | 1.0 | 71.0 | Zero-Edit Visits | 0.36 | 0.00 | 9 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 05's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
Microsoft Word
4
View Reference Numbers
5
Microsoft Outlook
6
View Contacts
7
View Create Options
8
Create New Item
9
Continue
10
View Study
11
Microsoft Word
12
View Patient
13
View Medical History
14
View Adverse Events
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
83.4
Avg Adherence Score (0-100)
Median 82.5 · Range 62.5–97.5
164.4 min
Avg Task Duration
1.1 min median
3.6
Avg Sub-Steps per Instance
82.5% have multiple sub-steps
1.6%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
1.6% of instances follow this exactly
Review Narrative — Mined SoP
The most common sub-step sequence observed across 63 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Narrative
1.5s
0.3 edits
Veeva Safety
100%
2
View Submissions
0.0s
Veeva Safety
13%
Variant Explorer
Reference
Review Narrative Reference Path
1 instances · 1 analysts
This is the mined reference path — 1 instances across 1 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Review Narrative.
Genuine Complexity
Complex-Case Execution Path
11 instances · 5 analysts
· Δ adherence +4.5
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
×
View Submissions
skipped — this reference step was not executed
Genuine Complexity — this sequence differs from the reference path (1 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 88.0 vs reference 83.4 (delta +4.5). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
7 instances · 4 analysts
· Δ adherence +6.6
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Preview English Narrative
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 90.0 vs reference 83.4 (delta +6.6). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
4 instances · 3 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
2 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View System Section
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 2 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -1.7
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View Entry Phase
extra step (reference ends at step 2)
4
Select Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
Submit Cancel Workflow
extra step (reference ends at step 2)
7
Cancel Workflow
extra step (reference ends at step 2)
8
Select Start Case Entry
extra step (reference ends at step 2)
9
Select Generate Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (9 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 81.7 vs reference 83.4 (delta -1.7). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Generate Narrative
reference at this step: View Submissions
3
View Validation Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +1.4
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Select Cancel Workflow
extra step (reference ends at step 2)
4
Submit Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
View Submissions
extra step (reference ends at step 2)
7
Select Start Case Entry
extra step (reference ends at step 2)
8
View Reference Numbers
extra step (reference ends at step 2)
9
View Contacts
extra step (reference ends at step 2)
10
View Patient
extra step (reference ends at step 2)
11
View Medical History
extra step (reference ends at step 2)
12
View Case Details
extra step (reference ends at step 2)
13
Select Unknown Value
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (13 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 84.8 vs reference 83.4 (delta +1.4). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Preview Japanese Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Products
reference at this step: View Submissions
3
Select Patient
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Show More Details
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Product: Pembrolizumab
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Open Case Assessment Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Veeva Safety | 203 | 89.8% | 100.0% |
| Microsoft Word | 10 | 4.4% | 0.0% |
| collaboration.merck.com | 4 | 1.8% | 0.0% |
| Acrobat | 4 | 1.8% | 0.0% |
| Microsoft Outlook | 3 | 1.3% | 0.0% |
| Microsoft Excel | 1 | 0.4% | 0.0% |
| YoudaoDict | 1 | 0.4% | 0.0% |
Top Cross-App Transitions (within task instance)
Consecutive events that cross application boundaries within a task instance — the signal where swivel-chair patterns live.
| From | To | Transitions |
|---|---|---|
| Veeva Safety | Microsoft Word | 8 |
| Microsoft Word | Veeva Safety | 4 |
| Veeva Safety | Acrobat | 3 |
| Veeva Safety | Microsoft Outlook | 2 |
| Veeva Safety | collaboration.merck.com | 2 |
| Microsoft Outlook | Veeva Safety | 2 |
| collaboration.merck.com | Veeva Safety | 2 |
| Veeva Safety | Microsoft Excel | 1 |
| Microsoft Word | YoudaoDict | 1 |
| Acrobat | collaboration.merck.com | 1 |
On-Case Application Journey (±15 min around anchor)
Apps the same analyst touched on the same case within ±15 minutes of the task anchor. Captures work that spans task boundaries — the Veeva/Acrobat/Outlook/Word context surrounding the anchor click.
Case counts per app are not mutually exclusive — a case that touched Veeva AND Phobos in this window is counted in both rows. Overlap reflects real cross-app work, not double-counted cases.
Veeva Safety DOM 1,290 events 56 cases 17.8 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
99×
pyzeClick
<div>
"Narrative"
65×
pyzeClick
<div>
"Case Assessment Results"
44×
pyzeClick
<a>
"Show more"
44×
pyzeClick
<span>
"Adverse Events"
35×
pyzeClick
<button>
"Save"
33×
pyzeClick
<div>
"Case Assessments"
33×
pyzeClick
<span>
"Products"
32×
Phobos DOM 130 events 26 cases 3.2 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<button>
"Proceed"
21×
pyzeClick
<button>
"Send to process"
19×
pyzeClick
<button>
"Advance"
14×
pyzeClick
<td>
"2345469 (v5.1) Japanese (Japan)"
12×
pyzeClick
<td>
"2352671 (v0.1) Japanese (Japan)"
10×
pyzeClick
<button>
"Save Comments"
10×
pyzeClick
<button>
"Login"
9×
pyzeClick
<td>
"2347576 (v2.1) Japanese (Japan)"
6×
Acrobat App 29 events 9 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
349 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Word Document 29 events 12 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
V-Narrative 549550 (English) (26643764_0_1_347593)
354×
file
V-Narrative 523977 (English) (26234010_0_2_341403)
116×
file
V-Narrative 549428 (English) (26642399_0_2_349187)
88×
file
V-Narrative 531855 (English) (26362027_0_1_346062)
84×
file
Narrative 481786 (English)
84×
file
V-Narrative 524568 (English) (26241711_0_2_343144)
34×
file
V-Narrative 540056 (English) (26485638_0_3_344672)
31×
file
V-Narrative 533936 (English) (26397592_0_1_338360)
25×
Microsoft Teams App 23 events 12 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
293 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Excel Document 15 events 7 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
Case tracking list
42×
file
ICHICSR-EVHUMAN_10020278639 (1)
33×
file
All PV Smart Submissions 28-NOV-2025 PM
12×
file
2355984 (v0.1)
12×
file
2354547 (v0.1)
9×
file
Query 21-NOV-2025
9×
collaboration.merck.com App 11 events 10 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Microsoft Outlook Message 9 events 7 cases
Message-level capture
Task Mining captures email subjects. Case numbers frequently appear in the subject line.
evocpr01.apps.americas.cf.merck.com App 5 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Notepad App 3 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.07
Swivel Rate
events in non-primary app / total
0.79
Zero-Edit Visit Rate
inspection-only clicks
1.08
Avg Revisit Depth
max repeats of any activity
0.00
Cross-App Time Share
time outside primary app
Meta Score Distribution
Instance count in each 10-point adherence bucket. Right-skewed = healthy execution; long left tail = concentrated pain points.
0
10
20
30
40
50
60
70
80
90
Top Concern Vector
Zero-Edit Visit Rate — current value 0.79
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Vector Contribution to Adherence Loss
Each vector's weighted contribution to lost adherence. The top row is your highest-leverage fix.
Zero-Edit Visit Rate
value 0.79
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.08
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.07
Reduce cross-app hops by surfacing the secondary-app data inline (API integration or pre-fetched context panel).
Cross-App Time Share
value 0.00
Time outside primary app dominates this score. Identify which secondary app(s) and whether their function can be in-lined.
Lowest-Adherence Instances
The 5 task instances that scored lowest. These are the concrete cases worth investigating to understand the worst patterns.
| Case | Analyst | Score | Duration | Sub-Steps | Swivel | X-App | Revisit |
|---|---|---|---|---|---|---|---|
| 2354472 | Analyst 12 | 62.5 | 6.9m | 3 | 0.67 | 0.00 | 1 |
| 2355984 | Analyst 09 | 62.5 | 24.4m | 11 | 0.55 | 0.00 | 3 |
| 2354895 | Analyst 05 | 67.5 | 0.1m | 2 | 0.50 | 0.00 | 1 |
| 2351742 | Analyst 12 | 67.5 | 5.0m | 2 | 0.50 | 0.00 | 1 |
| 2342905 | Analyst 09 | 67.5 | 1.2m | 4 | 0.50 | 0.00 | 1 |
Users on This Task
10 analysts executed this task during the pilot. Scatter plots productivity (instances per active day) against adherence (meta score). Top-right = healthy high-volume analysts; bottom-right = firefighters; top-left = careful low-volume; bottom-left = struggling.
Adherence (meta score) →
Productivity (instances / active day) →
07
15
14
02
12
09
10
03
01
05
User-by-User Breakdown
Click any analyst to see their dominant sequence vs the reference SoP.
| Analyst | Instances | Inst / Day | Adherence | Weakest Vector | Swivel | X-App | Min | |
|---|---|---|---|---|---|---|---|---|
| ▸ | Analyst 07 | 1 | 1.0 | 97.5 | Revisit Depth | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 07's Dominant Sequence
— 1 of 1 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 15 | 2 | 2.0 | 88.8 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 15's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
View Narrative Preview Header
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 14 | 8 | 4.0 | 86.8 | Zero-Edit Visits | 0.00 | 0.00 | 13 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 14's Dominant Sequence
— 3 of 8 instances
1
View Narrative
2
Preview English Narrative
· reference: View Submissions
This analyst exhibits 6 distinct sequences across their 8 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 02 | 2 | 1.0 | 84.4 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 02's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Open Details Section
· reference: View Submissions
3
Create New Item
4
Save
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 12 | 11 | 1.8 | 83.9 | Zero-Edit Visits | 0.14 | 0.00 | 10,211 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 12's Dominant Sequence
— 4 of 11 instances
1
View Narrative
This analyst exhibits 8 distinct sequences across their 11 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 09 | 27 | 2.1 | 82.6 | Zero-Edit Visits | 0.07 | 0.00 | 72 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 09's Dominant Sequence
— 2 of 27 instances
1
View Narrative
This analyst exhibits 24 distinct sequences across their 27 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 10 | 6 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 25 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 10's Dominant Sequence
— 2 of 6 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
This analyst exhibits 5 distinct sequences across their 6 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 03 | 3 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 03's Dominant Sequence
— 3 of 3 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 01 | 1 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 01's Dominant Sequence
— 1 of 1 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
|
||||||||
| ▸ | Analyst 05 | 2 | 1.0 | 69.9 | Zero-Edit Visits | 0.35 | 0.00 | 29 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 05's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
Microsoft Word
4
View Reference Numbers
5
Microsoft Outlook
6
View Contacts
7
View Create Options
8
Create New Item
9
Continue
10
View Study
11
Microsoft Word
12
View Patient
13
View Medical History
14
View Adverse Events
15
View Test Results
16
Microsoft Word
17
Create New Item
18
Open Test Results Section
19
View Case Assessment Results
20
Open Case Assessments
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
83.4
Avg Adherence Score (0-100)
Median 82.5 · Range 62.5–97.5
166.3 min
Avg Task Duration
1.0 min median
3.4
Avg Sub-Steps per Instance
82.3% have multiple sub-steps
1.6%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
1.6% of instances follow this exactly
Review Narrative — Mined SoP
The most common sub-step sequence observed across 62 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Narrative
1.6s
0.4 edits
Veeva Safety
100%
2
View Submissions
0.0s
Veeva Safety
13%
Variant Explorer
Reference
Review Narrative Reference Path
1 instances · 1 analysts
This is the mined reference path — 1 instances across 1 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Review Narrative.
Genuine Complexity
Complex-Case Execution Path
11 instances · 5 analysts
· Δ adherence +4.6
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
×
View Submissions
skipped — this reference step was not executed
Genuine Complexity — this sequence differs from the reference path (1 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 88.0 vs reference 83.4 (delta +4.6). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
7 instances · 4 analysts
· Δ adherence +6.6
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Preview English Narrative
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 90.0 vs reference 83.4 (delta +6.6). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
4 instances · 3 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
2 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View System Section
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 2 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -1.7
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View Entry Phase
extra step (reference ends at step 2)
4
Select Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
Submit Cancel Workflow
extra step (reference ends at step 2)
7
Cancel Workflow
extra step (reference ends at step 2)
8
Select Start Case Entry
extra step (reference ends at step 2)
9
Select Generate Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (9 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 81.7 vs reference 83.4 (delta -1.7). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Generate Narrative
reference at this step: View Submissions
3
View Validation Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +1.4
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Select Cancel Workflow
extra step (reference ends at step 2)
4
Submit Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
View Submissions
extra step (reference ends at step 2)
7
Select Start Case Entry
extra step (reference ends at step 2)
8
View Reference Numbers
extra step (reference ends at step 2)
9
View Contacts
extra step (reference ends at step 2)
10
View Patient
extra step (reference ends at step 2)
11
View Medical History
extra step (reference ends at step 2)
12
View Case Details
extra step (reference ends at step 2)
13
Select Unknown Value
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (13 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 84.8 vs reference 83.4 (delta +1.4). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Preview Japanese Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Products
reference at this step: View Submissions
3
Select Patient
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Show More Details
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Product: Pembrolizumab
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Open Case Assessment Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Veeva Safety | 194 | 91.1% | 100.0% |
| Microsoft Word | 7 | 3.3% | 0.0% |
| Acrobat | 4 | 1.9% | 0.0% |
| collaboration.merck.com | 4 | 1.9% | 0.0% |
| Microsoft Outlook | 3 | 1.4% | 0.0% |
| Microsoft Excel | 1 | 0.5% | 0.0% |
Top Cross-App Transitions (within task instance)
Consecutive events that cross application boundaries within a task instance — the signal where swivel-chair patterns live.
| From | To | Transitions |
|---|---|---|
| Veeva Safety | Microsoft Word | 6 |
| Microsoft Word | Veeva Safety | 3 |
| Veeva Safety | Acrobat | 3 |
| Veeva Safety | collaboration.merck.com | 2 |
| Microsoft Outlook | Veeva Safety | 2 |
| Veeva Safety | Microsoft Outlook | 2 |
| collaboration.merck.com | Veeva Safety | 1 |
| Acrobat | collaboration.merck.com | 1 |
| Veeva Safety | Microsoft Excel | 1 |
| Microsoft Excel | Veeva Safety | 1 |
On-Case Application Journey (±15 min around anchor)
Apps the same analyst touched on the same case within ±15 minutes of the task anchor. Captures work that spans task boundaries — the Veeva/Acrobat/Outlook/Word context surrounding the anchor click.
Case counts per app are not mutually exclusive — a case that touched Veeva AND Phobos in this window is counted in both rows. Overlap reflects real cross-app work, not double-counted cases.
Veeva Safety DOM 1,290 events 56 cases 17.8 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
99×
pyzeClick
<div>
"Narrative"
65×
pyzeClick
<div>
"Case Assessment Results"
44×
pyzeClick
<a>
"Show more"
44×
pyzeClick
<span>
"Adverse Events"
35×
pyzeClick
<button>
"Save"
33×
pyzeClick
<div>
"Case Assessments"
33×
pyzeClick
<span>
"Products"
32×
Phobos DOM 130 events 26 cases 3.2 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<button>
"Proceed"
21×
pyzeClick
<button>
"Send to process"
19×
pyzeClick
<button>
"Advance"
14×
pyzeClick
<td>
"2345469 (v5.1) Japanese (Japan)"
12×
pyzeClick
<button>
"Save Comments"
10×
pyzeClick
<td>
"2352671 (v0.1) Japanese (Japan)"
10×
pyzeClick
<button>
"Login"
9×
pyzeClick
<td>
"2347576 (v2.1) Japanese (Japan)"
6×
Acrobat App 29 events 9 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
349 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Word Document 29 events 12 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
V-Narrative 549550 (English) (26643764_0_1_347593)
354×
file
V-Narrative 523977 (English) (26234010_0_2_341403)
116×
file
V-Narrative 549428 (English) (26642399_0_2_349187)
88×
file
V-Narrative 531855 (English) (26362027_0_1_346062)
84×
file
Narrative 481786 (English)
84×
file
V-Narrative 524568 (English) (26241711_0_2_343144)
34×
file
V-Narrative 540056 (English) (26485638_0_3_344672)
31×
file
V-Narrative 533936 (English) (26397592_0_1_338360)
25×
Microsoft Teams App 23 events 12 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
293 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Excel Document 15 events 7 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
Case tracking list
42×
file
ICHICSR-EVHUMAN_10020278639 (1)
33×
file
All PV Smart Submissions 28-NOV-2025 PM
12×
file
2355984 (v0.1)
12×
file
2354547 (v0.1)
9×
file
Query 21-NOV-2025
9×
collaboration.merck.com App 11 events 10 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Microsoft Outlook Message 9 events 7 cases
Message-level capture
Task Mining captures email subjects. Case numbers frequently appear in the subject line.
evocpr01.apps.americas.cf.merck.com App 5 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Notepad App 3 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.07
Swivel Rate
events in non-primary app / total
0.80
Zero-Edit Visit Rate
inspection-only clicks
1.05
Avg Revisit Depth
max repeats of any activity
0.00
Cross-App Time Share
time outside primary app
Meta Score Distribution
Instance count in each 10-point adherence bucket. Right-skewed = healthy execution; long left tail = concentrated pain points.
0
10
20
30
40
50
60
70
80
90
Top Concern Vector
Zero-Edit Visit Rate — current value 0.80
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Vector Contribution to Adherence Loss
Each vector's weighted contribution to lost adherence. The top row is your highest-leverage fix.
Zero-Edit Visit Rate
value 0.80
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.05
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.07
Reduce cross-app hops by surfacing the secondary-app data inline (API integration or pre-fetched context panel).
Cross-App Time Share
value 0.00
Time outside primary app dominates this score. Identify which secondary app(s) and whether their function can be in-lined.
Lowest-Adherence Instances
The 5 task instances that scored lowest. These are the concrete cases worth investigating to understand the worst patterns.
| Case | Analyst | Score | Duration | Sub-Steps | Swivel | X-App | Revisit |
|---|---|---|---|---|---|---|---|
| 2354472 | Analyst 12 | 62.5 | 6.9m | 3 | 0.67 | 0.00 | 1 |
| 2355984 | Analyst 09 | 64.5 | 2.1m | 5 | 0.60 | 0.00 | 1 |
| 2351742 | Analyst 12 | 67.5 | 5.0m | 2 | 0.50 | 0.00 | 1 |
| 2342905 | Analyst 09 | 67.5 | 1.2m | 4 | 0.50 | 0.00 | 1 |
| 2354895 | Analyst 05 | 67.5 | 0.1m | 2 | 0.50 | 0.00 | 1 |
Users on This Task
10 analysts executed this task during the pilot. Scatter plots productivity (instances per active day) against adherence (meta score). Top-right = healthy high-volume analysts; bottom-right = firefighters; top-left = careful low-volume; bottom-left = struggling.
Adherence (meta score) →
Productivity (instances / active day) →
07
15
14
02
12
10
03
01
09
05
User-by-User Breakdown
Click any analyst to see their dominant sequence vs the reference SoP.
| Analyst | Instances | Inst / Day | Adherence | Weakest Vector | Swivel | X-App | Min | |
|---|---|---|---|---|---|---|---|---|
| ▸ | Analyst 07 | 1 | 1.0 | 97.5 | Revisit Depth | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 07's Dominant Sequence
— 1 of 1 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 15 | 2 | 2.0 | 88.8 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 15's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
View Narrative Preview Header
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 14 | 8 | 4.0 | 86.8 | Zero-Edit Visits | 0.00 | 0.00 | 13 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 14's Dominant Sequence
— 3 of 8 instances
1
View Narrative
2
Preview English Narrative
· reference: View Submissions
This analyst exhibits 6 distinct sequences across their 8 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 02 | 2 | 1.0 | 84.4 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 02's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Open Details Section
· reference: View Submissions
3
Create New Item
4
Save
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 12 | 11 | 1.8 | 83.9 | Zero-Edit Visits | 0.14 | 0.00 | 10,211 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 12's Dominant Sequence
— 4 of 11 instances
1
View Narrative
This analyst exhibits 8 distinct sequences across their 11 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 10 | 6 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 25 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 10's Dominant Sequence
— 2 of 6 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
This analyst exhibits 5 distinct sequences across their 6 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 03 | 3 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 03's Dominant Sequence
— 3 of 3 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 01 | 1 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 01's Dominant Sequence
— 1 of 1 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
|
||||||||
| ▸ | Analyst 09 | 26 | 2.0 | 82.4 | Zero-Edit Visits | 0.08 | 0.00 | 50 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 09's Dominant Sequence
— 2 of 26 instances
1
View Narrative
This analyst exhibits 23 distinct sequences across their 26 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 05 | 2 | 1.0 | 71.0 | Zero-Edit Visits | 0.36 | 0.00 | 9 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 05's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
Microsoft Word
4
View Reference Numbers
5
Microsoft Outlook
6
View Contacts
7
View Create Options
8
Create New Item
9
Continue
10
View Study
11
Microsoft Word
12
View Patient
13
View Medical History
14
View Adverse Events
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
83.4
Avg Adherence Score (0-100)
Median 82.5 · Range 62.5–97.5
167.0 min
Avg Task Duration
1.0 min median
3.6
Avg Sub-Steps per Instance
82.3% have multiple sub-steps
1.6%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
1.6% of instances follow this exactly
Review Narrative — Mined SoP
The most common sub-step sequence observed across 62 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Narrative
1.6s
0.4 edits
Veeva Safety
100%
2
View Submissions
0.0s
Veeva Safety
13%
Variant Explorer
Reference
Review Narrative Reference Path
1 instances · 1 analysts
This is the mined reference path — 1 instances across 1 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Review Narrative.
Genuine Complexity
Complex-Case Execution Path
11 instances · 5 analysts
· Δ adherence +4.6
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
×
View Submissions
skipped — this reference step was not executed
Genuine Complexity — this sequence differs from the reference path (1 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 88.0 vs reference 83.4 (delta +4.6). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Genuine Complexity
Complex-Case Execution Path
7 instances · 4 analysts
· Δ adherence +6.6
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Preview English Narrative
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 90.0 vs reference 83.4 (delta +6.6). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Genuine Complexity
Complex-Case Execution Path
4 instances · 3 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Reviewer Sweep
Reviewer Verification Pass
2 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View System Section
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 2 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -1.7
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Submissions
3
View Entry Phase
extra step (reference ends at step 2)
4
Select Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
Submit Cancel Workflow
extra step (reference ends at step 2)
7
Cancel Workflow
extra step (reference ends at step 2)
8
Select Start Case Entry
extra step (reference ends at step 2)
9
Select Generate Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (9 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 81.7 vs reference 83.4 (delta -1.7). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Generate Narrative
reference at this step: View Submissions
3
View Validation Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +1.4
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Select Cancel Workflow
extra step (reference ends at step 2)
4
Submit Cancel Workflow
extra step (reference ends at step 2)
5
Cancel Workflow
extra step (reference ends at step 2)
6
View Submissions
extra step (reference ends at step 2)
7
Select Start Case Entry
extra step (reference ends at step 2)
8
View Reference Numbers
extra step (reference ends at step 2)
9
View Contacts
extra step (reference ends at step 2)
10
View Patient
extra step (reference ends at step 2)
11
View Medical History
extra step (reference ends at step 2)
12
View Case Details
extra step (reference ends at step 2)
13
Select Unknown Value
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (13 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 84.8 vs reference 83.4 (delta +1.4). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Preview Japanese Narrative
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence +4.1
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Select Products
reference at this step: View Submissions
3
Select Patient
extra step (reference ends at step 2)
Genuine Complexity — this sequence differs from the reference path (3 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 87.5 vs reference 83.4 (delta +4.1). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Case Details
reference at this step: View Submissions
3
Show More Details
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Genuine Complexity
Complex-Case Execution Path
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
View Product: Pembrolizumab
reference at this step: View Submissions
Genuine Complexity — this sequence differs from the reference path (2 sub-steps vs 2 in reference) but shows no strong pain-point signals: adherence score 82.5 vs reference 83.4 (delta -0.9). Likely a legitimate case-complexity path — not an automation candidate, but worth cataloging.
Linked Remediation Opportunities
Reviewer Sweep
Reviewer Verification Pass
1 instances · 1 analysts
· Δ adherence -0.9
Observed Sequence (vs Reference SoP on left)
differs from reference
matches reference
1
View Narrative
2
Show More Details
reference at this step: View Submissions
3
Open Case Assessment Results
extra step (reference ends at step 2)
Reviewer Sweep — a viewing-heavy pattern with 3.0 avg sub-steps and zero edits captured. Consistent with a downstream reviewer re-opening the task to verify earlier work rather than progressing new data. 1 analysts across 1 cases.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Veeva Safety | 203 | 89.8% | 100.0% |
| Microsoft Word | 10 | 4.4% | 0.0% |
| Acrobat | 4 | 1.8% | 0.0% |
| collaboration.merck.com | 4 | 1.8% | 0.0% |
| Microsoft Outlook | 3 | 1.3% | 0.0% |
| Microsoft Excel | 1 | 0.4% | 0.0% |
| YoudaoDict | 1 | 0.4% | 0.0% |
Top Cross-App Transitions (within task instance)
Consecutive events that cross application boundaries within a task instance — the signal where swivel-chair patterns live.
| From | To | Transitions |
|---|---|---|
| Veeva Safety | Microsoft Word | 8 |
| Microsoft Word | Veeva Safety | 4 |
| Veeva Safety | Acrobat | 3 |
| Veeva Safety | Microsoft Outlook | 2 |
| collaboration.merck.com | Veeva Safety | 2 |
| Microsoft Outlook | Veeva Safety | 2 |
| Veeva Safety | collaboration.merck.com | 2 |
| collaboration.merck.com | Microsoft Word | 1 |
| YoudaoDict | Microsoft Word | 1 |
| Microsoft Word | collaboration.merck.com | 1 |
On-Case Application Journey (±15 min around anchor)
Apps the same analyst touched on the same case within ±15 minutes of the task anchor. Captures work that spans task boundaries — the Veeva/Acrobat/Outlook/Word context surrounding the anchor click.
Case counts per app are not mutually exclusive — a case that touched Veeva AND Phobos in this window is counted in both rows. Overlap reflects real cross-app work, not double-counted cases.
Veeva Safety DOM 1,290 events 56 cases 17.8 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
99×
pyzeClick
<div>
"Narrative"
65×
pyzeClick
<div>
"Case Assessment Results"
44×
pyzeClick
<a>
"Show more"
44×
pyzeClick
<span>
"Adverse Events"
35×
pyzeClick
<button>
"Save"
33×
pyzeClick
<div>
"Case Assessments"
33×
pyzeClick
<span>
"Products"
32×
Phobos DOM 130 events 26 cases 3.2 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<button>
"Proceed"
21×
pyzeClick
<button>
"Send to process"
19×
pyzeClick
<button>
"Advance"
14×
pyzeClick
<td>
"2345469 (v5.1) Japanese (Japan)"
12×
pyzeClick
<td>
"2352671 (v0.1) Japanese (Japan)"
10×
pyzeClick
<button>
"Save Comments"
10×
pyzeClick
<button>
"Login"
9×
pyzeClick
<td>
"2347576 (v2.1) Japanese (Japan)"
6×
Acrobat App 29 events 9 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
349 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Word Document 29 events 12 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
V-Narrative 549550 (English) (26643764_0_1_347593)
354×
file
V-Narrative 523977 (English) (26234010_0_2_341403)
116×
file
V-Narrative 549428 (English) (26642399_0_2_349187)
88×
file
V-Narrative 531855 (English) (26362027_0_1_346062)
84×
file
Narrative 481786 (English)
84×
file
V-Narrative 524568 (English) (26241711_0_2_343144)
34×
file
V-Narrative 540056 (English) (26485638_0_3_344672)
31×
file
V-Narrative 533936 (English) (26397592_0_1_338360)
25×
Microsoft Teams App 23 events 12 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
293 granular events captured, but no DOM, document, or message-level metadata is available for this application. Instrumenting this app directly with Pyze would unlock element-level detail.
Microsoft Excel Document 15 events 7 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
file
Case tracking list
42×
file
ICHICSR-EVHUMAN_10020278639 (1)
33×
file
All PV Smart Submissions 28-NOV-2025 PM
12×
file
2355984 (v0.1)
12×
file
2354547 (v0.1)
9×
file
Query 21-NOV-2025
9×
collaboration.merck.com App 11 events 10 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Microsoft Outlook Message 9 events 7 cases
Message-level capture
Task Mining captures email subjects. Case numbers frequently appear in the subject line.
evocpr01.apps.americas.cf.merck.com App 5 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Notepad App 3 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.07
Swivel Rate
events in non-primary app / total
0.79
Zero-Edit Visit Rate
inspection-only clicks
1.1
Avg Revisit Depth
max repeats of any activity
0.00
Cross-App Time Share
time outside primary app
Meta Score Distribution
Instance count in each 10-point adherence bucket. Right-skewed = healthy execution; long left tail = concentrated pain points.
0
10
20
30
40
50
60
70
80
90
Top Concern Vector
Zero-Edit Visit Rate — current value 0.79
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Vector Contribution to Adherence Loss
Each vector's weighted contribution to lost adherence. The top row is your highest-leverage fix.
Zero-Edit Visit Rate
value 0.79
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.10
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.07
Reduce cross-app hops by surfacing the secondary-app data inline (API integration or pre-fetched context panel).
Cross-App Time Share
value 0.00
Time outside primary app dominates this score. Identify which secondary app(s) and whether their function can be in-lined.
Lowest-Adherence Instances
The 5 task instances that scored lowest. These are the concrete cases worth investigating to understand the worst patterns.
| Case | Analyst | Score | Duration | Sub-Steps | Swivel | X-App | Revisit |
|---|---|---|---|---|---|---|---|
| 2355984 | Analyst 09 | 62.5 | 24.4m | 11 | 0.55 | 0.00 | 3 |
| 2354472 | Analyst 12 | 62.5 | 6.9m | 3 | 0.67 | 0.00 | 1 |
| 2354895 | Analyst 05 | 67.5 | 0.1m | 2 | 0.50 | 0.00 | 1 |
| 2351742 | Analyst 12 | 67.5 | 5.0m | 2 | 0.50 | 0.00 | 1 |
| 2342905 | Analyst 09 | 67.5 | 1.2m | 4 | 0.50 | 0.00 | 1 |
Users on This Task
10 analysts executed this task during the pilot. Scatter plots productivity (instances per active day) against adherence (meta score). Top-right = healthy high-volume analysts; bottom-right = firefighters; top-left = careful low-volume; bottom-left = struggling.
Adherence (meta score) →
Productivity (instances / active day) →
07
15
14
02
12
10
03
01
09
05
User-by-User Breakdown
Click any analyst to see their dominant sequence vs the reference SoP.
| Analyst | Instances | Inst / Day | Adherence | Weakest Vector | Swivel | X-App | Min | |
|---|---|---|---|---|---|---|---|---|
| ▸ | Analyst 07 | 1 | 1.0 | 97.5 | Revisit Depth | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 07's Dominant Sequence
— 1 of 1 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 15 | 2 | 2.0 | 88.8 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 15's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
View Narrative Preview Header
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 14 | 8 | 4.0 | 86.8 | Zero-Edit Visits | 0.00 | 0.00 | 13 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 14's Dominant Sequence
— 3 of 8 instances
1
View Narrative
2
Preview English Narrative
· reference: View Submissions
This analyst exhibits 6 distinct sequences across their 8 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 02 | 2 | 1.0 | 84.4 | Zero-Edit Visits | 0.00 | 0.00 | 1 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 02's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Open Details Section
· reference: View Submissions
3
Create New Item
4
Save
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 12 | 11 | 1.8 | 83.9 | Zero-Edit Visits | 0.14 | 0.00 | 10,211 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 12's Dominant Sequence
— 4 of 11 instances
1
View Narrative
This analyst exhibits 8 distinct sequences across their 11 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 10 | 6 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 25 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 10's Dominant Sequence
— 2 of 6 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
This analyst exhibits 5 distinct sequences across their 6 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 03 | 3 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 03's Dominant Sequence
— 3 of 3 instances
1
View Narrative
|
||||||||
| ▸ | Analyst 01 | 1 | 1.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 01's Dominant Sequence
— 1 of 1 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
|
||||||||
| ▸ | Analyst 09 | 26 | 2.0 | 82.4 | Zero-Edit Visits | 0.07 | 0.00 | 73 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 09's Dominant Sequence
— 2 of 26 instances
1
View Narrative
This analyst exhibits 23 distinct sequences across their 26 instances; the dominant one is shown.
|
||||||||
| ▸ | Analyst 05 | 2 | 1.0 | 69.9 | Zero-Edit Visits | 0.35 | 0.00 | 29 |
|
Reference SoP
1
View Narrative
2
View Submissions
Analyst 05's Dominant Sequence
— 1 of 2 instances
1
View Narrative
2
Show More Details
· reference: View Submissions
3
Microsoft Word
4
View Reference Numbers
5
Microsoft Outlook
6
View Contacts
7
View Create Options
8
Create New Item
9
Continue
10
View Study
11
Microsoft Word
12
View Patient
13
View Medical History
14
View Adverse Events
15
View Test Results
16
Microsoft Word
17
Create New Item
18
Open Test Results Section
19
View Case Assessment Results
20
Open Case Assessments
This analyst exhibits 2 distinct sequences across their 2 instances; the dominant one is shown.
|
||||||||