Task-Boundary Mode
How task-instance boundaries are drawn from the event stream. Applies to every Task SoP, Step SoP, and Variants view.
Case Review
📝 Task SoP
Mined from 53 instances
Open Combined Review
How 2 analysts execute this task across 20 cases — auto-generated Standard Operating Procedure with adherence scoring.
82.5
Avg Adherence Score (0-100)
Median 82.5 · Range 82.5–82.5
15.0 min
Avg Task Duration
0.0 min median
1.0
Avg Sub-Steps per Instance
0.0% have multiple sub-steps
100.0%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
100.0% of instances follow this exactly
Open Combined Review — Mined SoP
The most common sub-step sequence observed across 55 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Combined Review
0.0s
Phobos
100%
No deviation variants observed for this task in the current cut — every instance follows the reference path.
Reference
Open Combined Review Reference Path
55 instances · 2 analysts
This is the mined reference path — 55 instances across 2 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Open Combined Review.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Phobos | 55 | 100.0% | 0.0% |
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 219 events 15 cases 1.6 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
24×
pyzeClick
<span>
"Narrative"
17×
pyzeClick
<a>
"Show more"
17×
pyzeClick
<span>
"Submissions & Distributions"
12×
pyzeClick
<span>
"Products"
11×
pyzeClick
<span>
"Workflow Timeline"
11×
pyzeClick
<span>
"Study"
10×
pyzeClick
<span>
"Reference Numbers"
10×
Phobos DOM 175 events 20 cases 2.4 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<a>
"Cases"
50×
pyzeClick
<a>
"Review"
46×
pyzeClick
<a>
"Cases Coordinator"
41×
pyzeClick
<a>
"Review Coordinator"
40×
pyzeClick
<button>
"Proceed"
40×
pyzeClick
<button>
"Send to process"
38×
pyzeClick
<a>
"Inbox"
37×
pyzeClick
<button>
"Save Comments"
36×
Acrobat App 7 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
128 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 Teams App 5 events 3 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
55 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.
ONENOTE Document 3 events 1 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
MEDDRABROWSERWIN App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
43 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.
YoudaoDict App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
sync.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
collaboration.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
gpteal.merck.com DOM 1 events 1 cases
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.00
Swivel Rate
events in non-primary app / total
1.00
Zero-Edit Visit Rate
inspection-only clicks
1.0
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 1.00
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 1.00
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.00
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.00
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 |
|---|---|---|---|---|---|---|---|
| 1757023 | Analyst 05 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2335737 | Analyst 05 | 82.5 | 0.1m | 1 | 0.00 | 0.00 | 1 |
| 2335737 | Analyst 05 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
Users on This Task
2 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) →
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 09 | 51 | 4.6 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 825 |
|
Reference SoP
1
View Combined Review
Analyst 09's Dominant Sequence
— 51 of 51 instances
1
View Combined Review
|
||||||||
| ▸ | Analyst 05 | 4 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Combined Review
Analyst 05's Dominant Sequence
— 4 of 4 instances
1
View Combined Review
|
||||||||
82.5
Avg Adherence Score (0-100)
Median 82.5 · Range 82.5–82.5
15.0 min
Avg Task Duration
0.0 min median
1.0
Avg Sub-Steps per Instance
0.0% have multiple sub-steps
100.0%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
100.0% of instances follow this exactly
Open Combined Review — Mined SoP
The most common sub-step sequence observed across 55 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Combined Review
0.0s
Phobos
100%
No deviation variants observed for this task in the current cut — every instance follows the reference path.
Reference
Open Combined Review Reference Path
55 instances · 2 analysts
This is the mined reference path — 55 instances across 2 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Open Combined Review.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Phobos | 55 | 100.0% | 0.0% |
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 219 events 15 cases 1.6 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
24×
pyzeClick
<span>
"Narrative"
17×
pyzeClick
<a>
"Show more"
17×
pyzeClick
<span>
"Submissions & Distributions"
12×
pyzeClick
<span>
"Workflow Timeline"
11×
pyzeClick
<span>
"Products"
11×
pyzeClick
<span>
"Reference Numbers"
10×
pyzeClick
<span>
"Study"
10×
Phobos DOM 175 events 20 cases 2.4 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<a>
"Cases"
50×
pyzeClick
<a>
"Review"
46×
pyzeClick
<a>
"Cases Coordinator"
41×
pyzeClick
<a>
"Review Coordinator"
40×
pyzeClick
<button>
"Proceed"
40×
pyzeClick
<button>
"Send to process"
38×
pyzeClick
<a>
"Inbox"
37×
pyzeClick
<button>
"Save Comments"
36×
Acrobat App 7 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
128 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 Teams App 5 events 3 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
55 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.
ONENOTE Document 3 events 1 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
MEDDRABROWSERWIN App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
43 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.
YoudaoDict App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
sync.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
collaboration.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
gpteal.merck.com DOM 1 events 1 cases
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.00
Swivel Rate
events in non-primary app / total
1.00
Zero-Edit Visit Rate
inspection-only clicks
1.0
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 1.00
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 1.00
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.00
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.00
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 |
|---|---|---|---|---|---|---|---|
| 1757023 | Analyst 05 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2335737 | Analyst 05 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.1m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.2m | 1 | 0.00 | 0.00 | 1 |
Users on This Task
2 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) →
05
09
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 05 | 4 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Combined Review
Analyst 05's Dominant Sequence
— 4 of 4 instances
1
View Combined Review
|
||||||||
| ▸ | Analyst 09 | 51 | 4.6 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 825 |
|
Reference SoP
1
View Combined Review
Analyst 09's Dominant Sequence
— 51 of 51 instances
1
View Combined Review
|
||||||||
82.4
Avg Adherence Score (0-100)
Median 82.5 · Range 80.0–82.5
15.6 min
Avg Task Duration
0.0 min median
1.0
Avg Sub-Steps per Instance
3.8% have multiple sub-steps
100.0%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
100.0% of instances follow this exactly
Open Combined Review — Mined SoP
The most common sub-step sequence observed across 53 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Combined Review
0.0s
Phobos
100%
No deviation variants observed for this task in the current cut — every instance follows the reference path.
Reference
Open Combined Review Reference Path
53 instances · 2 analysts
This is the mined reference path — 53 instances across 2 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Open Combined Review.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Phobos | 55 | 100.0% | 0.0% |
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 219 events 15 cases 1.6 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
24×
pyzeClick
<span>
"Narrative"
17×
pyzeClick
<a>
"Show more"
17×
pyzeClick
<span>
"Submissions & Distributions"
12×
pyzeClick
<span>
"Workflow Timeline"
11×
pyzeClick
<span>
"Products"
11×
pyzeClick
<span>
"Reference Numbers"
10×
pyzeClick
<span>
"Study"
10×
Phobos DOM 175 events 20 cases 2.4 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<a>
"Cases"
50×
pyzeClick
<a>
"Review"
46×
pyzeClick
<a>
"Cases Coordinator"
41×
pyzeClick
<button>
"Proceed"
40×
pyzeClick
<a>
"Review Coordinator"
40×
pyzeClick
<button>
"Send to process"
38×
pyzeClick
<a>
"Inbox"
37×
pyzeClick
<a>
"Inbox Coordinator"
36×
Acrobat App 7 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
128 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 Teams App 5 events 3 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
55 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.
ONENOTE Document 3 events 1 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
MEDDRABROWSERWIN App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
43 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.
YoudaoDict App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
sync.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
collaboration.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
gpteal.merck.com DOM 1 events 1 cases
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.00
Swivel Rate
events in non-primary app / total
1.00
Zero-Edit Visit Rate
inspection-only clicks
1.04
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 1.00
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 1.00
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.04
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.00
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 |
|---|---|---|---|---|---|---|---|
| 2349786 | Analyst 09 | 80.0 | 40.8m | 2 | 0.00 | 0.00 | 2 |
| 2264672 | Analyst 09 | 80.0 | 0.6m | 2 | 0.00 | 0.00 | 2 |
| 2240449 | Analyst 09 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2335737 | Analyst 05 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
Users on This Task
2 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) →
05
09
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 05 | 4 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Combined Review
Analyst 05's Dominant Sequence
— 4 of 4 instances
1
View Combined Review
|
||||||||
| ▸ | Analyst 09 | 49 | 4.5 | 82.4 | Zero-Edit Visits | 0.00 | 0.00 | 825 |
|
Reference SoP
1
View Combined Review
Analyst 09's Dominant Sequence
— 49 of 49 instances
1
View Combined Review
|
||||||||
82.4
Avg Adherence Score (0-100)
Median 82.5 · Range 80.0–82.5
15.6 min
Avg Task Duration
0.0 min median
1.0
Avg Sub-Steps per Instance
3.8% have multiple sub-steps
100.0%
Reference Path Coverage
Instances following mined SoP exactly
Reference Baseline
100.0% of instances follow this exactly
Open Combined Review — Mined SoP
The most common sub-step sequence observed across 53 task instances. Use the dropdown on the right to compare any deviation to this baseline.
1
View Combined Review
0.0s
Phobos
100%
No deviation variants observed for this task in the current cut — every instance follows the reference path.
Reference
Open Combined Review Reference Path
53 instances · 2 analysts
This is the mined reference path — 53 instances across 2 analysts follow this exact sequence. Treat as the proposed Standard Operating Procedure for Open Combined Review.
Application Mix
Which applications analysts touch while executing this task, measured by event count and active dwell time.
| Application | Events | Event Share | Dwell Share |
|---|---|---|---|
| Phobos | 55 | 100.0% | 0.0% |
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 219 events 15 cases 1.6 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<span>
"Complete"
24×
pyzeClick
<span>
"Narrative"
17×
pyzeClick
<a>
"Show more"
17×
pyzeClick
<span>
"Submissions & Distributions"
12×
pyzeClick
<span>
"Products"
11×
pyzeClick
<span>
"Workflow Timeline"
11×
pyzeClick
<span>
"Study"
10×
pyzeClick
<span>
"Reference Numbers"
10×
Phobos DOM 175 events 20 cases 2.4 min
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
pyzeClick
<a>
"Cases"
50×
pyzeClick
<a>
"Review"
46×
pyzeClick
<a>
"Cases Coordinator"
41×
pyzeClick
<button>
"Proceed"
40×
pyzeClick
<a>
"Review Coordinator"
40×
pyzeClick
<button>
"Send to process"
38×
pyzeClick
<a>
"Inbox"
37×
pyzeClick
<a>
"Inbox Coordinator"
36×
Acrobat App 7 events 2 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
128 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 Teams App 5 events 3 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
55 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.
ONENOTE Document 3 events 1 cases
Document-level capture
Task Mining captures the specific file open during work — file names often encode case context.
MEDDRABROWSERWIN App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
43 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.
YoudaoDict App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
sync.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
collaboration.merck.com App 1 events 1 cases
App-level capture
Only application name and dwell time available. Direct instrumentation would unlock deeper detail.
gpteal.merck.com DOM 1 events 1 cases
DOM-level capture
Pyze JS captures every element interaction — button labels, field IDs, section panels.
Adherence Vectors
Each task instance is scored on four behavioral vectors. Lower values are more adherent to the mined SoP.
0.00
Swivel Rate
events in non-primary app / total
1.00
Zero-Edit Visit Rate
inspection-only clicks
1.04
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 1.00
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 1.00
Investigate why analysts inspect-and-leave without editing — usually missing upstream data or unclear UI affordances.
Revisit Depth
value 1.04
High revisit depth = mid-flow rework. Trace which sub-step is being repeated; usually a data-readiness gap upstream.
Swivel Rate
value 0.00
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 |
|---|---|---|---|---|---|---|---|
| 2264672 | Analyst 09 | 80.0 | 0.6m | 2 | 0.00 | 0.00 | 2 |
| 2349786 | Analyst 09 | 80.0 | 40.8m | 2 | 0.00 | 0.00 | 2 |
| 2240449 | Analyst 09 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.1m | 1 | 0.00 | 0.00 | 1 |
| 2087257 | Analyst 09 | 82.5 | 0.0m | 1 | 0.00 | 0.00 | 1 |
Users on This Task
2 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) →
05
09
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 05 | 4 | 2.0 | 82.5 | Zero-Edit Visits | 0.00 | 0.00 | 0 |
|
Reference SoP
1
View Combined Review
Analyst 05's Dominant Sequence
— 4 of 4 instances
1
View Combined Review
|
||||||||
| ▸ | Analyst 09 | 49 | 4.5 | 82.4 | Zero-Edit Visits | 0.00 | 0.00 | 825 |
|
Reference SoP
1
View Combined Review
Analyst 09's Dominant Sequence
— 49 of 49 instances
1
View Combined Review
|
||||||||