Pipeline forecast roll-up

Live Sales Correlation key: forecast_ref · 89.7%

Live Automated since Mar 2026 — 1.5 h/week reclaimed across everyone who runs it, 29 h to date. 0 h/week of hands-on work is left, and that is the figure quoted everywhere on this page.

Case footprint: median 7.9 h elapsed, 19m 48s of it hands-on, across 1 work session and 0.3 calendar days. 10 of the 10 happy-path waits exceed the 150 s idle-gap threshold, but a gap only ends a work session when it outlasts one (59 min, the fleet's mean). None here do: the case is put down and picked up inside the same sitting, while the person works other cases.

Cases: 64
Activities: 12
Variants: 22
Median throughput: 7.9 h
p95 throughput: 38.8 h
Working time / Waiting time: 19m 48s / 7.6 h
Rework: 25%
Fitness: 0.85
Precision: 0.66

No filters — showing every case

64 of 64 cases (100%)

Directly-follows map

Discovered from the event log. The editable automation design is the last tab.

showing 12 of 12 activities · 100% of activity instances covered

Geometry is computed at build time, so nothing reflows when you filter. 8 of 48 directly-follows relations sit below the 0.20 noise threshold and are hidden; together they carry 1.1% of transitions.

Node fill 0–20%20–40%40–60%60–80%80–100% Happy path Loop back Self-loop

Five discrete steps. Edge thickness is a square-root scale on frequency, so the busiest edge is 8 px and the quietest 1 px.

Where the hours go

Edges ranked by total recoverable waiting time, not mean.

11.1% working 88.9% waiting · mean 61m 36s · p95 3.5 h · 55 cases affected · 11.1% of total cycle time
7.1% working 92.9% waiting · mean 47m 27s · p95 2.7 h · 57 cases affected · 8.9% of total cycle time
10.4% working 89.6% waiting · mean 42m 59s · p95 2.4 h · 58 cases affected · 8.3% of total cycle time
11.4% working 88.6% waiting · mean 50m 36s · p95 2.9 h · 48 cases affected · 8% of total cycle time
10.7% working 89.3% waiting · mean 40m 42s · p95 2.3 h · 53 cases affected · 7.2% of total cycle time
11.2% working 88.8% waiting · mean 29m 51s · p95 1.7 h · 59 cases affected · 5.8% of total cycle time

Variant explorer

One row per distinct end-to-end activity sequence, ranked by case count. Row 1 is the happy path and every other row is column-aligned to it, so deviations read as vertical discontinuities.

Top 12 variants cover 84.5% of cases.

Select exactly two variants to compare.

#	Variant	Sequence	Cases	% of cases	Cumulative	Median	p95	Steps	Δ vs happy path	Conformance	Compare
1	V-01 Happy path	PPEXWBDFMFBPOWCVSW	16	25%	25%	5.4 h	20.7 h	9	—	Conforming	Compare V-01
2	V-02	PPEXWBDFMFBPOWCVSW	5	7.8%	32.8%	5.9 h	2 d	8	-1 · 26m 36s	Deviating	Compare V-02
3	V-03	PPVCEXSRWBVCDFMFBPOWCVSW	5	7.8%	40.6%	7.6 h	2.4 d	11	+2 · 2.1 h	Deviating	Compare V-03
4	V-04	PPEXWBDFSRMFBPOWCVSW	5	7.8%	48.4%	8.2 h	34 h	10	+1 · 2.8 h	Deviating	Compare V-04
5	V-05	PP^×3EXFOWBDFMFBPOWCVSW	5	7.8%	56.2%	10.9 h	3.1 d	12	+3 · 5.5 h	Deviating	Compare V-05
6	V-06	SRPPEXWBDFBPMF^×3BPOWCVSW	5	7.8%	64%	11.6 h	2.2 d	13	+4 · 6.1 h	Deviating	Compare V-06
7	V-07	PPVCEXWBDFMFBPOWCVSW	5	7.8%	71.8%	7.9 h	2.6 d	10	+1 · 2.5 h	Deviating	Compare V-07
8	V-08	PPEXFOWBDFBPMF^×2BPOWCVFOSW	4	6.3%	78.1%	10 h	2.8 d	13	+4 · 4.5 h	Deviating	Compare V-08
9	V-09	PPEXDFWB^×2DFMFBPOWCVSW	1	1.6%	79.7%	7.8 h	2.1 d	11	+2 · 2.3 h	Conforming	Compare V-09
10	V-10	PPEXWBDFSRMFBP^×4OWCVSW	1	1.6%	81.3%	11.7 h	47.9 h	13	+4 · 6.2 h	Deviating	Compare V-10
11	V-11	EXPP^×2EXWB^×2DFMFBPOWCVFOSW	1	1.6%	82.9%	11.3 h	3.9 d	13	+4 · 5.9 h	Deviating	Compare V-11
12	V-12	PPEXWBDFMFBPOWCVSW	1	1.6%	84.5%	6.7 h	29 h	8	-1 · 74m 09s	Deviating	Compare V-12
—	Other variants (0) · 0% of cases	Activity sequence —	0	0%	100%	—	—	—	—	—

14 variants (63.6% of all variants) occur exactly once, together 21.9% of cases.

Variant distribution

Rank on a log scale against cases on a log scale, with cumulative coverage on the right axis.

Cases (log scale) Cumulative coverage (%) Variant rank (log scale) 10 variants cover 80% of cases

Variant comparison

Two variants on the same alignment columns. Colour says which side; hatching repeats it, so the diff survives greyscale.

Variant A

Variant B

A · V-01

Merged activity set

B · V-02

Merged activity set

Every alignment column, coloured by which side uses it.

In both Only in A Only in B In neither

List of changes

Side by side
Side by side	A	B	Δ

Attributes associated with each branch

These are associations measured on the log, not causes. Every rule prints the number of cases it was measured on.

Forecast scope `forecast_scope`

62 of 64 cases · 2.7% missing

Team32 · 50%
Region19 · 29.7%
Global11 · 17.2%

Rule statements

Ranked by lift × support. Each rule is a sentence you can read aloud.

When resource_count > 3 → the case takes “Flag an outlier” in 70.2% of cases (baseline 20.3%, lift 3.46×, n = 33).
70.2% confidence 20.3% baseline 3.46× lift n = 33
When region = DACH → the case takes “Send the summary to RevOps” in 92% of cases (baseline 31.3%, lift 2.94×, n = 16).
92% confidence 31.3% baseline 2.94× lift n = 16
When product_line = Enterprise AND resource_count > 3 → the case takes “Flag an outlier” in 76.7% of cases (baseline 20.3%, lift 3.78×, n = 8).
76.7% confidence 20.3% baseline 3.78× lift n = 8
When period_end = true AND forecast_scope = Region → the case takes “Send the summary to RevOps” in 89% of cases (baseline 31.3%, lift 2.84×, n = 10).
89% confidence 31.3% baseline 2.84× lift n = 10
When deal_band = > €100k → the case takes “Check the variance” in 38.9% of cases (baseline 18.8%, lift 2.07×, n = 10).
38.9% confidence 18.8% baseline 2.07× lift n = 10
When forecast_scope = Region AND deal_band = > €100k → the case takes “Check the variance” in 41% of cases (baseline 18.8%, lift 2.18×, n = 8).
41% confidence 18.8% baseline 2.18× lift n = 8

Decision point

Pick an exclusive choice in the map to see its branch shares and the attributes that discriminate between them.

Decision point

Branch

Wait for the report to build6 · 30%
Map the values to the forecast6 · 30%
Pull the pipeline export5 · 25%
Copy values between windows2 · 10%
Request export1 · 5%

Pick an exclusive choice in the map to see its branch shares and the attributes that discriminate between them.

Conformance against the reference model

Reference model v3, 3 Jul 2026

Fitness0.85

Precision0.66

Fitness and precision trade off; we report both rather than a single model-quality score.

Conforming cases — 17 (26.6%) Non-conforming — 47 (73.4%)

Deviations by type

A deviation is not necessarily an error — it is behaviour the reference model does not allow.

					Breaks conformance
Skip	22	34.4%	2m 41s	59m 02s	Breaks conformance
Activity retry	18	28.1%	3m 06s	55m 48s	—
Invalid activity	44	68.8%	73s	53m 32s	Breaks conformance
Loop back	11	17.2%	3m 32s	38m 52s	—
Exclusive-choice violation	5	7.8%	43s	3m 35s	Breaks conformance
Invalid start/end	5	7.8%	0s	0s	Breaks conformance

Conforming cases over the window

Conforming cases (%) · 16 Jun – 13 Jul 2026

Conforming cases (%)16 Jun – 13 Jul 2026

Rework and loops

Self-loops and loop-backs, with loop inflow, outflow and net gain.

Activity	Kind	Self-loops	Cases affected	Mean repeats	Loop in	Loop out	Net gain	Total waiting
Request export	Loop back	0	10	2×	10	9	+1	20.6 h
Wait for the report to build	Loop back	0	10	2×	10	7	+3	10.4 h
Map the values to the forecast	Loop back	0	9	2×	9	9	0	10.3 h
Wait for the report to build	Loop back	0	6	2×	6	6	0	16.6 h
Map the values to the forecast	Loop back	0	6	2×	6	5	+1	8.2 h
Map the values to the forecast	Self-loop	6	6	2×	6	5	+1	2.6 h
Switch application	Loop back	0	6	2×	6	5	+1	12.2 h
Pull the pipeline export	Self-loop	10	5	3×	10	9	+1	1.9 h

Rework cost €1,102–1,653 · 16 cases · 55 h Costed at the €25/h loaded rate used everywhere in this dashboard.

Cases

Showing 16 of a 40-case sample drawn from 64 cases, across the 22 variants listed on the Variants tab. The totals above are exact; this table is sampled.

Variant				Roles	Departments		Conformance
V-16	2026-07-13 08:19:32	22.4 h	9	Sales Ops Manager	sales	0	Deviating
V-02	2026-07-09 13:50:40	7.6 h	8	Treasury Analyst	sales	0	Deviating
V-10	2026-07-09 12:11:11	46.4 h	13	Sales Ops Manager	sales	3	Deviating
V-02	2026-07-09 11:05:05	11.5 h	8	Treasury Analyst	salesfinance	0	Deviating
V-18	2026-07-09 09:57:16	36.7 h	13	Treasury Analyst	sales	2	Deviating
V-02	2026-07-08 14:40:05	9.8 h	8	Treasury AnalystSales Ops Manager	sales	0	Deviating
V-04	2026-07-08 14:14:18	15.6 h	10	Treasury AnalystSales Ops Manager	salesfinance	0	Deviating
V-01	2026-07-08 13:42:40	7.7 h	9	Treasury Analyst	sales	0	Conforming
V-06	2026-07-08 08:42:42	8.1 h	13	Sales Ops ManagerTreasury Analyst	sales	3	Deviating
V-06	2026-07-07 11:56:08	16.2 h	13	Sales Ops ManagerTreasury Analyst	salesfinance	3	Deviating
V-02	2026-07-07 10:16:27	7 h	8	Sales Ops ManagerTreasury Analyst	sales	0	Deviating
V-20	2026-07-06 16:00:37	10.7 h	9	Treasury Analyst	salesfinance	0	Deviating
V-06	2026-07-06 13:43:10	22.3 h	13	Sales Ops Manager	salesfinance	3	Deviating
V-02	2026-07-05 14:59:17	4.3 h	8	Treasury AnalystSales Ops Manager	salesfinance	0	Deviating
V-02	2026-07-02 12:26:28	12.5 h	8	Treasury AnalystSales Ops Manager	salesfinance	0	Deviating
V-01	2026-07-02 11:10:29	12.7 h	9	Sales Ops ManagerTreasury Analyst	salesfinance	0	Conforming

16 of 40

Live 89% confidence

Automation design

The Map tab is what the event log shows. This is the automation you are designing from it.

CRM (web)ExcelOutlook

1.5h reclaimed / week across everyone who runs it

Case V-01 Conforming

—

· Process: Pipeline forecast roll-up · Correlation key forecast_ref

Total duration

Working Waiting Steps · Rework

Field	Value
`forecast_ref`	FCT-2026-01182
`account`	Kestrel Logistics GmbH
`amount_eur`	€46,647.31
`region`	DACH
`owner_role`	Sales Ops
`contact_phone`	+34 ••• ••• 477 · masked at capture (Phone number masked at capture)

Field	Value
`forecast_ref`	FCT-2026-84442
`account`	Havensmark Trading NV
`amount_eur`	€35,766.96
`region`	DACH
`owner_role`	Sales Ops
`contact_phone`	+34 ••• ••• 197 · masked at capture (Phone number masked at capture)

Field	Value
`forecast_ref`	FCT-2026-53241
`account`	Meridian Supplies SL
`amount_eur`	€5,926.61
`region`	Iberia
`owner_role`	Sales Ops
`contact_phone`	+34 ••• ••• 360 · masked at capture (Phone number masked at capture)