Bottleneck diagnosis
Find where cases actually wait using the log rather than the process diagram.
— Operations & Process
Computes activity volumes and profiles from an event log, then diagnoses bottlenecks, rework loops and variant paths with root-cause hypotheses and capacity gains.
1–2 weeks → ~15 minutes
For a full population, not a sample
No coding required
— USE CASES
Find where cases actually wait using the log rather than the process diagram.
Quantify rework loops and off-path variants that never appear in the documented process.
Attach a capacity gain to each bottleneck so remediation can be prioritised.
— HOW IT BEHAVES
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Every row of your table is processed on the same basis, however long the table is.
Ambiguities are settled with you up front, so the run does not quietly assume the wrong scope.
The pattern is visualised from the computed data, so the trend is legible at a glance.
Findings are written up as a document that reads like professional output rather than raw model text.
Detail rows are summarised into the grouped view without losing the underlying lines.
In operations & process work, process mining from event logs is one of those tasks that looks straightforward until you are three documents deep and the details stop agreeing with each other. In practice it shows up as bottleneck diagnosis: find where cases actually wait using the log rather than the process diagram. The value sits in the rigour, not the typing — yet the rigour is exactly what gets traded away when there is only 1–2 weeks of capacity for it.
Here the same job runs as a Skill. Your material goes in; computed activity volumes and log profile comes out, alongside bottlenecks, rework loops and variant paths with root-cause hypotheses. The criteria, ordering and review points that make the answer trustworthy are encoded in the Skill itself — which is the difference between a structured method and a prompt someone pastes in. Net effect: 1–2 weeks down to ~15 minutes, no drift between runs, and every conclusion traceable back to the evidence behind it.
Process mining from event logs exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
Automation opportunity map
Maps team or function activities to automation potential, computing addressable effort and bucketing opportunities into a prioritised roadmap.
Control failure → incident RCA pattern engine
Joins control test results to incident logs by process to show where control failures are actually producing incidents, grouped by systemic weakness with residual risk quantified.
Process diagnostic
Inventories every process step with its owner, system, effort and wait time, tests each against bottleneck, duplication, handoff and control-gap lenses, and returns a prioritised 30/60/90 improvement backlog.