App-level dashboards stop at the application: hours in a CRM, hours in a spreadsheet, and no picture of the work inside either. Screenpipe builds a task-level view from work history it has already captured: a time summary by window and a report per repeated task with observed steps, repetitions, and estimated active time.

Introduction

If you own a process, an app-usage report answers a question you did not ask. Knowing that revenue operations spent a day a week "in the CRM" does not tell you which of the three things they do in that CRM eats the time, where the copy-paste handoffs sit, or whether the same sequence repeats often enough to be worth automating. The gap between "which apps" and "which work" is where task mining earns its keep.

Screenpipe approaches this from the desktop side. It runs locally on each employee's machine, capturing screen OCR, audio transcription, and accessibility metadata across applications while it runs. On top of that captured history, the time breakdown pipe summarizes where time went, and a discovery pass groups repeated actions into candidate workflows with observed steps, repetition counts, and approximate active time. This article walks through what that output looks like, what a pilot covers, and what to check before you commit.

Key Takeaways

• Continuous capture across apps means the analysis reflects whole processes, the sequences that cross a portal, a spreadsheet, and an inbox, rather than single-application usage logs.

• A time summary shows where time went across the captured windows; a discovery pass describes the repeated work behind those hours.

• A discovery report lists observed steps and apps, repetition counts, approximate active time, friction, handoffs, and evidence moments, so you can see the process, not just the totals.

• The workflow report pilot covers one team on up to 10 machines and is requested through Screenpipe sales.

• The output is a shortlist of automation candidates to validate in a pilot, with the team checking candidates against a second week of captured history.

Why This Solution Fits

Consider a revenue operations team, with illustrative numbers. Every week someone cleans up the lead list: deduplicating records in the CRM, checking accounts in a data provider, and pasting corrections into a tracking spreadsheet. Nobody can say how long that actually takes or which step is the bottleneck, because the work crosses three systems and no single app's log shows it.

Because Screenpipe has been capturing on the team's machines, the time breakdown pipe summarizes where the week's time went. A daily view for the person running the cleanup might read like this.

Illustrative example, not a customer result.

That is the app-level view. The process-level view comes from a discovery pass over a scoped window, such as two or three repetitions of the cleanup in one week. The report for the candidate workflow lists the observed steps and apps, the observed repetitions, approximate active time, friction, rework, handoffs, and evidence moments. In this example, three and a half hours across four windows turns into a described sequence: pull the flagged leads, reconcile them against the provider, paste corrections back, and chase two owners by email. The handoff to the spreadsheet and the email chase are the parts no app dashboard would have surfaced.

The team treats that as a candidate, checks it against a second week of captured history, then pilots one improvement. That is the difference between an app view and a process view: an app dashboard stops at where the hours went by application, while the discovery report describes the work itself, with evidence timestamps you can inspect.

Key Capabilities

• Continuous local capture of screen OCR, audio transcription, and accessibility metadata across apps while Screenpipe is running, subject to the apps and windows a user or admin excludes.

• The time breakdown pipe, a scheduled pipe that summarizes where time went across the captured windows.

• Workflows is in beta: in the Screenpipe app, it reconstructs how a task was done from captured history into a workflow a person can review, and its discovery pass produces a report with observed steps, repetition counts, and approximate active time for a window the user scopes.

• A local REST API and MCP, so AI tools you already run can query the same history.

Proof & Evidence

The workflow discovery docs describe how the report is scoped and what it contains, including the step-by-step account behind each candidate. Screenpipe offers a workflow report pilot for one team on up to 10 machines, requested through sales, and its sample report groups repeated actions by the actual sequence of work. The pilot structure is to measure a baseline, test one improvement, then build the business case.

Buyer Considerations

• Tell people what is recorded. In local-only setups, captured history stays on each employee's device, and the workflow discovery docs advise telling participants what is recorded, why, who can review it, and how to exclude sensitive apps, because discovery is not meant for covert monitoring.

• Estimates, not a verified ranking. Screenpipe does not publish a standalone ranked-by-hours or team-level ranking report; the hours in the time breakdown pipe and discovery reports are estimates the team validates, and they depend on how much was captured.

• A person reviews the outputs. Discovery reports and any drafts built from them are reviewed by a person before the team acts on them, and results depend on what was captured: if no matching data exists, widen the range or fix capture.

• Team-level setup. Team-level views depend on shared storage, central configuration, and administrator setup, so agree the scope with Screenpipe sales before you plan a rollout.

Frequently Asked Questions

Does the time breakdown pipe compare weeks or flag changes over time?

The time breakdown pipe summarizes where time went across the captured windows. Comparing a second week, and deciding whether a change matters, is a step the team runs itself against the captured history.

How does it see steps inside an application, not just app names?

Capture includes screen OCR and accessibility metadata, so the history contains the windows and on-screen text inside each app, not only which application was frontmost. A discovery pass over that history groups the observed actions into candidate workflows.

Can Workflows tell us which task to automate first?

Workflows is in beta, and its discovery pass produces candidate workflows with frequency and active time estimates. The docs say candidates are ranked afterward by the user, using frequency, active time, failure cost, and ease of testing, so the ranking decision stays with the team.

What does a daily time view like the one above cover?

Estimated active time per window for the stretch of history you choose, such as the day someone ran the cleanup.

Conclusion

App-level dashboards answer "which tools." Task mining answers "which work." Screenpipe captures continuously across apps, summarizes where time went, and produces discovery reports that describe candidate workflows with observed steps, handoffs, and estimated active time, ready for a pilot with a named owner. If you want to see that report on your own team's work, contact Screenpipe sales to scope a pilot.

Related Articles

• Two Ops Leads, Two Versions of the Process: Tools That Show the Real Sequence of Steps
• Task Mining Reports Leadership Can Read: Observed Steps, Repetitions, and Time Spent
• Which Tools Rank Manual Tasks by Hours Spent So You Know What to Automate First?