All agent skills

Leading Deeper with AI / 07

Check whether the automation is helping

Compare preparation, review, corrections and upkeep before deciding whether to keep an automation.

Compare human effort and quality for comparable cases. Calculations stay separate from the AI drafted assessment. A person checks assumptions and decides whether to keep, revise or stop.Human effortPreparationReview + fixesKeepReviseStopBaselineAI workflowYou decideAI drafts assessment
AI generation or assessmentHuman input or judgment

Fictional example / AI draft

Workflow assessment | Five comparable drafts

Recurring human effort
Manual: 125 active person-minutes. Assisted: 45 active person-minutes including maintenance. Difference: 80 minutes before setup. [Supplied fictional effort records]
See the full example
Quality and unknowns
Equal acceptance requirements are assumed for the illustration, not independently validated evidence. Setup effort and monetary cost are unknown.
Recommendation
Revise the assessment: collect setup effort and real comparable case measurements before claiming an all-in benefit.
Next evidence
Have the workflow owner record active preparation, review, corrections and maintenance for the next comparable completed cases; retain failures and exclusions.
Give your agent this context

All examples use invented sources and results. They are illustrations, not reports from Jasmine’s workplace or measured outcomes.

Comparable work | Fictional week
Five completed drafts per approach, with the same acceptance requirements assumed. No failed or unfinished cases in this illustration. Effort is active person-minutes, not agent runtime or elapsed time.
Effort records | Invented measurements
Manual work: 25 minutes per draft including preparation and checks, with zero separate baseline maintenance explicitly assumed. Assisted work: 7 minutes per draft including preparation, review and corrections, plus 10 minutes of maintenance for the week.
Unknowns and request
Setup effort, monetary cost and use of attention are unknown. Equal quality is assumed for the example, not independently verified. Return a decision draft and one next measurement; make no workflow or staffing changes.
How this example works
  1. 01 / You

    Supply a fair comparison

    Name the completed task, period and quality requirements. Provide human effort for both approaches and label assumptions, estimates and missing values.

  2. 02 / AI

    Prepare a decision draft

    Explain what the effort comparison can establish, showing a traceable calculation. Separate the recurring difference from unknown setup, cost, quality and impact.

  3. 03 / You

    Choose the next measurement

    Check comparability and arithmetic, then decide whether the evidence supports keeping, revising or stopping. Unknown effort stays unknown rather than becoming zero.

You check before using the result

  • Were the cases comparable, and did you count all human effort once, including unsuccessful attempts in your real comparison?
  • Do the known results support the decision, or do you first need setup, quality or other missing evidence?

Use the AI tool approved for your work with supplied material. Wording and layout will vary by model; look for the evidence, uncertainty and review decisions shown here. Connections and recurring runs depend on your setup.

What the output should include across models
  • Comparable cases, units and a traceable calculation
  • Assumptions, missing evidence and setup treatment
  • Quality, monetary cost and use of attention kept distinct from effort
  • A reviewed keep, revise or stop proposal and one next measurement
See the full fictional example and its limits

Fictional worked example

Count the review and maintenance.

Five comparable drafts in one invented week. These numbers illustrate the calculation and do not describe my team.

Manual effort
125 min
5 drafts × 25 human minutes
Assisted human effort
45 min
5 × 7 minutes, plus 10 minutes of maintenance
Recurring difference
80 min
Before setup. Quality requirements assumed equal.

Setup effort and monetary cost are unknown. This comparison does not establish an all-in saving or a customer outcome.

Calculation and assumptions

25 - (7 + 10 / 5) = 16 active person-minutes per comparable case before setup; 16 × 5 = 80 per week before setup.

Have the workflow owner record active preparation, review, corrections and maintenance for the next comparable completed cases; retain failures and exclusions.

Read the example JSON
Use this agent skill ↑
Connect your sources (optional)
01

Start here

Bring your context.

What you’ll need

  • Workflow step, intended outcome, owner, people involved and protected judgment or development
  • Definition of a comparable completed case, acceptance checks and reporting period
  • Manual baseline and assisted human effort, including remaining preparation, review, correction, interventions and handoffs
  • Recurring maintenance and one-time setup effort, with case counts or an explicit amortization horizon where known
  • Known tool costs, quality findings and evidence of what available attention was used for
  • Source, date, unit, coverage and measured or estimated status for each input; unknowns may remain unknown

MCP & tool setup

No MCP is needed with supplied measurements and workflow context. Optional scoped read access can help establish case counts, dates and effort evidence.

Read optional effort and case evidencePossible toolsReportsCSVIssues

Needed when: Only when approved measurements or records must be retrieved rather than supplied.

MCP or tool examples
Approved local CSV, spreadsheet or timing-log tools · An approved reporting or issue-tracker connector or MCP · An approved calendar connector or export for context only
Tools must support
Read the selected timing measures, completed-case records and quality findings; Check definitions, case counts, dates and coverage; Record provenance and distinguish active effort from calendar or system elapsed time
Access needed
Read access to the named records and reporting window. Calendar duration or task state alone is not an effort measure; no edits, messaging, administration or tracking setup is required.
Without that connection
Supply selected timing notes, case outcomes and known overhead in a small table, or leave unknowns explicit and plan the next measurement.

No live connection? Provide an approved aggregate table, timing notes or excerpts with dates, units, scope and provenance. Keep missing values unknown and propose one small manual measurement.

Use the full prompt instead
02

Copy. Adapt. Try.

Make it your own.

01HumanDefine the comparison

Choose comparable cases and the result they need to meet.

02Count human effort

Include preparation, review, correction and relevant overhead.

03AIHumanCheck the result

AI can draft the assessment. You check quality, assumptions and the use of attention.

04HumanChoose the next step

Keep, revise or stop based on evidence. Measure what is still unknown.

Replace the bracketed inputs. Use context you’re authorized to share.

Download .txt

Copy the template or select the text directly.

Using an agent? Other formats

New companion exercise for the talk resources; not a historical result or the original internal prompt.

Review checks
03

Keep your judgment in the loop

Review the result.

01

Are the cases and quality requirements comparable, and are every input, exclusion and estimate traceable?

02

Does human effort include preparation, review, correction and overhead exactly once, with unknown setup kept distinct?

03

Does the conclusion separate effort, cost, quality and actual use of attention while protecting judgment and person-relative growth?

04

Is the proposed keep, revise or stop decision proportionate to the evidence?

What evidence should you look for?
  • Use active human effort for comparable completed cases; retain unsuccessful attempts, rework and case-mix or coverage limits.
  • Check maintenance allocation and setup treatment; a before-setup comparison does not establish an all-in benefit.
  • Compare quality and known costs for the same scope. Record what available attention supported without assuming a customer, growth or wellbeing result.
  • If evidence is missing, take one small prospective measurement rather than deriving hours from messages, assistance rates or calendar time.
How this connects to the talk

A new measurement companion

Check the value in your own work.

Try it in your practice project

Use a repeatable Softball IQ task, such as a debrief or content review, as a proposed measurement exercise.

Apply the comparison at work

Apply the same comparison to a workplace workflow, including preparation, review, correction and the outcome people need.

Your judgmentYou decide whether the evidence supports keeping, changing or stopping the automation, and where any released capacity should go.

Value to checkCompare similar tasks and periods, count all human effort, record quality tradeoffs and label estimates separately from observed results.