Compare · Optional exploration
Vary human work in progress
Keep the same worker limit while changing how many unfinished changes enter the workflow. Plan a bounded comparison.
Think it through with your agent
Give your agent this URL. It contains the scenario and guidance to ask one question at a time. Start with your own prediction or explanation, then check it against the book.
Use with your task. Compare one agent with the fleet. Keep discoveries in your existing evidence or learning notes.
Follow the argument. Agent concurrency and human work in progress.
Read the exercise
Scenario#
Use this extension when the fleet trace suggests that waiting or competing review requests limit the workflow. Keep its findings in the existing fleet evidence.
Investigate#
- Choose three small changes that can each be accepted separately. Freeze their briefs, contracts, acceptance checks, and starting revision; use fresh copies for both trials with the same model, tools, reviewer, and aggregate resource budget.
- Compare admitting one unfinished change at a time with admitting up to three. Both conditions permit at most two executing agents, with the same delegation and integration rules. Before running either, predict when overlapping work could reduce waiting and when competing requests could increase review or correction effort.
- Record change start and acceptance or abandonment times, actual agent concurrency, unfinished changes, review waiting, interruptions, active human review and correction time, and total cost. Count accepted changes over the full trial window and preserve failed or abandoned attempts in the effort and cost records.
- Explain whether the traces support your prediction. A shared worker limit does not guarantee equal observed concurrency; use the trace to show which workers were active or waiting. Would the evidence support changing admission, worker capacity, or the feedback interface? Keep a faster model or a different interface as a separate intervention.
One pair is a workflow diagnostic: task order, practice, and execution variation can explain a difference. Report unfinished work at the cutoff and avoid treating a quieter workflow or a larger completion count as proof of better overall performance.
Show worked reasoning
Admitting one unfinished change and admitting three are different work-in-progress policies even when both allow at most two executing agents. The worker limit is a ceiling, not evidence that both conditions actually use two workers throughout. Overlapping work may use otherwise idle time, while competing review requests may add waiting, interruption, or correction effort. The traces must decide which occurred; no result is supplied by this protocol.
Compare accepted changes over the full trial window, actual concurrency, human effort, review waiting, and all-attempt cost, retaining unfinished or abandoned work. One pair is a diagnostic rather than a causal estimate: task order, practice, and execution variation can explain a difference. Changing the model or feedback interface is another intervention that needs its own comparison.
This is optional, ungraded exploration. The course brief defines the required work.