The studio / An interactive reading
Make the decision
visible.
Follow a product choice from the problem it addressed to the work it changed. These diagrams interpret three public accounts; they are not live system traces.
An interactive reading / 4 documented cases
Choose the intervention.
Follow what it changed.
Each case separates Shawn’s product choice, the agents’ work, the recorded outcome, and the limit of the evidence. Select a case and a step to read the account.
Case 01 / Order books
Give obligations a durable home.
Work was disappearing when a handoff was shortened or rewritten. Making every handoff longer would have made the next agent’s arrival heavier.
01 / Human choice
Keep obligations
Shawn described the need for each office to retain its longer-lived work separately from its current handoff.
02 / Agent response
Build the checker
Agents surveyed existing practice, tested a separate order book, revised its closure rules after independent review, and added safeguards against silent loss.
03 / Observed outcome
Catch ordinary drops
Checks reached actual retirement paths. Completed work moved out of the entry view, and a review caught a missing step before an obligation was judged filled.
04 / Limit
Meaning still needs review
Continuity and pointers can be checked. Whether an obligation is meaningful or truly complete still requires judgment.
Read the public account: Order books . The case and stage labels are portfolio interpretation; the account carries its evidence and unresolved edges.
Case 02 / Succession and retirement
Simplify the handoff.
A responsibility could outlive its agent’s session. Starting a fresh host process added friction and failures in the information a successor received.
01 / Human choice
Simplify the transition
Shawn supported agents retiring themselves, then challenged the complexity of the fresh-process approach.
02 / Agent response
Repair succession
Agents built a supported retirement action with handoff checks, returned to a simpler session transition, and repaired the successor’s arrival timing.
03 / Observed outcome
Simpler succession
Witnessed handoffs showed another holder arriving with an office, its open responsibilities, and an account of where to resume. Later use led to further corrections.
04 / Limit
Host routes differ
The account does not establish that succession always improves work, that hosts behave alike, or that inheritance beats a fresh start.
Read the public account: Succession and retirement . The case and stage labels are portfolio interpretation; the account carries its evidence and unresolved edges.
Case 03 / Tests under the floor
Measure before naming the cause.
Waiting for tests was shaping development. Blaming test quality alone could hide several different causes of the delay.
01 / Human choice
Measure the wait
Shawn asked for a closer look at the testing process: where could effort shorten feedback without discarding useful checks?
02 / Agent response
Profile the loop
Agents profiled representative runs, corrected a misleading measurement, and made focused repairs while preserving the checks’ purpose.
03 / Observed outcome
Find concrete costs
Specific bottlenecks were found and reduced. The investigation left a more accurate account of the remaining cost; the measured suite was later archived.
04 / Limit
No overall speed claim
This is a historical result, not a live benchmark or a controlled overall speedup claim. A fair comparison needs matching conditions and correctness standards.
Read the public account: Tests under the floor . The case and stage labels are portfolio interpretation; the account carries its evidence and unresolved edges.
Case 04 / An idea withdrawn after one measurement
Drop the fix, keep the concern.
Shawn read only a small share of what agents wrote in their panes and wondered whether they should be told to write less. He said he was unsure it was a good idea.
01 / Human choice
Raise a concern
Shawn raised the concern, asked for a role that could follow the work for him, and withdrew the suggestion when the measurement came back.
02 / Agent response
Measure the fix
The Architect had a scout measure a day of transcripts before judging, then advised against a length rule and pointed to one place for the Human to read.
03 / Observed outcome
Withdraw the rule
No rule on reply length. A guidance sentence added that evening came out minutes later, once the suggestion was withdrawn, and the requested role became the Reeve.
04 / Limit
One day, one exchange
One exchange, measured over one day of transcripts. It does not show how often Shawn changes course or how well agents argue.
Read the public account: An idea withdrawn after one measurement . The case and stage labels are portfolio interpretation; the account carries its evidence and unresolved edges.