Protocol
Replay the decision without repeating the damage
A saved checkpoint is a place to restart an experiment. It is not permission to repeat the original payment, email or database write.
Before you use it
- Use when
- An agent failed late in a long run and a full rerun is expensive, slow or unlikely to recreate the same decision.
Keep this limit in mind
- A checkpoint is only as good as the state it captures. External systems, time and hidden side effects can still prevent an exact reproduction.
Current editorial reading
Define what runs again
Choose a checkpoint before the failed decision. Record the one change you want to test and which earlier results will be reused. Before starting, identify every later tool that can change an external system. Replace those effects with recorded responses or an isolated test service unless a live action is separately authorized.
Compare decisions in a safe test
For an agent that closed the wrong support ticket, restore the relevant state and change the routing rule. Capture the proposed closure in a test system rather than closing another live ticket. Compare the decision and final test state with the original. Missing files, changed services or unrecorded state can still break the comparison.
Take it with you
Before replay, list the calls that will run live and show where their effects will go. If you cannot account for a consequential write, stop and isolate it first.
Sources and evidence (2)
What we checked
The conference demonstration reuses saved checkpoints before a changed step, then runs the remaining execution under the intervention.
Selected timestamped transcript read on 2026-10-04, especially 5:03–7:35. This supports the demonstrated comparison pattern, not a universal checkpoint contract or a verified deployment.
Your Agents Need a Save Button · Transcript 5:03–7:35; chapter Change one part of the execution
Kitaru documentation describes replaying tool calls from recorded responses rather than repeating their real effects.
Selected README passage read on 2026-10-04. This is the current product description, not a test of the older conference version or this repository.
Kitaru: replay-based evaluation · README, Why, bullet Replay re-executes your code
The documented protection depends on substituting recorded tool responses; it does not establish that an arbitrary replay harness isolates every external write.
The call inventory and stop rule are editorial safety checks derived from the documented mechanism. Neither runtime behavior nor external services were executed in this review.
Kitaru: replay-based evaluation · README, Why; Self-hosted, by design
Editorial sources (2)
Save and practise this idea
My learning
Read. Recall. Repeat.
Save this idea and return to it on any device.
Keep exploring
Connected ideas
You are readingReplay the decision without repeating the damage
Original edition evidence and sources
These records belong to the original released edition. The current editorial reading has its own evidence above; neither set silently replaces the other.
A checkpointed agent run can be replayed from an intermediate state while changing one model or tool decision, which can make interventions easier to compare than full reruns.
Replay quality depends on what state the checkpoint actually captures; hidden external state can still make the reproduced execution differ from production.
Your Agents Need a Save Button · 2:03-10:54, production checkpoints, change one execution part and apply an intervention across a cohort
All sources (1)
Original edition, downloads and provenance
The reading above is editorial version 1.0.0, bound to this exact source edition. The original data and saved downloads retain that edition and the separate editorial layer. They may contain earlier wording; use the current reading above when interpreting it.
Version 0.1.0
No review details are supplied for this edition.
Read the original edition and overlay as JSON · Release details