Keep a reviewable history of assistant decisions
Record the context, reasoning summaries, artifacts, and unresolved factual questions from important assistant work. Use the record to investigate mistakes and preserve reviewed lessons for later tasks.
How this works
Record the context, reasoning summaries, artifacts, and unresolved factual questions from important assistant work. Use the record to investigate mistakes and preserve reviewed lessons for later tasks.
Keep a decision record that can be investigated later without pretending it is a truth ledger. Capture concise reasons, evidence and artifacts, then distinguish unresolved claims from corrected conclusions and reviewed lessons that may be reused.
Before you start
Defined operating scope
Important assistant work produces decisions and artifacts that need later investigation and correction.
Required source material
Obtain Assistant session records; Referenced documents and artifacts; Human corrections. If connectors are unavailable, use authorized files with the same fields.
Decision and exception rules
An artifact link no longer resolves. Mark the evidence unavailable and request a recoverable version rather than trusting the summary alone.
Prepare the inputs
- session_scope
- Required
Selected assistant session and task
Limit logging to relevant authorized material.
- decision_records
- Required
Choices and concise rationale summaries
Do not require hidden chain-of-thought.
- artifact_references
- Required
Files and source versions
Preserve stable references and availability.
- human_corrections
- Required
Reviewed correction and evidence
Record reviewer, date and applicability limits.
Implementation, step by step
Establish the working record
- Confirm the selected records, effective versions and responsible owner.
- Check session_scope, decision_records, artifact_references, human_corrections before beginning. Record the source version and the selected scope; an unavailable value stays unknown rather than becoming an inferred fact.
Checkpoint: The input record identifies the selected session_scope and any missing required fields.
Capture the decisions, source context, and output artifacts from the session
- Capture the key decisions, concise reasons and artifacts needed to understand the completed task.
- Verify decision references point to the actual artifact and version.
Checkpoint: A saved intermediate result for: Capture the decisions, source context, and output artifacts from the session.
Mark claims that still need factual verification
- Identify factual claims that lack verification and keep them separate from confirmed observations.
- Check reused lessons retain reviewer status, scope and known exceptions.
Checkpoint: A saved intermediate result for: Mark claims that still need factual verification.
Review incorrect conclusions and record the correction with its evidence
- When a conclusion is challenged, record the original, correction and evidence without erasing the history.
- Verify decision references point to the actual artifact and version.
Checkpoint: A saved intermediate result for: Review incorrect conclusions and record the correction with its evidence.
Reuse only the reviewed lessons when a similar task arises
- Reuse only reviewed lessons in a similar context, checking their scope and freshness before turning them into a future rule.
- Check reused lessons retain reviewer status, scope and known exceptions.
Checkpoint: A saved intermediate result for: Reuse only the reviewed lessons when a similar task arises.
Package the result and unresolved work
- A person verifies the record and any rule derived from it. A decision log helps investigation; it is not a truth detector and does not prevent future mistakes.
- Record concise evidence-backed rationale, not hidden internal reasoning.
Checkpoint: A searchable decision history with unresolved questions and reviewed lessons. Unresolved items remain visible in the review record.
Decisions along the way
An artifact link no longer resolves.
Mark the evidence unavailable and request a recoverable version rather than trusting the summary alone.
A correction applies only to one project.
Store that scope and do not promote it into a universal instruction.
A claimed lesson has not been reviewed.
Keep it provisional and exclude it from automatically reused guidance.
What you will produce
reviewable-ai-decision-history-result.json
JSONA searchable decision history with unresolved questions and reviewed lessons. Label proposed and completed states separately.
Include: decision_id · context · rationale_summary · artifact_references · verification_state · correction · reviewed_lesson · status · evidence_reference · review_note
reviewable-ai-decision-history-review.md
MarkdownKeep the evidence and unresolved decisions needed to apply this result, including exceptions involving human_corrections.
Include: source_reference · question · owner · next_action
Check the result
- Verify decision references point to the actual artifact and version.
- Check reused lessons retain reviewer status, scope and known exceptions.
- Inspect session_scope and decision_records in both the original and output; confirm that record identity and interpretation survived the transformation.
- A person verifies the record and any rule derived from it. A decision log helps investigation; it is not a truth detector and does not prevent future mistakes.
When something goes wrong
An artifact link no longer resolves.
Mark the evidence unavailable and request a recoverable version rather than trusting the summary alone. Retain the affected evidence and recovery status.
A correction applies only to one project.
Store that scope and do not promote it into a universal instruction. Retain the affected evidence and recovery status.
A claimed lesson has not been reviewed.
Keep it provisional and exclude it from automatically reused guidance. Retain the affected evidence and recovery status.
A worked example
SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT
Request
Keep a reviewable history of assistant decisions for the following bounded example; prepare the result for review.
Inputs
Synthetic example: Session S-4 assumed a report used net revenue. Reviewer shows the source defines gross revenue; the correction applies to report R-2 only.
Expected result
Synthetic expected result: Log the original assumption, source-backed correction and R-2 scope. Future tasks may reuse the lesson to inspect definitions, not assume all reports use gross revenue.
Run a small pilot
Start small
Trial a representative batch containing the ordinary case and the exception demonstrated above.
Record the baseline
Record current preparation time, review effort and correction types for the same records.
Agree success criteria
Agree acceptable review and error limits; measure decisions traceable to artifacts; unresolved claims and repeat errors after reviewed corrections.
Stop or revise
A claimed lesson has not been reviewed. Pause affected records and apply this recovery: Keep it provisional and exclude it from automatically reused guidance.
Keep the scope clear
- Record concise evidence-backed rationale, not hidden internal reasoning.
- A log supports investigation; it does not prove truth or prevent future errors.
Check before using
A person verifies the record and any rule derived from it. A decision log helps investigation; it is not a truth detector and does not prevent future mistakes.
Business activities
- Maintain shared company knowledge
- Operate and improve AI workflows
FROM A RECIPE TO YOUR WORKFLOW
Bring the company context together.
This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.
For this recipe: Assistant session records · Referenced documents and artifacts · Human corrections
Start with one recurring task, agree which sources to use, and review the first result with your team.
Discuss this workflow