Independent and not affiliated with the FDA, MHRA, ISPE, PDA, or any agency. Get the appgoutham@madhadi.com
madhadi.comData Integrity & GxP Quality
Browse all topics → Articles Templates & Procedures Learning paths GlossaryScenariosToolsRegulatory ReferencesLearning PathsTopics About Start here
Log Plug-and-play starting point AI & Automation

Log: AI-Assistance Disclosure and Human-Review Record

A plug-and-play log for recording generative-AI assistance in GxP quality records: what the model produced, the model and prompt version, the human review and edits, fact and number verification, and the accountable author, with a filled sample row.

Document type: Log

Read and copy the template below into your own quality system. It is a generic starting point for your own internal use, provided as is, with no warranty; see the Terms and License. Adopting it does not by itself create compliance.

This is a ready-to-use log for capturing that a generative-AI assistant helped produce a GxP quality record, who reviewed it, and what they verified. It makes AI use transparent and reconstructable, which is what keeps the practice defensible in an inspection. Where your validated quality system can capture these fields in its own audit trail, use that instead of a standalone log; this template defines the minimum field set either way. Replace every <<FILL: ...>> placeholder. A filled sample row follows. This content is educational and general; adapt it and verify it before use.

Purpose

To provide a traceable record that generative AI assisted a specific quality record, under what conditions it was generated, what a named human reviewed and changed, and that facts and numbers were verified against the source. The log is the evidence that AI use was disclosed, reviewed, and owned, rather than hidden.

Field definitions

FieldFormatRequiredWho entersWhen
Entry ID<<FILL: prefix>>-NNNNYesReviewerAt review
Date/timeISO 8601YesReviewerAt review
Linked record IDDeviation / CAPA / investigation / complaint IDYesReviewerAt review
WorkflowDeviation description / RCA narrative / CAPA draft / complaint-trend summaryYesReviewerAt review
Assistant name / instanceTextYesReviewerAt review
Model versionVendor build or version string; “not exposed” if unavailableYesReviewerAt review
Prompt / template versionInternal version IDYes where feasibleReviewerAt review
GroundingFacts supplied / retrieval corpus + version / open (open is not permitted for GxP content)YesReviewerAt review
What the model producedShort descriptionYesReviewerAt review
Facts verified against sourceYes / No / N/AYesReviewerAt review
Numbers verified or computed deterministicallyYes / No / N/AYesReviewerAt review
Edits made by reviewerShort description or “none”YesReviewerAt review
Quality decision made by toolMust be “None”YesReviewerAt review
Accountable authorNameYesReviewerAt review
QA oversight (where required)Name / datePer procedureQAAt oversight

Instructions

  1. Create one entry per AI-assisted record. If the same record was assisted more than once (for example a description then a CAPA draft), create an entry for each use.
  2. “Grounding” must never read “open” for GxP content; an open-prompt draft is not permitted by the parent SOP.
  3. “Quality decision made by tool” must always read “None.” If it does not, the use violated the permitted boundary; do not finalize the record and raise it to QA.
  4. Record the model version where the vendor exposes it. Where it does not, enter “not exposed” and note that a vendor model change is managed through change control instead.
  5. The accountable author is the human, never the tool.

Retention

Retain each entry for not less than <<FILL: retention period>>, aligned to the retention of the linked GxP record, per <<FILL: records retention schedule ID>>. The disclosure entry and the linked record together are the story of how the content was produced.

Acceptance criteria for a complete entry

  • Every required field is populated and the linked record ID resolves.
  • Facts and numbers are marked verified (or N/A with a reason), never left blank.
  • “Quality decision made by tool” reads “None.”
  • An accountable human author is named.

Filled sample row

The following shows one completed entry. The content is illustrative; replace it with your own.

FieldEntry
Entry IDAID-2026-0311
Date/time2026-06-08T14:50-04:00
Linked record IDDEV-2026-0417
WorkflowDeviation description
Assistant name / instanceContained quality assistant, prod instance
Model versionbuild 2026-06 (pinned)
Prompt / template versiondev-desc-tmpl v3
GroundingFacts supplied via structured intake; open-web knowledge disabled
What the model producedDraft description of a tablet-press stop with hopper-level alarm
Facts verified against sourceYes (equipment log, batch record)
Numbers verified or computed deterministicallyYes (stop duration corrected 20 to 22 min against equipment log)
Edits made by reviewerCorrected duration; confirmed segregation occurred; no invented facts
Quality decision made by toolNone
Accountable authorA. Patel
QA oversightR. Gomez, 2026-06-09

In this entry the model drafted the description, the reviewer corrected one number and confirmed the physical facts, and the log shows exactly what the model produced, what the human changed, and who owns the record. If an investigator asks how AI was used in this deviation, this single row answers it.

Common inspection findings this log prevents

  • AI in use in quality records with no disclosure, discovered rather than declared.
  • No way to show a human verified the facts and numbers in an AI-assisted record.
  • No record of which model version or prompt produced a draft, so behavior cannot be reconstructed after a vendor change.
  • A record where the tool, in effect, made a quality call that no field or reviewer flagged.

How to adapt this log

  1. Map these fields onto your validated quality system’s audit trail where it can hold them, and use a standalone log only for what the system cannot capture.
  2. Set your retention period to match the linked record’s retention.
  3. Add a QA-oversight cadence appropriate to the risk of the workflows you support.
  4. If you use retrieval-augmented generation, record the corpus name and version in the grounding field.
Use madhadi.com as an app Full screen, works offline, one tap from your home screen.