Before you paste anything

AI workflow preflight.

Define the evidence, unknowns, human gate, and stop conditions while planning a controlled AI workflow test with synthetic or public material.

This planning worksheet combines lessons from two published synthetic tests with this experiment's operating boundaries. It is not a safety certification, approval, or evidence that any workflow is ready to automate.

Seven fields

Make the test falsifiable before the output looks persuasive.

  1. 01

    Narrow job to test

    Name one bounded input-to-output task. List any actions the AI must not take.

    Test 001 boundary
  2. 02

    Approved source material

    List the exact documents or facts the output may use. Everything else is outside the test.

    Test 001 boundary
  3. 03

    Facts AI must never infer

    Write the owners, dates, prices, capabilities, permissions, or decisions that cannot be filled silently.

    Tests 001–002 inference boundary
  4. 04

    Missing-information label

    Choose one visible label, such as Not stated or Needs clarification, for every material gap.

    Test 002 rule
  5. 05

    Required source trace

    Require a quote, source ID, or exact field for every material claim in the output.

    Test 001 evidence
  6. 06

    Human decision boundary

    Name the reviewer and what they must verify. AI output is advisory only; it may not itself change a record, purchase, schedule, or external message.

    Tests 001–002
  7. 07

    Stop conditions

    Stop for confidential data, a high-stakes decision, an unapproved tool, or any missing permission.

    Experiment operating boundary
Why these fields exist

Two tests, two different failure boundaries.

Test 001 · synthetic

Missing owners and dates stayed visible.

The action-register run retained source quotes and surfaced unresolved owners and relative dates. Its rubric was formalized after output generation, and Codex evaluated the run. This is one preserved, self-evaluated run—not independent multi-run validation.

Inspect Test 001 evidence →
Test 002 · synthetic

Vague access language became a false capability.

Two of three runs silently upgraded “editor access” into confirmed text-and-photo editing. Trials 2 and 3 scored 75 and hard-failed; the precommitted rule therefore set the verdict to Reject for this workflow, even though Trial 1 scored 100. The test did not approve a vendor or interpret a contract.

Inspect Test 002 evidence →
Permanent boundary

A completed worksheet does not authorize a test or operational use.

Do not use this experiment for legal, medical, financial, personnel, safety-critical, or confidential-customer decisions. Use only synthetic or public material. This page has no form or upload for business material; a successful copy may emit the event disclosed above. Do not paste private material into this site or treat the worksheet as permission to use it elsewhere.