How to Give AI Reference Material Before Asking for a Draft
A beginner-safe AI workflow for give ai reference material before asking for a draft, with a copyable prompt, source boundaries, missing-information rules and line-by-line verification.
By the end: You will run a grounded AI task using real source material, verify every consequential claim, and keep a reusable prompt plus human-review process.
You will run a grounded AI task using real source material, verify every consequential claim, and keep a reusable prompt plus human-review process.
Key terms before you start
These definitions make the steps easier to follow and help distinguish controls, files and concepts that can look similar at first.
What you need before starting
- Access to ChatGPT
- The real source material required for the task
- Permission to use that material
- A person who can verify/approve consequential facts
Step-by-step tutorial
Every step is shown below. Work through them in order and use each checkpoint to confirm the result before moving on.
Open a new ChatGPT conversation
Start a new chat so unrelated earlier instructions do not accidentally shape the workflow.
A clean conversation makes the task/source boundary easier to audit.
Treat the claim as unsupported; open the source yourself and correct/remove it.
Collect the authoritative input first
Prepare the real the authoritative policy, manual, report or approved page copy you are allowed to use.
Do not ask the model to reconstruct private/current facts that should come from a document, database or person.
Strengthen the source-only/missing-information rule, delete unsupported content, and verify the revised output. Do not keep a plausible guess.
Define the output format
Ask for a draft that points back to source sections and specify headings/fields/order.
A defined structure makes comparison/review easier.
Restate the exact schema/headings and show a tiny structural example without adding fake factual values.
Run the prompt without asking for extra creativity
Send the request.
For factual extraction/rewrite, creativity is not the goal.
Restate the exact schema/headings and show a tiny structural example without adding fake factual values.
Check every number and date
Compare numbers, dates, prices, percentages and deadlines back to the source one by one.
These details are easy to alter accidentally and often consequential.
Treat the claim as unsupported; open the source yourself and correct/remove it.
Check every proper name and product/service name
Compare spelling and identity with the source.
A plausible wrong name is still wrong.
Strengthen the source-only/missing-information rule, delete unsupported content, and verify the revised output. Do not keep a plausible guess.
Use the current authoritative version
Check document date/version before upload.
An accurate summary of an obsolete policy is still operationally wrong.
Check every cited section
Open the source section and compare the draft sentence.
Citation formatting alone is not proof.
Treat the claim as unsupported; open the source yourself and correct/remove it.
Record reusable prompt only after it works
Save the prompt template plus required inputs and review checks.
A repeatable workflow includes validation, not just reusable wording.
Re-run the same verification after every material revision. Human review is not a one-time step.
Re-test when source/model/process changes
If the input format, policy, model or business process changes, run validation examples again.
A workflow proven on one version is not permanently proven.
Strengthen the source-only/missing-information rule, delete unsupported content, and verify the revised output. Do not keep a plausible guess.
If a factual sentence cannot be traced to the allowed source, remove it or mark the information missing.
Concrete examples
Copyable example
Read the attached POLICY first.
Then draft a 150-word customer explanation of cancellation terms.
Use only the POLICY.
Do not soften, extend or reinterpret deadlines.
After each paragraph cite the policy section heading used.
If the policy is ambiguous, ask a question instead of choosing an interpretation.Troubleshooting
Strengthen the source-only/missing-information rule, delete unsupported content, and verify the revised output. Do not keep a plausible guess.
Restate the exact schema/headings and show a tiny structural example without adding fake factual values.
Treat the claim as unsupported; open the source yourself and correct/remove it.
Re-run the same verification after every material revision. Human review is not a one-time step.
The process remains current.
Continue with these tutorials
Documentation and references
Use these primary and supporting sources to verify current controls, browser behavior and product-specific details.