We can’t keep up with content.

The plan

Repurpose one useful source into a week of drafts. This is a manual, AI-assisted workflow: you copy approved inputs into Claude, check the output, and move the accepted result into your existing process. Start with the synthetic example below.

You need access to Claude and your team’s approved document or spreadsheet workspace. Use only data your business permits in those services. Tool plans and limits vary; this walkthrough does not require an API connection.

1. Prepare a small, useful input

Choose one approved FAQ, article, or product update. Put its facts, your audience, tone, and one permitted call to action in a short document. Create a Google Sheet with channel, source_fact, draft, reviewer, status. Start with a single source, not your entire site.

Use this fictional sample for your first run:

SOURCE F1: Our inventory audit identifies discrepancies between stock records and a physical count.
SOURCE F2: The audit ends with a discrepancy report for the operations team.
AUDIENCE: Small retailers.
TONE: Direct, useful, no hype.
CTA: Ask us what an audit covers.

2. Give Claude a precise job

Open a new chat at claude.ai. Paste the prompt below, then paste the sample after it under a heading called INPUT. For a PDF, attach the sample file to the chat instead. Keep the source and instructions clearly separated.

Create three distinct drafts: a LinkedIn post under 100 words, an email paragraph under 80 words, and a three-question FAQ. Cite F1 or F2 beside each factual claim. Use only the source. No invented savings, testimonials, product capabilities, or urgency. End with the supplied CTA where appropriate. Return channel, source_fact and draft.

INPUT:
[Paste the sample or your approved source here.]

Read the response before continuing. If required columns are missing, ask: “Return the same result using every requested column. Mark unsupported fields UNKNOWN.” Do not fill gaps by asking the model to guess.

3. Check against the expected result

A LinkedIn draft explains why a discrepancy report is useful; an email introduces the audit; the FAQ answers what is checked and what the team receives. None claims a percentage saving.

4. Put the checked result to work

Paste the drafts into your content sheet. Review each claim against its source ID. Remove source labels from the final public copy only after checking. Adapt the voice and schedule approved drafts in your existing publishing tool.

Keep a status of draft, needs clarification, approved, or completed beside each item. A draft is not a completed action. If the service is unavailable, use the original source and your normal manual process.

5. Test the awkward cases

Try a source with no outcome data and a prompt request for a customer quote. Reject invented numbers or testimonials. Compare editing time with writing three drafts from scratch; a large edit burden means the source or prompt needs work.

Run the same cases again after changing the prompt or source. Keep the input, output, correction, and reviewer decision together. Expand only when someone can reliably check the results.

If the result is off

Narrow the input to one record and recheck the source. For missing facts, ask the process owner. For an unsupported statement, remove it and add an explicit constraint to the prompt. If the same failure repeats, do the task manually until the source or instructions are fixed.

Scope: This is an original illustrative recipe with synthetic data, adapted from the field guides below. It is not a live-tested integration or a claim of time saved. Claude’s file-upload documentation explains supported attachments; the copy-and-paste path does not need file uploads.