Author: AILesson7 min setupTested with:ChatGPTReviewed: 2026-08-28
Quick answer
Write a platform-fit post whose facts, examples, and uncertainty remain traceable to supplied sources. Provide: Source material, Post brief, Accuracy and publishing rules. Expected result: A publishable draft, claim-to-source ledger, unresolved questions, and final verification checklist.
1
Add your context
Your text stays in this browser. AILesson Prompts does not send it to a model or server.
2
Your prompt
Unfilled fields remain visible as placeholders, so you can still copy and edit the prompt
Draft a social post using only the supplied sources and brief.
Sources, dates, authors, locators, permissions, facts, quotes, and limits:
[source]
Platform, audience, goal, angle, tone, length, CTA, and voice:
[brief]
Citation, prohibited claims, disclosure, privacy, brand, legal, and date rules:
[rules]
First extract usable facts, interpretations, examples, and exact quotations; mark permissions and limitations. Draft a platform-native post with one clear idea, an accurate opening, useful context, and a proportionate CTA. Preserve qualifiers, denominators, sample scope, dates, uncertainty, and correlation-versus-causation boundaries. Never invent statistics, trends, people, experience, quotes, links, outcomes, urgency, or consensus. Do not write in first-person experience unless supplied and authorized. Distinguish source conclusions from your synthesis. Then provide a claim-to-source ledger with exact post excerpt and locator, plus unresolved items that must be removed or confirmed. Check length, link status, attribution, privacy, disclosure, accessibility, and whether the opening overstates the body.
Private by defaultPrompt assembly happens locally in your browser. Avoid placing confidential information into any AI service unless your organization allows it.
From input to outcome
A worked example
See how concrete context turns this recipe into a usable result
Actual input
Source material
Internal survey report, Aug 20 2026, section 'Handoffs': 48 operations managers recruited from our webinar list; 29 selected unclear ownership among their top three handoff problems. Multiple selections allowed. The report does not represent all operations managers. Approved guide URL: https://example.com/handoff-guide. No participant quotes approved.
Post brief
LinkedIn, operations leads at small companies, help readers notice ownership ambiguity and download the guide. Calm, practical, 700-900 characters, no first-person story. One question opening and one CTA.
Accuracy and publishing rules
Mention sample and recruitment context near the number. No industry-wide prevalence or causal language. No participant details. Link approved. English post plus Chinese example. No legal review required if wording stays within report.
Example output
Who owns the handoff—not just the task?
In an August 2026 internal survey of 48 operations managers recruited from our webinar list, 29 selected unclear ownership as one of their top three handoff problems. Respondents could select more than one issue, and this sample does not represent every operations team.
The useful question is not “Do we have an assignee?” It is whether the workflow makes three things explicit:
• who decides the work is ready to move
• who accepts it on the other side
• what happens when acceptance is late or disputed
A tool can display a name while those decisions remain unclear. Review one recurring handoff this week and look for the first missing decision.
Claim ledger: the 29-of-48 result, August date, webinar-list recruitment, multiple-selection design, and non-representative limitation all come from the report's Handoffs section. The three review questions and tool observation are editorial synthesis, not survey findings. No quote, causation, or industry prevalence claim is used.
Why this works
1
A claim ledger makes the final short-form copy auditable despite compression.
2
Preserving scope and uncertainty prevents a catchy opening from changing the evidence.
Check the result
Can every factual or quoted phrase be traced to a locator and permission?
Does the post retain sample, date, qualifier, and causal boundaries?
Is the CTA proportionate to what the source supports?
Use it with confidence
Frequently asked questions
Practical answers about when to use this recipe, what to provide, and where human review still matters
What should I prepare before using “Draft a source-grounded social post”?
For “Draft a source-grounded social post,” prepare Source material, Post brief, and Accuracy and publishing rules. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.
When is the “Draft a source-grounded social post” result not ready to use?
The result is not ready if it does not yet deliver the stated outcome—A publishable draft, claim-to-source ledger, unresolved questions, and final verification checklist—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.
Which AI tools have recorded tests for “Draft a source-grounded social post”?
The published test record for “Draft a source-grounded social post” lists ChatGPT as of 2026-08-28. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.
Go from understanding AI to getting things done. Practice prompting, reviewing, and improving results through interactive lessons for work and everyday life.
ChatGPT
