Long-Form Article Drafting in Canvas from an Editorial Brief

Take a topic and audience through a brief, outline, and first draft with a fact-check list. Designed for ChatGPT Canvas so you can edit section by section and keep claims verifiable.

You get: Editorial brief, outline and full draft

More like this

The prompt

long-form-article-drafting-in-canvas-from-an-editorial-brief.md
Role: You are a senior editor and writer for {brand}, producing articles for {audience}.Context: The article topic is {topic}. The goal is {goal}, and the reader should be able to {reader_outcome} after reading. The decision to support is whether the angle and structure are strong enough to publish after review.
Task: Produce an editorial brief, outline, and first draft of about {word_count} words.Constraints: Do not invent statistics, quotes, studies, or customer stories. Where a fact is needed, insert [VERIFY: description of needed evidence] instead of making it up. Follow the voice guidelines: {voice_guidelines}. Avoid filler intros, hype, and unsupported superlatives.

Inputs:
- Topic and angle: {topic}
- Audience and their level of knowledge: {audience}
- Primary keyword or theme and search intent: {keyword}
- Source material I provide (notes, links text, data): {source_material}
- Brand voice and banned phrases: {voice_guidelines}
- Call to action: {cta}

Workflow:
1. Write a brief: reader problem, thesis, angle, 3 key takeaways, and what to exclude.
2. List assumptions and missing information. Ask up to 4 questions if the angle is unclear.
3. Present an outline with section purposes and estimated word counts. Pause for my approval only if I asked for it; otherwise proceed.
4. Draft the article in Canvas with clear headings, short paragraphs, and concrete examples that come from my inputs.
5. Add a fact-check table of every claim that needs verification.
6. Provide 3 headline options and a meta description under 155 characters.
7. Suggest revisions: what to cut, strengthen, or test.

Output format:
- Editorial brief
- Outline
- Full draft (in Canvas)
- Fact-check table (claim, location in draft, evidence needed, status)
- Headlines and meta description
- Revision notes and next actions

Acceptance criteria:
- The draft delivers the reader outcome stated above.
- Every unsupported claim is flagged with [VERIFY].
- The tone matches the voice guidelines and the call to action appears once.

Quality checks:
- Count words against the target, within 10 percent.
- Remove repeated points and generic phrases.
- Confirm each section serves a takeaway in the brief.

Example output

AI-written example

Editorial brief

  • Reader problem: Account managers lose Friday afternoons writing client status updates.
  • Thesis: A fixed three-part template beats a custom report.
  • Takeaways: (1) Report decisions, not activity. (2) Use one template every week. (3) Cap it at 15 minutes.
  • Exclude: Tool comparisons, dashboards.
  • Open question: Do you have your own timing data from client teams?

Outline

  1. The cost of the long update (~40 words)
  2. The three-part template (~90 words)
  3. Run it in 15 minutes (~50 words)

Draft (Canvas)

Stop Writing Status Updates Nobody Reads

Most clients skim updates for one thing: do I need to decide anything? Long reports bury the answer. [VERIFY: data on how clients read status emails]

Use three blocks, every week

  • Done: Three outcomes, not tasks.
  • Next: What ships before the next update.
  • Needs you: Decisions, each with a due date.

Keep the order fixed. Clients learn where to look, and you stop reinventing the format.

Run it in 15 minutes
Draft from your task list on Thursday, trim to one screen, and send. If "Needs you" is empty, say so. Fewer words usually means more replies. [VERIFY: internal reply-rate comparison]

Want the template? Download the Fieldnote update kit.

(Draft is about 150 words, shortened for this example. Full length would be 1,200.)

Fact-check table

ClaimLocationEvidence neededStatus
Clients skim for decisionsIntroSurvey or interview dataOpen
Shorter updates get more repliesSection 3Reply-rate comparison from your accountsOpen

Headlines and meta description

  1. Stop Writing Status Updates Nobody Reads
  2. The 15-Minute Client Update Template
  3. Three Blocks That Replace Your Weekly Report

Meta (148 chars): Cut weekly client updates to 15 minutes with a three-block template: what's done, what's next, and what needs the client's decision.

Revision notes and next actions

  • Strengthen: Add a real before-and-after example from your source material.
  • Cut: The Thursday drafting tip if it doesn't fit your workflow.
  • Test: Two headlines in the email subject line.
  • Next: Supply the data for both [VERIFY] flags, then confirm the angle.
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Ask ChatGPT to open the draft in Canvas, then use inline edits to refine one section at a time. Resolve every [VERIFY] flag with real sources before publishing.

Questions about this prompt

More in ChatGPT

Long-Form Article Brief With Source Discovery Plan and Citation Table

Creates an editorial brief and outline for a researched article. It includes a source discovery plan, an evidence review template, and a citation table, without pretending any live browsing took place.

Short Explainer Video Script With Scene Table and Fact-Check List

Produces a 60-180 second explainer video script from a brief, with a scene-by-scene table for voiceover and visuals, a fact-check list, and a go/no-go checklist for recording.

Trending

Developmental Edit Memo for an Essay Draft With Revise-or-Cut Decisions

Gives a draft essay a structured developmental edit: thesis check, paragraph-by-paragraph audit, and a prioritized revision plan so you can decide what to keep, rewrite, or cut before line editing.

30-Minute Moderated Usability Test Script with Tasks and Notes Template

Produces a timed 30-minute moderated usability script with task scenarios, neutral follow-up questions and a ready-to-use notes template.

4-Week Small Business Launch Plan: $0 and Small-Budget Versions

Builds a 4-week launch plan for a product or service in a specific market, with channels and weekly tasks in a $0 version and a small-budget version.

60-Minute Lesson Plan with Checks for Understanding and Differentiation

Builds a timed, objective-aligned lesson plan with formative checks, differentiation, and a teach-or-revise readiness verdict. It asks for missing inputs first and keeps assumptions separate.

90-Day Lifecycle Marketing Diagnostic and Experiment Roadmap for Onboarding and Retention

Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.

Above-the-Fold Landing Page Critique with 3 Headline, Subhead, and CTA Variants

Critiques landing page copy for clarity and conversion, then rewrites the headline, subhead, and CTA in three distinct variants.

Adaptive Quiz from My Notes with Weak-Spot Summary

Quizzes you one question at a time from your own notes, adjusts difficulty after each answer, and ends with a ranked list of weak spots.

AI Paper Explainer with Evidence Table and Practical Takeaways

Turns a pasted AI paper abstract or text into a plain-language explanation of what is new, how it was tested, its limits and what to do with it.

AI Visibility Audit: Brand Mention and Citation Test Plan for AI Answer Engines

Design and analyze a repeatable prompt test set that checks how AI answer engines mention and cite your brand. It turns results into a citation table, evidence-based gap findings, and prioritized page and entity fixes.

AI Visibility Prompt Tracker List: 25 Buyer Prompts by Funnel Stage

Produces 25 realistic buyer prompts grouped by funnel stage, ready to run monthly to track whether AI assistants mention your brand.