Build a daily editorial brief from multiple sources
Collect topic signals across the web, group them into themes, and give an editor a short list of timely story ideas.
How this works
Collect topic signals across the web, group them into themes, and give an editor a short list of timely story ideas. An editorial trend brief should help an editor select a timely story, not automatically turn every popular signal into content. Relevance, freshness, credibility, and the publication's angle need separate consideration.
Collect a bounded multi-source window, cluster related items into events or themes, and propose a short list of story angles. Preserve source dates and access limits. The editor chooses the topic before drafting so the workflow does not flood the publication with redundant or weak material.
Before you start
Editorial remit
Define audience, topic boundaries, and excluded formats.
Source mix
Choose available feeds, public discussions, and primary pages.
Selection rubric
Agree freshness, relevance, evidence quality, and novelty criteria.
Prepare the inputs
- source_items
- Required
Text and metadata
Record publication and observation dates.
- topic_scope
- Required
Audience questions
Avoid generic popularity as the only criterion.
- prior_coverage
- Required
Recent published topics
Detect repeated stories.
- selection_rules
- Required
Criteria and examples
Keep uncertain cases visible.
- channel_needs
- Required
Formats and deadlines
State what can realistically be produced.
Implementation, step by step
Collect the reporting window
- Gather accessible material and record failed sources.
- Keep late-discovered older items separate from genuinely new developments.
Checkpoint: A dated source manifest.
Cluster related signals
- Group coverage of the same event and preserve independent perspectives.
- Do not count copied headlines as several confirmations.
Checkpoint: An event-level set.
Assess editorial relevance
- Apply the rubric to the audience question and publication remit.
- Explain why an item matters now rather than assign an opaque trend score.
Checkpoint: A ranked topic queue.
Develop distinct angles
- Suggest an explanatory question, practical implication, or expert response for each selected topic.
- Keep the angle grounded in what the evidence can support.
Checkpoint: A concise story pitch.
Match formats to channels
- Recommend a format suited to the substance and production deadline.
- Do not stretch a thin signal into a long analysis or imply unseen media was reviewed.
Checkpoint: Channel-specific suggestions.
Prepare the editor's choice
- Deliver a short brief with evidence, caveats, and required follow-up.
- Record selected and deferred topics before any full drafting.
Checkpoint: An editorial decision queue.
Decisions along the way
A story is popular but outside the remit
Exclude it or explain the narrow relevant angle.
The primary source is unavailable
Lower confidence and request verification before drafting.
A topic was recently covered
Propose only the genuinely new development.
What you will produce
daily-editorial-brief.md
MarkdownHelps the editor choose what to commission.
Include: topic · why_now · angle · evidence · limits · format
trend-source-log.csv
CSVMaintains coverage and deduplication history.
Include: item_id · event_id · date · source_type · access_status · decision
Check the result
- Verify freshness and event dates.
- Check independent evidence rather than repeated coverage.
- Confirm each angle serves the audience.
- Keep proposed formats realistic for available material.
When something goes wrong
The brief becomes a long link dump
Reduce it to a few decision-ready pitches.
A model invents momentum metrics
Remove them or use verified visible observations.
Collection misses an important source
Disclose the gap and update the brief if material evidence arrives.
A worked example
SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT
Request
Prepare today's brief on workplace AI.
Inputs
Synthetic example. Synthetic three articles repeat one launch, while a separate primary report describes a limited trial.
Expected result
Synthetic expected result. Offer one launch pitch and one trial-analysis pitch with different evidence limits. Do not present four independent trends.
Run a small pilot
Start small
Several daily briefs with editor selection recorded.
Record the baseline
Record selection time and rejected-topic reasons.
Agree success criteria
Agree relevance, novelty, and evidence quality before automating collection cadence.
Stop or revise
Stop drafting when the editor has not selected a topic or central facts remain unverified.
Keep the scope clear
- A trend brief does not authorize publication or social posting.
- Public attention is not proof of practical value or business impact.
Check before using
Check sources, novelty, and relevance; the editor chooses what deserves publication.
Business activities
- Create and publish content
- Research customers and markets
FROM A RECIPE TO YOUR WORKFLOW
Bring the company context together.
This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.
For this recipe: Selected public sources · Topic priorities · Audience and channel guidance
Start with one recurring task, agree which sources to use, and review the first result with your team.
Discuss this workflow