Skip to main content

Content · build guide

AI Brief Machine

From one objective, keyword, or product to a full creative brief in under five minutes

Path A · Manual extracts Path B · MCP integration Guardrail-first

Give the AI Brief Machine a single input — a campaign objective, a keyword, a product — and its multi-step prompt chain returns a structured creative brief in under five minutes. The chain runs in stages: audience definition, angle, format, messaging hierarchy, and distribution notes, with each stage's output feeding the next so the brief stays internally consistent instead of reading like five disconnected paragraphs.

The chain itself is the compounding asset. Every run surfaces a weak prompt or a missing brand rule; you fix it once and every future brief improves. Over months you build a brief library your writers trust and a prompt chain tuned to your brand — not a blank chat window someone re-improvises each time.

What it moves: A complete, structured creative brief — audience definition, angle, format, messaging hierarchy, and distribution notes — from a single input in under five minutes.
Path A · Manual

This version runs entirely on a saved prompt chain, a Google Docs template, and an intake sheet — no API connections and no build tooling, matching the automation's core dependency: one input per run. It suits a team that wants consistent briefs this week and is fine running the chain by hand for each request.

Path B · Integrated

This version wraps the same prompt chain in an agent: intake triggers a run automatically, the agent pulls read-scoped brand and performance context over MCP, drafts the brief, and parks it at a human gate before anything reaches production. It suits teams producing enough briefs per week that hand-running the chain has become the bottleneck.

Prerequisites.

A Claude workspace where the prompt chain can be saved and shared with the team
Brand basics written down: positioning, tone rules, banned claims, audience segments
A brief template your writers and production team already accept
One input per run — a campaign objective, keyword, or product; no external system connections required to start
A named owner who approves changes to the prompt chain
New to the stack? Set up your environment first — data access, workspace, integration platforms, and the agent layer are covered once in Environments & tooling.

Build it with manual data extracts.

This version runs entirely on a saved prompt chain, a Google Docs template, and an intake sheet — no API connections and no build tooling, matching the automation's core dependency: one input per run. It suits a team that wants consistent briefs this week and is fine running the chain by hand for each request.

  1. Lock the brief template first

    Create a Google Docs template with the five sections in fixed order: audience definition, angle, format, messaging hierarchy, distribution notes. Add a header block for the input, requester, date, and the prompt-chain revision that produced it. The chain writes into this shape, so agree on it with your writers before you build anything.

  2. Build the prompt chain in Claude

    Write one saved prompt per stage, where each stage takes the previous stage's output as its input — audience feeds angle, angle feeds format, and so on. Store the chain in a shared Claude Project with your brand context (tone rules, banned claims, segments) loaded as project knowledge. Record the chain in a change log from day one so every later revision is traceable.

  3. Set up an intake sheet

    Make a Google Sheet with columns for the input (objective, keyword, or product), audience notes, deadline, requester, and status. Optionally paste supporting rows from a search term or GA4 landing-page export into a context column — it sharpens the audience and angle stages, but the chain runs fine without it.

  4. Run the chain per request

    Take the next intake row, run stage one, paste its output into stage two, and continue through all five. Paste the final output into the template. A run takes under five minutes; resist editing mid-chain — note weaknesses instead so they get fixed in the prompts.

  5. Review, file, and log

    The owner checks the draft against brand rules, makes corrections in the doc, saves it to the brief library, and marks the intake row done. Log any correction that reveals a prompt gap — those notes are the raw material for the next chain revision.

  6. Iterate the chain monthly

    Once a month, review the logged corrections, update the weakest prompts, and note the revision in the change log. Keep prior prompt wording so you can roll back if a revision makes briefs worse.

Cadence: On demand per campaign request — a run takes under five minutes plus a short review; batch the intake queue weekly if requests pile up, and revise the chain monthly.

Integrate it with MCP connections.

This version wraps the same prompt chain in an agent: intake triggers a run automatically, the agent pulls read-scoped brand and performance context over MCP, drafts the brief, and parks it at a human gate before anything reaches production. It suits teams producing enough briefs per week that hand-running the chain has become the bottleneck.

Claude with MCP servers — runs the multi-step chain and reads scoped context
An MCP server for Google Drive/Docs — brand guidelines in (read-only), finished briefs out (scoped to one folder)
Google Sheets or your project management tool — intake queue, status, and run log
BigQuery with GA4 or Google Ads exports (optional, read-only) — performance context for the audience and angle stages
Slack — approval notifications for the human gate
  1. Encode the chain as an agent workflow

    Rebuild each stage as a step with structured output — named fields for audience, angle, format, messaging hierarchy, and distribution notes — in n8n, Make, or a Claude agent workflow. Store the prompts in version control or a versioned doc so every change is reviewable and reversible.

  2. Wire intake as the trigger

    A new row in the intake sheet or a new ticket in your project tool starts a run — no one pastes anything by hand. Reject malformed intakes back to the requester with a note rather than letting the agent guess at missing inputs.

  3. Connect read-scoped context

    Give the agent MCP connections to your brand guidelines folder and, optionally, performance data such as GA4 or Google Ads exports in BigQuery. All connections are read-only and scoped to specific folders and datasets; write access exists only for the briefs output folder.

  4. Let the agent draft and self-check

    The agent runs the five stages, then validates the draft against your brand exclusion list — banned claims, restricted audiences, off-limits comparisons. Sections it can't ground in the provided context get flagged for the reviewer instead of filled with plausible-sounding filler.

  5. Hold every brief at the human gate

    The finished draft lands in Google Docs and a Slack notification goes to the chain owner, showing the input and which sources the agent used. Only approved briefs move to the writers' queue. The agent recommends; it never publishes.

  6. Keep the audit trail per run

    Each run writes input, prompt revision, sources read, output, approver, and timestamp to a log sheet or BigQuery table. When a brief goes wrong, the log tells you exactly which revision of the chain produced it — and rolling back is one change.

Run it safely.

Claude — runs the multi-step prompt chain that builds each brief section
Google Docs — the brief template and the growing finished-brief library
Google Sheets — intake queue, status tracking, and run log
n8n, Make, or Zapier — triggers runs from intake and routes drafts to approval on the MCP path
Claude with MCP servers — read-scoped access to brand docs and performance context on the MCP path
Slack — approval notifications and the human gate
  • Every brief passes a named human approver before it reaches writers or production — the agent drafts, it never publishes
  • Agent access is read-only and scoped: brand-docs folder and performance datasets in, one briefs folder out, nothing else
  • The prompt chain is versioned and every run logs input, prompt revision, output, and approver — any bad brief traces to a revision and rolls back in one change
  • A brand exclusion list is checked on every run; flagged briefs route to the owner instead of the queue

Want new build guides as they ship?

Optional — every guide on this site is free either way. Leave your details and we'll email you when new automations join the library, nothing else.

We only email when there's something worth building — every email has a one-click unsubscribe, and you can withdraw consent anytime. Consent requested by Campaign Automation AI, Caledon, Ontario · hello@campaignautomation.ai.

Prefer it built for you?

We stand this automation up as a governed sprint on the stack you already run — scoped, built, and handed over with the guardrails configured. No new platform, no migration.

Start with the Audit → Request proposals →