How it works

Four scenarios,
module by module.

Below is exactly what runs. Each scenario is a Make.com flow chaining real modules — Google Sheets, a brand-memory data store, Claude, the ads APIs, and Slack — into one autonomous loop. Scroll through to see every step reveal in sequence.

Scenario G1 · Google Pre-Launch

Brief → Google strategy
in one linear pass.

A linear, 12-module scenario. Watches the Briefs tab. When a new row arrives flagged for Google, it pulls brand memory, sends a prompt to Claude, parses the JSON, iterates the campaigns, writes them as strategy rows, then pings Slack.

1
📋
Google Sheets
Watch New Rows
3
✏️
Google Sheets
Update a Row
4
🗂️
Data store
Get a record
5
A\
Anthropic Claude
Create a Prompt
6
{ }
JSON
Parse JSON
7
Iterator
Loop campaigns
8
Google Sheets
Add a Row
9
Google Sheets
Add a Row
10
Array aggregator
Aggregate
11
✏️
Google Sheets
Update a Row
12
#
Slack
Send a Message
01 · 03

Pick up the brief

Polls the Briefs tab every 15 min. Picks rows where platforms ∈ Google, Both AND google_status is empty. Flips status to Researching.

04

Load brand context

Reads the Make data store record keyed by brand. Voice, audience, geo, competitors, historical KPIs, conversion IDs — all loaded.

05 · 06

Claude generates strategy

Sonnet 4.6 returns JSON: 4 campaigns × 15 RSAs each, with keywords, negatives, geo targeting. The JSON module parses it.

07 · 10

Iterate & write

The iterator unpacks each campaign. Two parallel addRow modules populate GoogleStrategy and seed the Benchmarks tab. Aggregator collects results.

11 · 12

Mark ready + ping

Flips google_status to Strategy_Ready. Slack pings the strategist: "Google strategy ready — review on Sheet."

make.com / scenarios / G1 — Google Pre-Launch
Google Pre-Launch scenario in Make.com
Scenario G2 · Google Post-Launch

Three branches. One router.
Hourly forever.

Same trigger, three different jobs depending on the row's state. Approved-but-not-built → Build. Live-and-24h-old → Health check. Live-and-72h-since-last-optimisation → Search-terms optimiser. Routes per row.

1
🔍
Google Sheets
Search Rows
2
🗂️
Data store
Get a record
3
Router
3 branches
Branch A · Approved & not built
4
🔍
Google Sheets
Search Rows
5
Google Ads
API Call
6
✏️
Google Sheets
Update a Row
7
#
Slack
Send a Message
Branch B · Live, 24h+ elapsed
8
Google Ads
API Call
9
A\
Anthropic Claude
Diagnose
10
Google Sheets
Add a Row
11
✏️
Google Sheets
Update a Row
12
#
Slack
Send a Message
Branch C · Live, 72h+ since opt
13
Google Ads
API Call
14
Google Ads
API Call
15
A\
Anthropic Claude
Propose negs
16
Google Sheets
Add a Row
17
✏️
Google Sheets
Update a Row
18
#
Slack
Send a Message
Branch A

Build

Reads GoogleStrategy rows for the brief, hits Google Ads mutate API to create the campaigns PAUSED, marks status Built, pings Slack: "Built — flip live in Ads UI."

Branch B

24h Health

Pulls last-7-day GAQL performance, hands it to Claude for diagnosis against Benchmarks, logs to OptimizationLog, pings Slack with verdict.

Branch C

72h Optimise

Pulls last-7-day search terms (top 200) + last-7-day perf. Claude proposes negatives only for clearly out-of-context terms. Logs proposal, pings Slack — human 👍 applies via mutate API.

make.com / scenarios / G2 — Google Post-Launch
Google Post-Launch scenario in Make.com
Scenario M1 · Meta Pre-Launch

Brief → 5 creative concepts.
Designer-ready.

Same backbone as G1, different prompt. Watches the Briefs tab for Meta or Both. Pulls brand memory, asks Claude for 2 static + 2 carousel + 1 video concept with hook, copy, and visual direction. Writes to MetaStrategy.

1
📋
Google Sheets
Watch New Rows
3
✏️
Google Sheets
Update a Row
4
🗂️
Data store
Get a record
5
A\
Anthropic Claude
Create a Prompt
6
{ }
JSON
Parse JSON
7
Iterator
Loop concepts
8
Google Sheets
Add a Row
9
Google Sheets
Add a Row
10
Array aggregator
Aggregate
11
✏️
Google Sheets
Update a Row
12
#
Slack
Send a Message
01 · 03

Pick up the Meta brief

Same trigger as G1, but filters for platforms ∈ Meta, Both AND meta_status empty. Flips to Researching so the team knows it's in flight.

04

Load brand memory

Reads the same brand record. Includes preferred creative angles, banned imagery, voice rules, and competitor creative landscape.

05 · 06

Claude creative briefs

Returns JSON with 5 concepts: 2 static + 2 carousel + 1 video. Each has a hook line, body copy variants, and visual direction the designer can act on.

07 · 10

Iterate to MetaStrategy

Iterator unpacks each concept. AddRow writes to MetaStrategy + seeds Benchmarks with Meta KPI defaults. Aggregator confirms count.

11 · 12

Hand off to designer

Flips meta_status to Strategy_Ready. Slack: "Meta creative brief ready — 5 concepts for designer." Designer drops assets in Drive.

make.com / scenarios / M1 — Meta Pre-Launch
Meta Pre-Launch scenario in Make.com
Scenario M2 · Meta Post-Launch

Build, watch, refresh.
Forever, on Meta.

Same router pattern as G2 but talks to the Meta Graph API over HTTP. Build branch creates campaigns + ad sets PAUSED. 24h branch watches CPL, CTR, frequency. 72h branch detects ad fatigue and proposes 2-3 fresh creative angles.

1
🔍
Google Sheets
Search Rows
2
🗂️
Data store
Get a record
3
Router
3 branches
Branch A · Approved & not built
4
🔍
Google Sheets
Search Rows
5
🌐
HTTP
POST Meta API
6
✏️
Google Sheets
Update a Row
7
#
Slack
Send a Message
Branch B · Live, 24h+ elapsed
8
🌐
HTTP
GET insights
9
A\
Anthropic Claude
Diagnose
10
Google Sheets
Add a Row
11
✏️
Google Sheets
Update a Row
12
#
Slack
Send a Message
Branch C · Live, 72h+ since opt
13
🌐
HTTP
GET ad insights
14
A\
Anthropic Claude
Fatigue + angles
15
Google Sheets
Add a Row
16
✏️
Google Sheets
Update a Row
17
#
Slack
Send a Message
Branch A

Build

Reads MetaStrategy rows, POSTs to Meta Graph API to create campaign + ad sets PAUSED. Marks Built. Slack: "Built — flip live in Ads Manager."

Branch B

24h Health

GETs last-7-day insights (spend, CPL, CTR, frequency). Claude compares to Benchmarks. Logs verdict. Slack alerts only on tolerance breach.

Branch C

72h Fatigue + angles

GETs last-14-day ad-by-ad insights. Claude detects fatigue (CTR decay, frequency thresholds) and proposes 2-3 new angles. Designer picks up after thumbs-up.

make.com / scenarios / M2 — Meta Post-Launch
Meta Post-Launch scenario in Make.com
The whole picture

Every scenario. Every gate.
One diagram.

The system board ties all four scenarios, the brand memory layer, the Campaign Hub Sheet, and every human gate into a single flowing diagram.