Offer and Landing Page

Builds campaign landing pages as drafts and tests offers: bundle versus discount versus gift. Creates the codes, points Ad Creative's batch at the right page, and reads the result. No autonomous mode on purpose.

AdviseAct $79 a month, ₹4,999

Email us to start See the workflow

Who it is for

The owner running a sale on the home page banner, and the marketer who wants one live test per product with a plan for reading it.

What it reads from the brain

Before every run. Sections are addressed as layer.section.

identity.*customer.objectionscustomer.vocabularyproduct.hero_productsmodule:market.sale_calendar

What it does, step by step

Read the brain
Opens the sections above and the inputs.
Gather evidence
Reads the product page the campaign will sell. Every finding cites its source.
Decide and draft
Drafts the landing page copy and structure, the offer variants (bundle, discount, gift) with their codes, and the test plan. Drafts use your customers' vocabulary and only claims_allowed.
Advise stops here
You get the page draft, the offers and the test plan.
Act
Creates the page as a draft and the discount code, requests your approval to publish, and records the test in the brain for Ad Growth to read.
Write back
What worked and what did not are appended.

Tools it uses

storefront.pageThe product page the campaign sells
shopify.pages.create_draftAct: the landing page as a draft
shopify.pages.publishApproval gated, always
shopify.discount.createApproval gated, always. The offer code
image.composePage imagery from your real product images

The three modes for this agent

AdviseYour own AI, no credentials

Read tools only. You get the landing page copy and structure, the offer variants with codes, and the test plan.

ActConnected, every write waits for a tap

Page created as a draft, code created after your approval, publish after your approval. The test is recorded in the brain for Ad Growth.

AutonomousHosted, scheduled, still gated

Not offered, on purpose. Launching an offer is a decision you make.

Guardrails and approvals

Enforced in code. Items with a filled circle wait for your tap in Telegram.

Pages go to draft first.
Discount depth cap.
Never edits the main product page. That is Store Fix's job.
One live test per product at a time.
Offer copy uses only claims_allowed.

What it writes back to the brain

Dated and sourced. Learnings and performance sections are append only.

learnings.what_worked (append only)learnings.what_did_not (append only)

Example output

Example output: summary.md and the test planExample output

Example output. Structure only. No performance figures.

Offer and Landing Page, your store, hero product 1

Ran at data level 3 (Shopify connected).

Landing page drafted: 1, copy and structure in page-draft.md. Planned: the section order (hook, top objection answered, proof inside claims_allowed, offer, one CTA) is our working template, not yet fixed in the contract.
Offer variants: 3, in offers.csv. Bundle: [hero product 1 plus hero product 2]. Discount: [inside your depth cap]. Gift: [low cost add on].
Codes drafted: 3. Sale window: [from your market playbook].

Draft page created. Waiting for your approval to create the codes and publish.

test-plan.md (structure)

What is being tested: bundle versus discount versus gift, one live test on this product.
How traffic arrives: Ad Creative's batch pointed at this page.
How to read it: Ad Growth reads the recorded test from the brain and reports which variant the written rule favoured, with evidence, or no clear cause.
When it ends: [the sale window from your market playbook closes]. Planned: a written stopping rule per test.

Also delivered: offers.csv (variant, code, depth, window, status).

Price

$79₹4,999a month, hosted. Cancel any month.

Email us to start