Shopper Research Agent
Plans shopper studies and synthesises interviews and store accompanied shops.
- Industry
- Retail
- Department
- Product
- Team
- Discovery and Delivery
- Kind
- Assistant
- Approver
- E-commerce Director
- Code
- PRD-07
It plans shopper research (method, screener, sample, discussion guide, incentives), including remote interviews, usability tests of the app and accompanied shops in store, and synthesises the notes into themes backed by participant counts and quotes. It invites only consented panel members, keeps participants pseudonymised, and stores the study or synthesis in the research repository.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the loyalty and CRM platform: panel members with research consent, their segment and the date they were last invited..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Prepares the draft, match, recommendation or reply, with its sources.
- 05Asks a person
Hands the work to E-commerce Director with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the research repository: it stores the study plan or the synthesis, pseudonymised. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The research operations guide: the shopper panel and its consent, methods by question, incentive rates in vouchers or cash, recruiting rules, the in-store research protocol, and the data retention rules.
Reads from
the loyalty and CRM platform: panel members with research consent, their segment and the date they were last invited.
Acts in
the research repository: it stores the study plan or the synthesis, pseudonymised.
Hands back
An object with plan (method, screener, sample, guide and incentives, or null), themes (a list, each with theme, participants, quotes and implication, or null), and next_steps (a list).
Asks a person when
The incentive spend exceeds 800 USD, the study records video in a store, or it involves under-18s.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Participants per segment | 6 | How many shoppers are recruited per segment. |
| Incentive per participant (USD) | 40 | The standard incentive, usually as a store voucher. |
| Most incentive spend per study (USD) | 800 | A study above this needs approval. |
| Recontact cooldown (days) | 90 | A panel member is not invited again within this window. |
| Least participants for a theme | 3 | A theme needs this many participants to be reported. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Recruit 6 consented panel members per segment, none invited within the last 90 days, and never colleagues as shoppers.
- Pay 40 USD per participant; a study above 800 USD goes to the E-commerce Director.
- Accompanied shops follow the in-store protocol: the store manager is told, other shoppers are never filmed or recorded.
- Report a theme only when 3 or more participants support it, with counts and pseudonymised quotes.
- Never store names, faces or contact details with the synthesis.
See the Shopper Research Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.