A pilot on your own weeks.
Your data, about eight weeks, and four numbers agreed before it starts. A pilot answers one question: would this planning team use Kelynto every Monday?
No pilot has been run yet. Kelynto is an early-stage company opening its first pilots with retail planning teams. You would be among the first, which is why the scorecard is set first and measured in the open.
What a pilot is.
One team or one region, alongside your current process. Nothing you do today is switched off, so if it does not help, you stop and nothing has changed.
-
Weeks 1 and 2: backtest
We run your past weeks and set each draft beside what your team actually wrote. You see the fit before anyone changes how they work.
-
Weeks 3 to 8: six live Mondays
A drafted review arrives each Monday. Your planner edits it and marks each cause. For the first weeks we deliver it by hand: you send the week's file and we return the review.
-
End of week 8: readout
The four scorecard numbers, what the draft got wrong, and a decision. Either side can stop earlier.
The data a pilot needs.
Two files are enough to start. Totals only: no transactions, baskets, shopper, payment or employee data.
| File | One row per | Needed | Helpful if you have it |
|---|---|---|---|
| Stores | Store | Store number, region | Coordinates, district, city, state, postal code, format |
| Weekly sales against plan | Store, week and category | Store number, week, category, actual sales, plan sales | Prior-year sales, units |
| In-stock (optional) | Store, week and category | In-stock rate | |
| Promotions (optional) | Week and category | Week, category | Store, promotion type, discount |
| Local facts only you know (optional) | Fact | Type, title, start date, and a store or a location | End date, expected direction, categories |
- Your format. CSV or Excel, with your own column names. Common names from planning and BI exports are recognised.
- History. Twelve weeks is workable and 26 is better. Daily rows are summed into your fiscal weeks.
- In-stock is the most valuable addition. It is what lets a draft tell a stockout from a demand problem.
- Store coordinates matter. Local signals are matched to stores by location. Without coordinates, weather, events and road work cannot be matched.
- What the field knows gets in as a file. A competitor opening, a remodel or a parking-lot closure is one row.
- A bad export cannot overwrite good data. The loader reports what it read row by row and rejects a file outright when more than one row in five has an error.
Success criteria, set before it starts.
Four numbers from the scorecard, measured from what your planners actually did. They are targets for the pilot. They are not results we have achieved.
- 20%or less of the draft rewritten. Editing a few words means the draft is doing the work.
- 60%or more of causes confirmed by your planners, out of those they reviewed.
- 75%or more radar calls pointing the right way once the week's sales are in.
- 4 of 5or higher when planners are asked whether they would use it every week.
Each figure shows its sample size and reads "insufficient data" until there are enough reviews, labels or outcomes behind it.
What we ask of you.
Not "no effort". These are the real asks.
- A weekly file. The closed week's sales against plan, every week of the pilot.
- One planner, about 30 minutes each Monday, to read the draft, fix it, and confirm or correct each cause.
- Four to eight weeks of the commentary your team already wrote, for the backtest.
- How long the Monday review takes today. That number becomes the pilot's reference point.
- A named contact for data and, if people will sign in, one in IT.
Cost, and what happens after.
Pricing is not finalised. It will depend on deployment model, number of locations and pilot scope. The fastest way to get a number for your situation is a 20-minute conversation.
- There is no price list to quote, for a pilot or a subscription, and we would rather say that than invent one.
- If the scorecard is met and your team wants to keep it, terms are agreed then.
- If not, you keep the drafts and the record of confirmed causes, and your data is deleted. No obligation either way.
- You own your data, the drafts and the labels your planner creates, and you can export them.
What is true today
- No customers, no completed pilots and no results from a real retailer
- Built and tested on synthetic data; the scores in the demonstration are not results
- One founder, with more than 17 years in retail supply chain and planning technology
- Nothing is hosted yet, which is why the first weeks run by hand
Not ready for a pilot yet?
-
Explore
See the product
The sample workspace is not open to visitors yet. The product tour shows nine real screens from it.
A private copy of a synthetic retailer, Harborview Markets. No conversation needed first.
-
Evaluate with your data
Run it on your own weeks
A backtest on your past weeks, then about six live Monday reviews, judged on four measures agreed before it starts.
Create a workspace and load your own files. Sign in by an emailed link. No password to create.
-
Deploy in your environment
Check the architecture
What runs where, what crosses the boundary, and how far each path has been proven. Azure first.
-
Talk to us
Twenty minutes with the founder
Your process and your questions. Or write to marc@kelynto.com.
Kelynto is an early-stage company opening its first pilots with retail planning teams. The product is built and tested on synthetic data. There are no customers and no results yet, and this site says so wherever it matters.