Kelynto is variance commentary for retail planning: the weekly review, written from your own records.
Your Monday business review, already written.
Kelynto writes the weekly review of sales against plan, store by store and category by category, from your own records: what the records explain, with the evidence one click away, what is on file near your stores, and what is still open. Then it looks ahead against your plan. Your planner reads it and publishes.
A working conversation about how your team writes its Monday review. The product tour shows real screens of the product on a synthetic retailer.
Opens a private sample workspace with a synthetic retailer. No conversation needed first.

One product, two ways to use it.
-
For retail planning teams
The Monday review, written before the week starts.
Sales against plan by store and category, each recorded cause with its evidence, the recap leadership reads, and the Outlook for the weeks ahead. Your planner edits, decides and publishes.
-
For planning services, retail software vendors and consultancies
Offer the weekly review to every client, inside your product and under your brand.
Kelynto is an explanation layer on top of your planning service or product: one workspace per client, a partner API, embedded views, and your name on what your clients read.
See the partner platform Book a 30-minute partner conversation
Why it exists
Every Monday, someone has to explain last week.
Which stores missed plan, which beat it, and why. The planning system supplies the numbers. The explanation is still put together by hand, from spreadsheets, store calls and memory.
Today
"Why did Produce miss plan in the Valley stores?"
- The week closes. Actuals land. The misses show up in the dashboard.
- The calls start. Stores and distribution centers. Was it a stockout, the weather, a promotion across the street?
- Sunday night. Spreadsheets, dashboards, emails and chat threads become a narrative.
- Monday. Leadership asks a question the deck does not answer.
With Kelynto
The review is written before Monday starts.
Harborview Markets finished the week $649K below plan, a shortfall of 3.0%. Harborview Markets sales were $20.9M against a plan of $21.6M, yet 2.4% above the same week last year, so the miss is against plan rather than against last year.
Valley was only 0.6% below plan the week before, so this week's Valley drop is sharp and new.
Recorded this week, with estimated impact. Produce: Average in-stock 69% vs 96% typical across 9 stores.
Questions to resolve. Chesapeake's unexplained shortfall of $199K is larger than its net gap of $119K. Which lifts are offsetting it?
Proposed next steps. Planning should check whether the plan for the 10 stores below plan in every category is still realistic.
Excerpts of a review written by Claude from the week's evidence in the sample workspace, on synthetic data, quoted as written. Every figure in it is printed from an entry of the week's evidence that Kelynto computed from the files, and each claim is checked against the entries it cites before anyone sees it. Your planner reads it, adds what the team knows, and sends it up.
- Who uses it Demand planners, merchandise planners and analysts who write the weekly commentary, and the advisors of a planning service who write it for their clients.
- Who reads it Directors and vice presidents in planning, merchandising, supply chain and store operations, and the owners of independent stores.
- Where it fits Wherever sales are reviewed against a plan by store and category: from a single store working with a planning service to chains of several hundred locations.
Where it sits
Your planning system makes the plan. Kelynto explains the variance to it.
They do different jobs. Kelynto reads the plan you already have and never changes it.
Planning system
What should happen
Forecasts, replenishment and the plan. Kelynto works from that plan.
Dashboards
What happened, and where
Variance by region, category and store. The cause is left for a person to find.
Kelynto
Why it happened
What your own records show, with an estimated impact and the record behind it. What is on file near your stores, as context. What is still open, as an amount. What is coming against your plan. Written with every figure traced, checked by your planner, and kept on record with every decision.
A simple test. Does a planner on your team still spend part of Monday working out why stores missed plan, then writing a paragraph for leadership? Does an advisor at your firm do the same for every client before every call? That is the work Kelynto covers.
Beside a general AI assistant. An assistant writes fluently about whatever is pasted into it. In Kelynto the engine computes every number, a cause gets an amount only when a record shows it, and a claim whose figure the evidence does not hold is dropped before anyone reads it.
What it works from. Weekly files from whatever you plan in and sell through, a spreadsheet included: uploaded, sent to its API, or collected on a schedule from a folder you name. It reads the standard exports of the common point-of-sale systems as they are. See what it reads.
One loop, every week.
Explain, Watch, Act, Score. The last step shows, from what your planners did, how the first three are serving them.
-
Explain
What happened last week and why, with evidence.
Every figure reconciles to the week's variance to plan, and what the records do not explain is stated as an amount.
-
Watch
What is on file near your stores for the weeks ahead, on a map and a list, with alerts.
Each record with its place, its dates and its source.
-
Act
Planners confirm, reject or correct each cause, add what the review missed, and assign follow-up actions.
Every decision and every publish is kept, with who made it and when.
-
Score
Score and learn shows how the reviews are serving your planners, from what they actually did.
Counted from your planners' own edits and decisions, with sample sizes shown.


See each part on real product screens, or follow one week from the closed file to the published review.
Looking ahead
Then the review turns forward.
The Outlook sets what is on file for the coming weeks beside your own plan or latest forecast: promotions, store closures, holidays and stock-out risk, by cause and by week, each estimate with what it rests on. Weather, local events and road work are listed beside them with place and dates. Change an assumption and the outlook moves beside it, so a planner walks into Monday with the next four weeks already argued.


Proof you can check
Three things you can verify before you buy.
-
Every figure reconciles.
The parts of each review add up to the week's variance to plan at every level, from store and category to the company. A recurring export is reconciled to its own control totals, to the cent, before anything loads.
-
A cause gets an amount only when your own records show it.
Each amount is labelled an estimate and opens to the record behind it. What the records do not explain is stated as an amount, every week, at every level.
-
You can run it on your own history first.
A pilot starts with eight sealed weeks of your own history, run once against bars fixed in advance. A partner starts with a sandbox of synthetic clients. See the pilot.
Why trust it
Built to be checked.
Every claim in a draft shows how it was earned.
- The engine computes every number. The words are written by Kelynto's built-in writer, or by Claude when the AI writer is switched on for the workspace. Either way every figure is printed from the week's evidence, which Kelynto computes from your files. Read the methodology.
- An amount only where a record shows the cause. An estimated impact goes only to a cause your own files record, it is labelled an estimate, and it opens to the record behind it.
- What is still open is stated. Stores and categories under plan and over plan are added up separately, so a strong store never hides a weak one. What no record explains is an amount on the page, at every level.
- With the AI writer, each claim is checked against the evidence it cites. A figure must be the one it cites, at the place it names, and a proposed step is never reported as done. A claim that fails is dropped. "How this draft was written" shows each claim beside its evidence.
- Your planner decides. Each recorded cause is a candidate until a person confirms, rejects or corrects it. Every decision and every edit is kept in the review's history. When corrected data arrives, the published review stays as published until a planner publishes the restatement, which says what it replaces.
For your architect and your security reviewer
Enterprise-grade controls, each with its evidence.
The questions an architect asks first have plain answers.
- Kelynto Managed on Microsoft Azure, or in your own Azure account. The same software either way.
- Tenants kept apart twice. In the application, and again in the database with row-level security that fails closed. A partner's clients each have a workspace of their own.
- The AI writer is a choice. Switched on for a workspace by its admin, or for a partner's clients under the partner's recorded agreement with them. It sees the week's evidence, built from weekly totals.
- Weekly totals only. No transactions, shopper, payment or item-level data required.
- Your sign-in. OpenID Connect through your identity provider, which your admin can set up in the product, and SCIM provisioning. Four roles, no passwords stored.
- Files in, nothing installed. CSV or Excel, uploaded, sent to the inbound API, or collected on a schedule from a folder you name. No agent on your side.
- Governed delivery. A recurring export is read against its own contract and reconciled to its control totals to the cent. A file that does not match is held, line by line, for an admin or analyst to decide with a reason.
- Access by region, district or store. A district manager can be limited to their own stores, enforced in the database and on every screen, document, email and export.
Open the Trust center, where every control carries its status and its evidence, or read the deployment notes.
Questions about Kelynto? Ask us.
Ask in your own words, or pick a question. Every answer carries a label: available today, available through enterprise implementation, planned, or not available.
What does Kelynto do?
Kelynto drafts the Monday business review for a retail planning team. Each week it takes sales against plan by store and category, plus in-stock, promotions and local signals, and drafts the review in three parts: what your own records show with an estimated impact, what is on file near your stores, and how much is not explained. The planner edits the draft, confirms or corrects what is on record, and publishes. It also shows what is coming near your stores in the next few weeks, and counts, from real use on its Score and learn page, whether its explanations are proving useful. It sits above the planning system you already use and replaces none of it. The quickest way to judge it is a 20-minute conversation about your own Monday review.
How is it different from a planning suite?
They do different jobs. A planning system produces the plan and the forecast, and often the orders that follow. Kelynto starts where that ends: it takes the plan you already have, compares last week's actual sales with it by store and category, and sets the variance beside the evidence: causes your own records show, with an estimated impact, and what a planning system does not hold, such as a storm, road work, a local event or a competitor opening near a store, listed as context. Then it records what your planner confirmed or corrected. It does not produce your plan or replace your forecast, and it writes nothing back; its Outlook sets what is coming beside your own plan or latest forecast, by cause, for your planner to decide on. You keep your planning system. Kelynto works from weekly files exported from it, so it sits above whichever system, or spreadsheet, produces your plan.
Can we offer Kelynto to our clients under our brand?
Yes. A partner's brand goes on what its clients read. Once your brand is recorded, the embedded views carry your name, your logo and your primary colour, and so do the documents Kelynto produces for the retailers you serve: the review as Word, PDF and PowerPoint, the emails a review is sent with and the Monday pack. The mail can carry your name as its sender, and can come from your own domain once that domain is verified. Embedded, your people read a client's review, Outlook, causes and This quarter inside your own application, with no second sign-in. Each client workspace also stays a standalone workspace its own people can open. To see it on synthetic clients, book a 30-minute partner conversation from https://kelynto.com/partners/.
Is there a partner API and a sandbox?
The developer documentation is public at https://kelynto.com/developers/: an overview, a quickstart in curl and Python from a key to a published review, the embedding guide, every route with its scope and error codes, and a Postman collection. For a sandbox, write to marc@kelynto.com with the subject Sandbox access, your company, your name and role, and the origin you will embed from if you plan to embed. You receive a base address and a sandbox key that reaches two synthetic client workspaces, and the synthetic clients the key makes itself, for 30 days. The key holds every scope, so a developer can send a file, produce and publish a review, download the documents, add webhooks and frame the embedded views. Every name in the sandbox is marked synthetic.
Which exports does it read as they are?
Kelynto reads the standard exports of Lightspeed Retail (R-Series and X-Series), Square for Retail, Shopify POS, NCR Counterpoint, Retail Pro and Microsoft Dynamics 365 Business Central (Item Ledger Entries), as well as an open-to-buy plan by month and class and a weekly recap with stores down the side and weeks across the top. On the first upload it knows the export by its columns, says which export it read the file as, and maps every column without a mapping screen. You can choose another export, or none, on the preview, and a saved source profile remembers the choice. Clover line items and RICS weekly sales are read with a ready-made mapping you pick on the preview. Each shape is built from the vendor's public documentation, and every file goes through the same validator as any upload.
Can it run in our Azure environment?
Available through enterprise implementation. The Azure deployment kit is the one that runs Kelynto Managed; in your subscription it is set up during the implementation. What the kit is: Bicep templates for a single-tenant install in your own subscription (Container Apps for the API, web app and scheduler, PostgreSQL Flexible Server on a private network, Key Vault, Log Analytics, optional Front Door), signing in with your own directory, plus scripts for preflight, deploy, validation, upgrade, rollback and uninstall. A private shape adds your existing virtual network, private endpoints, internal ingress and a database key you hold. The templates compile and lint, and the same container stack ran in production mode with a full onboarding rehearsal. The first deployment in your subscription is run with your team as its validation run. You own the subscription, network, keys and backups.
What data does a pilot require?
Five things; your own column names are fine. A store list with store code, region and coordinates for all or nearly all stores. Weekly sales and plan by store and category, the plan as it was approved: 26 weeks or more, 34 or more if you can. In-stock by store, week and category if you measure it, or an acceptance that stockouts will not be explained. A promotion calendar and a list of closures, remodels and competitor openings if you have them. And the commentary your team actually sent for the last eight weeks, held by a custodian on your side with those eight weeks of data until our set-up is frozen. Two facts before the first load: the day your fiscal week starts and the time zone most stores are in. CSV or Excel, aggregates only: no transaction, shopper or employee data. If your plan comes from a named planning system, we have a file recipe for its export.
How is our data protected?
The short version. Sign-in goes through your own identity provider, so passwords and multi-factor authentication stay with you; Kelynto stores no passwords. Each customer's data is separated twice, in the application and again in the database with row-level security that shows a connection carrying no workspace nothing at all. Four roles are checked on every request, and every change is written to an audit log. The product holds weekly sales, plan and in-stock totals by store and category, never shopper, payment or employee data. The AI writer is switched on per workspace, and the engine computes every number either way. Encryption in transit and at rest comes from the platform it is deployed on. Kelynto Managed runs on Microsoft Azure in Central US, deployed by an automated pipeline with health checks and automatic rollback. The Trust page lists every control with its status.
What does a pilot look like?
A pilot answers one question on your own data: would this planning team use Kelynto every Monday? It starts with a backtest we call the eight sealed weeks. You send 26 weeks or more of weekly sales and plan by store and category, your store list, and in-stock and promotions if you have them. A custodian on your side, outside the planning team, holds the last eight weeks until our set-up is frozen and recorded. We then run those eight weeks once and give you each week restated in three parts, a scorecard against bars fixed before anyone saw a result, and a written finding whichever way it goes. If it earns it, about eight live weeks follow, with one planner editing, confirming or correcting each week's draft. The measures are fixed in advance so the result is judged in the open.
Can we try it before speaking with sales?
Two self-service routes are built and open with the hosted service: a one-click sample workspace filled with synthetic data, and creating your own workspace with sign-in by emailed link. The site shows both links as soon as the product reports them as on. Today, without a call, you can take the product tour on the site, which shows real screens of the product with the synthetic demonstration retailer, read the deployment and trust pages, and ask this assistant. To see it working on your own questions, book a 20-minute conversation at https://calendly.com/kelynto/30min. You talk with the founder directly, with no sales process in between.
Start from your seat.
Each role asks different questions. Go straight to yours.
-
Demand planning leader
- What does my planner's Monday look like?
- How does it decide a cause, and can I challenge it?
- How will we know whether it works?
Next: Take the product tour
-
Merchandise planning leader
- What does a review by category look like?
- How is a promotion or a stock-out stated?
- What data do you need from us?
Next: Take the product tour
-
Supply chain executive
-
Operations leader
-
Enterprise architect or IT
-
Procurement or security reviewer
-
Planning service, software vendor or consultancy
-
Developer at a partner
- How do I get from a key to a published review?
- How do I show a review inside our application?
- Where is every route, scope and error code?
Next: Request sandbox access
Five ways to take the next step.
-
Explore
See the product
The product tour shows real screens of the product on a synthetic retailer, in the order a week runs.
A private copy of a synthetic retailer, Harborview Markets. No conversation needed first.
-
Evaluate with your data
Run it on your own weeks
Eight sealed weeks of your own history, run once and scored against bars fixed before anyone sees a result, then about eight live weeks.
Create a workspace and load your own files. Sign in by an emailed link. No password to create.
-
Review the security
Check every control
Kelynto Managed on Microsoft Azure or in your own Azure account, what crosses the boundary, and every control with its status and evidence.
-
Offer it to your clients
Build it into your service or product
For planning services, retail software vendors and consultancies: the partner API, embedded views and your brand, starting with a sandbox of synthetic clients.
-
Talk to us
Twenty minutes with the founder
Your process and your questions. Or write to marc@kelynto.com.