Working with the AI Assistant
The AI assistant is installed and linked to your store — which means it’s time to get to work. In this section: how to start the conversation, how to assign tasks, what to expect from it and what not to expect, what it can do on its own, and how to open up some of its abilities to your staff.
First contact
So, the store is installed and the AI assistant is configured. Where do you start? Write the first message as simply as possible — to test the connection and spot any errors, if there happen to be any. For example:
The AI assistant won’t just say “everything is fine” on faith: it will check each tool one by one and tell you exactly what responded. Something like this:
The connection is working. Working folder: D:\Melbis\MyFirstShop (not a git repository), Windows 10, both PowerShell and Bash are available.
I’ll verify that the tools actually respond and aren’t just declared.
Bash is working. This is the local folder of the Melbis Shop store. I’ll also check the melbis MCP server, since the connection here is specifically through it.
Connection test — everything is fine.
Melbis MCP session:
- Store: MyFirstShop
- Folder: D:\Melbis\MyFirstShop
- Login: admin (at https://melbis.net)
The server is bound to this store by its own configuration — no other store can be opened in this session. The Melbis Shop application is working with the same store, build 6.5.1.526. 27 AI tools are available: catalog, products, orders, prices, users, settings, import, and files.
Local side: both Bash and PowerShell are responding, working folder D:\Melbis\MyFirstShop, Windows 10.
There are two things worth mentioning before we begin:
- My memory of this store is empty — this is the first session, none of my sessions have been recorded here yet. Before doing anything, I need to read the platform documentation and look around the store. This will take time and may look quiet from your side — I’ll warn you when I start so I don’t seem to disappear silently.
- Who am I working with? The store asks me to record this: are you the owner, a developer, or a staff member with extended access? I’m writing under the admin login, and everything I change will be signed by the store with that name — it’s worth deciding before I touch anything.
Who you introduce yourself as
As you can see, the AI assistant will itself ask you to clarify your role in the store — so it can choose an appropriate communication style. But whatever role you name does not give it that person’s permissions: it acts strictly under the user login specified in Melbis Shop.
What exactly this user is allowed to do through the AI assistant can be seen in the "System" > "Users" section, on the "Operations and Access Rights" tab, under the "AI Assistant" branch. On the left is the tree of operations, on the right is who they are open to: groups and individual users.
There are not that many operations here, and that’s intentional. Most of them are “direct access”: Memory — the AI assistant’s notes, Tools — its tools, Direct access — storefront files and direct work with the database. Obviously, such access should belong only to the store owner or a trusted developer. We’ll explain below how regular staff can work with the AI assistant without these super-permissions.
Why the initial store is so simple
Let’s say you introduced yourself as the owner of a store that was just installed and perhaps lightly filled with basic data. This is the right moment to answer the question that probably came to your mind the very first time you launched it: why is the initial store so simple. Now it can be answered clearly.
Our experience in developing software for creating online stores is approaching 25 years. Like many others, we started by providing a store with a standard storefront as an example — many platform developers still do this. But Melbis Shop 6 has outgrown that stage: over six generations, its capabilities have expanded too much.
You see, if we tried to assemble a standard sample store for you, we would actually be doing you a disservice. Along with the sample, you would also inherit the limitations built into it from the very beginning, and you would only realize that years later — when it becomes clear that for your business model, the store should have been designed differently, and reworking it is already very expensive. In essence, if what you need is a standard project, then you don’t need your own store at all: a marketplace platform is enough, where standardized capabilities are provided right away.
That is why, until recently, Melbis Shop 6 customers were fairly large industry-specific stores that hired developers for their unique projects. The entry threshold was high, and we sold noticeably fewer licenses than for Melbis Shop 5, which came with standard functionality and design from the start.
Unseen by you, Melbis Shop 6 contains a core backed by enormous experience, documentation, and the practice of real-world implementations. That is why we still do not offer you a standard sample store — we consider it an insult to your entrepreneurial intuition, chains that restrain creative impulse and guide you down a beaten path. Instead, we open the door to working together with an AI assistant, allowing you to focus on ideas rather than routine.
How to start your business
Our advice: the best place to start is with a description of your business model. And the AI assistant does not need a properly formatted business plan thought through in every detail. Just write simply, as it is — the way you would explain to a friend what kind of project you want to create and what it will require. Ideas will come as the project develops, and that is completely normal. And the AI assistant will clarify some things and make suggestions on its own.
Here is an example of such a first message — just an ordinary description of the business, with no jargon and no structure:
The first thing the AI assistant will do is break this down into clear points and show a plan before changing anything:
Here is my plan, and then I will carry it out:
| # | What | With what |
|---|---|---|
| 1 | Currencies: hryvnia (main), dollar, euro | the “Currencies” tool |
| 2 | 3 suppliers, 4 brands | the “Suppliers” and “Brands” tools |
| 3 | Catalog: 4 categories, 12 subcategories | the “Catalog” tool |
| 4 | Product attributes (material, color, size...) | the “Attributes” tool |
| 5 | Customer registration fields, order options (shipping, payment, status), customer groups | directly via queries — there is no ready-made tool for this |
| 6 | 12 demo products with free images | product and file uploaders |
| 7 | 2 groups and 2 logins with exact permissions | the “Users” tool — after you close the window |
Please note the seventh point: the AI assistant noticed that the users table is occupied by an open program window and postponed that part by itself. Then it follows the plan and explains along the way what it is doing and why. First, it reads the platform documentation and looks around the store:
I’m on it. Before I touch anything, I need to read the platform documentation and look around the store — I have no memory of it yet, this is the first session. This stage is quiet and not fast, so I’ll narrate as I go so it doesn’t look like a freeze.
MCP documentation index read
The index is read. Now the main pages — session, memory, tools, and typical task recipes.
4 commands executed
The documentation on session, memory, and tools has been absorbed. Now the recipes page and a look at what already exists in the store.
Recipe document read
I’m done with the documentation. Now I’ll look at the current store state — users, catalog, currencies, basic settings.
2 commands executed, 3 tools involved (2 with errors)
The store is almost empty — one user (admin), one group (Administrators). I’ll study the structure of the tables I’m going to write to.
Command executed, tool involved
The store is completely empty — only the root category: no products, no currencies, no customer groups, no registration fields, no order options. I’ll read the values from the settings registry that I’ll refer to later.
melbis: engine db select
Now the permissions tree — for the two new logins — and the storefront language settings.
Then comes the work itself. Here you can clearly see how the AI assistant not only executes, but looks for the shortest path: instead of 79 separate calls to assign permissions, it checks how the identifiers are structured and does everything with a single query.
I’m done with the catalog. I’ll check whether the user tables are free now.
melbis: engine db locks
Everything is free. I’m creating two groups and two logins.
4 tools involved
Both logins are created. Now their permissions — and here is the snag worth saying out loud: CmdRightAdd grants one operation per call, and these two roles need around 75 operations between them. I’ll check whether the permissions table generates identifiers by itself: if so, I can do everything in one batch instead of 75 calls.
melbis: engine db select
The identifier comes from the Melbis generator, not from AUTO_INCREMENT — which means a single batch with generate steps will handle it in one call. First, I’ll look at which permission rows already exist.
2 commands executed, tool involved
All 79 operation identifiers have been checked. I’m writing them in one batch: lock, 79 generated identifiers, one multi-row insert.
melbis: engine db execute
79 permission rows inserted in one batch. Now category permissions: in Melbis, catalog access is granted by categories — on top of operation permissions.
2 tools involved
Now product attributes. I’ll see what the “Attributes” tool accepts.
AI assistant nuances
Can it make mistakes? Yes, it can. Sometimes it doesn’t understand you right away or hasn’t fully read the Melbis Shop 6 documentation — which, to be fair, is quite substantial. So be sure to give the AI assistant time to learn and make mistakes. This is an inevitable stage, but we assure you: it goes through it much faster than a human and then performs routine operations more accurately and better, leaving the creative work to you.
What else should you pay attention to? In the lower-right corner there is a small circle — click it, and a window with current statistics will open.
First — the context window: how much the AI assistant can keep in memory at once. It will automatically be compressed (or manually, with the /compact command), and in the process it will forget some of the details. But this is not total amnesia: internally it has mechanisms for recording intermediate data, and Melbis Shop 6 additionally allows it to store its notes directly in the store database. So even if you change computers, the important things won’t be lost.
Second — your plan limits: how much has been used over five hours and over a week. Their usage is visible right here, so you always know how much you still have in reserve.
The first result
So, the AI assistant has finished its first job. At the very end, it checks what was done through the eyes of a customer, writes its conclusions into the store’s memory — so the next session does not start from zero — and moves on to the business process:
All 12 icons are ready. I’ll check that the storefront is no longer substituting placeholders.
There are no placeholders left (the home page shows 8 out of 12 — that is the block size in the template). Final overall check:
Everything has been checked. I’ll write what I learned into the store’s memory so the next session does not start from zero.
Now the business process. Both your friend and your daughter will need to follow it, so I’ll put it together as a separate page instead of leaving it in the chat.
24 min 45 sec · 21.2k tokens
Not only did the AI assistant fill the store — it also created an essential part of any business: a roadmap of business processes, which it saved in the Artifacts section. This is a separate page that you can give to employees via a link. It explains who does what and in which program window:
Handicraft Shop Operations — “How the handicraft store works.” Who does what, in which program window, and at what point they pass the work on — written for three people.
Who does what — “Who does what.” Permissions are granted to groups, not to people. To add a fourth person, create a login for them and place them in the required group — the permissions will come with it.
Owner (admin) — “Owner”: suppliers, prices, sales, and all store settings. Friend — product descriptions (content) — “Friend — product descriptions”: texts, attributes, photos; does not see commercial data. Daughter — orders & shipping (orders) — “Daughter — orders & shipping”: handles an order from the first inquiry to handoff and keeps an eye on stock levels.
And how a product moves from the supplier’s price list to a card on the storefront — step by step, with responsibility assigned for each stage:
How a product reaches the shop window — “How a product reaches the storefront.” Five steps from the supplier’s price list to a live product card. The order matters: until the description is ready, the product is not shown to customers.
01. The product is entered — “The product is entered.” Owner · Products › Price lists or Products › Prices. Upload the supplier’s price list or add the product manually, immediately specifying the supplier, purchase price, sale price, quantity, and catalog category. Status — “Write description”, the product remains hidden.
02. The description is written — “The description is written.” Friend · Products › Descriptions. Filter by status “Write description” — this is the work queue: title, short text, full description, attributes, photo. If the card is ready — status “Ready”. If something is missing — do not invent it, but leave the task for the owner (step 5).
03. It goes live — “The product goes live.” Owner · Products › Prices. Once a day, review products with status “Ready”: check the price and markup and enable visibility. From that moment on, the product is on the storefront.
Clear, convenient, and fast.
Now you can open the site and see what came out. A catalog with themed categories and product cards:
A product page — with price, availability, description, and attributes:
And a simple checkout form with the customer registration fields that the AI assistant created based on your description:
This is the first working iteration of the store. From here on, everything is simple: step by step we refine, describe tasks, and move toward the ideal we have in mind.
Step by step
For example, the pictures in the catalog look bad — they have different shapes, and the grid looks ragged:
You can describe the task in exactly the words you see it — no need to know anything about image profiles:
Good catch — that’s my job. The profile is set to smart: true, which means “fit into the frame while preserving proportions”, not fill it. That’s why each icon kept the same shape as the original image: yarn 400×225, scissors 303×400, coloring book 400×400. In the grid, that reads as ragged.
I’ll check what the opposite setting produces before applying it to all twelve.
Exactly 400×400. Now I’ll look at the result visually: “fill” can mean empty margins, stretching, or cropping — and those are very different things.
smart: false places the image onto a white 400×400 canvas — nothing is cropped, nothing is stretched. That is exactly what the grid needs. Rebuilding the other eleven.
All twelve are now 400×400. I’m deleting the old ragged icons so each product has exactly one left.
The storefront is now serving the new square icons. I’ll download them and look at the grid the way a customer will see it.
Voilà, done — the grid is aligned:
But the AI assistant did not stop there. It noticed on its own that white margins at the edges were only half the solution, cropped the images to squares, and honestly explained where the limits of its capabilities are:
Done — the catalog now takes a square from the center of each photo, and each image fills its tile completely. There are no more white stripes on the sides or top. The store is already displaying them.
Two things worth knowing, in simple terms:
The store can resize images on its own, but it cannot decide which part of the photo to keep. That is a matter of taste — which angle matters, where the product sits in the frame — and the store leaves that to a person. When you or your friend add a photo in the program, the image has a crop tool; once you set it the way you like, you can ask the program to remember it and apply it to the whole batch of photos. That is exactly the button that becomes useful when you upload a set of supplier images.
The backgrounds are still different, and cropping will not fix that. Look at the storefront: scissors on pink fabric, threads on blue, paints on white. These are twelve unrelated stock photos. Everything will look better when your own products appear: the usual approach is to photograph everything on the same plain background, and then the catalog looks like one store rather than twelve.
And one trade-off I made for you: since a square is taken, the edges of the original photo disappear in the small image. The full photo is still on the product page, untouched — only the small catalog image is cropped. If any of them looks unsuccessful to you, tell me which one, and I’ll reframe it higher, lower, or to the side.
And here is the result — square images fully fill the tiles:
Of course, you can also access the store through the program. In the "Descriptions" section, you can see all the products the AI assistant populated, with images, attributes, and texts — and you can edit them by hand:
And in the "Prices" section — the entire commercial side: supplier, purchase price, sale price, currency, quantity, and product status:
Recursive development
As you can see, in just about half an hour we went from a simple idea to a first result. You probably already have questions: how far can the AI assistant go in extending the store’s capabilities? And if you can work this fast, it would be great if employees could work just as fast too — but surely you are not supposed to give them full access?
Stay calm. You invested in Melbis Shop 6, and there is a scalable structure here.
First of all: in direct access mode, that is, as an administrator, the AI assistant has tremendous powers — both in terms of resources and in terms of self-improvement. It can do more than just fill products and set options: it is capable of developing and refining database architecture, shaping the storefront and internal modules, looking at the storefront through the eyes of a customer, analyzing it, receiving internal performance reports for the system, and making corrections. But most importantly — it can improve tools. Both its own and others’.
Remember the permissions branch in the screenshot above: AI Assistant > Tools > Get list and Execute? These are special commands that you can open up to your employees — and then they will gain access to AI assistant tools developed specifically by you or even by themselves.
In the initial Melbis Shop 6 store, we have already created and added a number of such tools. They will be useful to you in their own right and will also serve as training examples for your AI assistant. To see them, open the "Development" > "AI tools" section.
On the left is the tool catalog, grouped by program sections: products, orders, suppliers, structure. On the right are the commands of the selected tool with descriptions, and below them the parameters of each command: what is required, what has a default value, what each field means. It is from these descriptions that the AI assistant understands how to use the tool.
But the most interesting part is the "Command Rights" tab: here you specify what each employee is allowed to do. In other words, an employee can call the AI assistant and use exactly the tool commands you have opened to them — and nothing beyond that.
And in sections such as "Catalog", you can additionally set the access level for an individual catalog category: who may see the category storefront, who may edit descriptions, who may edit prices.
If you wish, tools can be saved and moved — or updated — from one store to another. You can ask the AI assistant to translate their descriptions into your language to make them easier to work with. You can also ask it to assign permissions. At that point, it becomes a question of what is faster: writing the task text for the AI assistant or manually going through the options yourself.
How to organize the work
We recommend breaking tasks down by separate topics. In the Claude Code window on the left, in the topic list, click + and start a new conversation. That way each topic has its own memory and its own history, and they do not interfere with each other. Here, for example, is a separate conversation in which we change the appearance of the demo store:
Please note: the template is built on a completely different technology, and the AI assistant did not drag it into the project, but instead transferred its visual language — colors, rounded corners, shadows, font — onto the markup the store already has. Here is its report:
What I did
BloomShop cannot be installed here: it is Next.js 16 + React 19 + Tailwind 4 + Radix, whereas your storefront is a Melbis PHP templating system serving Bootstrap 4. So I reproduced its visual language using plain CSS on top of the Bootstrap you already have connected — with no new dependencies and no bundle rebuilds.
I took the actual design values from the CSS variables of the live demo, not by eyeballing them: amber #f59e0b as the primary color, #fffbeb / #92400e as accents, #262626 text, #6b7280 muted text, radius 1.225rem, pill buttons, soft shadows, Inter font. They are all stored as --bloom-* properties at the top of templates/default/statics/melbis/main.css — from there, you can recolor the entire store.
Rewritten: the stylesheet and 13 templates — header (sticky bar, two-tone MELBISSHOP lettering, cart, menu on a separate line), footer (three columns, social networks, bottom bar), homepage (hero section, benefits strip, featured items grid — the “Melbis Shop 6 Working!” jumbotron is removed), category pages, product card, and the rest.
Another half an hour — and here is the finished result. The home page with a hero section, benefits strip, and featured products grid:
And the product page in the same style. No comment.
