Skip to content
Amsby

Dedicated teams

From a dedicated team to an AI programme for KatanaPIM.

Amsby set up a dedicated team of four specialists in India for KatanaPIM, then built a data onboarding automation and two AI agents for release notes and support.

Client
KatanaPIM (katanapim.com, opens in a new tab)
Sector
Enterprise SaaS PIM platform, Leiden
Type
Dedicated team, automation and AI agents
Engagement
02 · Remote
Location
Leiden ↔ India
Team
  • 3 senior .NET developers
  • Software tester

About KatanaPIM

KatanaPIM is an enterprise SaaS Product Information Management (PIM) platform for online sellers, based in Leiden. Its promise is “Publish once, sell everywhere.” Brands use it to centralise product data from suppliers, ERPs and spreadsheets, enrich it with translated and SEO-optimised content, validate it through custom workflows, and distribute it to sales channels such as Shopify, Magento, BigCommerce, WooCommerce, Amazon, bol and Zalando.

The challenge

As a SaaS product company, KatanaPIM had to keep developing its core platform while also delivering implementations for a growing list of e-commerce customers, each with its own catalogue structure, channels and integrations. That combination needs senior .NET engineers who can work independently on a complex multi-tenant product, backed by solid QA so releases don’t break live customer catalogues.

Our approach

Our way of working is trust first, scale second: we prove our value on real work, and only then grow the relationship. Amsby set up a dedicated team in India that worked as part of KatanaPIM’s own product and delivery organisation:

  • 3 senior .NET developers for platform development, customer implementations, integrations and APIs.
  • 1 software tester for functional and regression testing of platform releases and customer implementations.

The team delivered and supported KatanaPIM implementations for e-commerce brands across very different product categories, from baby products and Asian food to wallpaper, wine and guitar parts.

From team to AI programme

After years of working on the platform, KatanaPIM came back to Amsby for automation, and then for two AI agents. One client, a growing relationship: from development capacity to AI that works across product, marketing and support.

Product data onboarding automation

Every new PIM customer starts with the same hurdle: getting their existing product data into the PIM. For manufacturers this usually means a large ERP export with dozens of Dutch-labelled columns, covering article numbers, EAN codes, units, shelf-life rules, pallet configuration and more. None of it matches the PIM’s data model, and mapping it by hand is slow and error-prone.

  1. The customer’s ERP export (Excel) is uploaded through a simple web form.
  2. All 40+ source fields are stored in a master data sheet, keeping a complete, auditable copy of the original data.
  3. A transformation step maps the source fields to KatanaPIM’s data model (SKU, name, description, GTIN, weight, unit, brand, category, supplier).
  4. The mapped data is written to five import-ready tables: Products, Stock, Suppliers, Descriptions and Categories.

Built with n8n and Google Sheets, the same mapping runs for every export and every update.

AI release notes from Jira

Every SaaS release ends with the same task: going through dozens of Jira tickets, working out which changes customers will notice, translating developer language into customer benefits and building a branded email. That took hours of a product owner’s time every release.

  1. When a release is marked as released in Jira, a webhook starts the agent automatically; a simple form also lets the product owner generate notes on demand.
  2. The agent collects every ticket in the Jira fix version and converts it into clean text.
  3. Claude filters out internal work, groups related tickets into topics, classifies them as New feature, Improvement or Fix, and scores their impact.
  4. Claude drafts the email in KatanaPIM’s established release-email tone, with “Learn more” links chosen only from a whitelist of real help-centre pages, so the AI cannot invent URLs.
  5. The draft is rendered as a fully branded HTML email in KatanaPIM’s house style.
  6. The product owner receives it marked DRAFT FOR REVIEW, with a reviewer-only panel showing which tickets each topic came from and which were excluded and why. Nothing reaches customers without human approval.

AI support assistant (RAG)

Support teams spend much of their time answering questions that have already been answered, in the documentation or in earlier tickets. Quality depends on who picks up the ticket, and real bugs can sit in the queue before anyone recognises them.

  1. Every night, an indexer collects the Confluence documentation and up to 200 recently resolved tickets, and stores them as vector embeddings in Elasticsearch, so every resolved ticket becomes part of the knowledge base.
  2. A Jira Service Management webhook starts the assistant as soon as a customer raises a ticket.
  3. The ticket is matched via vector search against the knowledge base, retrieving the 8 most relevant passages.
  4. Claude drafts a first response in the customer’s own language, bases every claim on the retrieved sources, cites them by number, and says so openly when the sources don’t cover the question.
  5. Each draft gets a confidence level and a recommended route: draft ready, needs more info, or escalate to development.
  6. The result is posted as an internal note on the ticket, so the customer never sees an unreviewed AI answer; likely bugs automatically get an escalation label.

At a glance

full-time specialists
4
brand implementations delivered
5
AI agents built
2

Projects

What the team built and maintained

  • Little Dutch

    PIM implementation

    The e-commerce platform for the Dutch brand of baby and children's products, including toys, accessories and lifestyle products.

    little-dutch.com(opens in a new tab)
  • Beagley Copperman

    PIM implementation

    An importer and distributor of authentic Asian food products, snacks and beverages.

    beagleycopperman.com(opens in a new tab)
  • Eijffinger

    PIM implementation

    A brand selling premium wallpapers, wall coverings and interior decoration products.

    eijffinger.com(opens in a new tab)
  • Delta Wines

    PIM implementation

    A wine distribution platform for managing and showcasing wine products, brands and distribution services.

    deltawines.eu(opens in a new tab)
  • Guitar Supplies

    PIM implementation

    An e-commerce platform for guitar parts, accessories and musical instrument supplies.

    guitarsupplies.nl(opens in a new tab)
  • Product data onboarding

    Data-mapping & import automation

    Maps a manufacturer's ERP export into KatanaPIM's data model and splits it into five import-ready tables.

  • AI release notes

    AI agent for release communication

    Turns every Jira release into a branded, customer-ready release email, with full traceability and human approval.

  • AI support assistant

    RAG agent for Jira Service Management

    Drafts grounded, source-cited answers to every new support ticket from documentation and past tickets, in the customer's own language.

Results

  • A senior four-person team embedded in an enterprise SaaS product company.
  • Five brand implementations delivered across baby products, food, interiors, wine and music retail.
  • Built-in QA that protects live customer catalogues during platform releases.
  • Customer catalogue data that is import-ready in minutes instead of being mapped by hand.
  • Hours of release-communication work reduced to a review, every release.
  • Support agents who start from a researched, source-cited draft, with nothing reaching the customer without their approval.

Technologies

  • .NET
  • C#
  • ASP.NET Web API
  • SQL Server
  • n8n
  • Anthropic Claude
  • OpenAI embeddings
  • Elasticsearch
  • Jira Cloud
  • Jira Service Management
  • Confluence

Grow your team with experienced developers?

On site, remote, a mix or per project. Dutch BV, Dutch contract.