How to market chemical products more efficiently

Logo Covalo (ehemals Chemberry)

“The Karakun AG team has been a cooperative, proactive part of the project from the very beginning. Their many years of experience in the agile development of web-based software projects as well as their extensive know-how in language analytics, search solutions and user experience were an absolute game-winner in the project.”

Timo von Bargen, Managing Director

Chemberry Netzwerk

Download the complete case study (PDF)


Chemberry was re-named Covalo after spinning-off from Clariant in March 2021. Covalo is available at For more info, please read the press release by Clariant AG.

It is becoming increasingly important (and at the same time more difficult) for chemical companies to market their products online. Existing offers often mean high running costs and possible lock-in effects for manufacturers – and buyers often fall back on outdated information from an incomplete supplier base. This is one reason why around 80% of B2B chemicals buyers start their online search on Google & Co. And before they even contact a manufacturer, the purchasing process is already well underway, a result that is not always satisfactory for either side…

Against this background, the Swiss chemicals group Clariant AG launched a project within its digital innovation team in 2017 to design, create and operate an innovative marketing platform. The aim of this online offer, known as Chemberry (as of March 1st, 2021: Covalo), is to make it easy to find the chemical ingredients required for the production of consumer goods and to put manufacturers of consumer goods in touch with suitable ingredient suppliers.

The foundation – high quality, comparable data

Chemberry collects a large proportion of the required data (offered ingredients and their properties) via crawling and automatic information extraction directly from suppliers’ websites. A supplier can optionally change or extend this data at any time.

To obtain a basis for the conception of the crawling strategy, individual websites were analyzed by Karakun experts. This research provided insights into the relevant ingredient properties, the technical terminology used as well as for the requirements for the crawlers and tools for information extraction to be developed. By combining the collected information, the team was able to design and implement an analysis pipeline that regularly visits the provider websites, extracts relevant information, stores it in a uniform data structure and assigns it to specific products. It was only this step that ultimately enabled automated processing and easy comparability.

Simple, intuitive and intelligent search

In the next step, the requirements for the central search function were analyzed and corresponding suggestions were developed, such as auto-complete, intelligent correction suggestions, synonym search and semantic search filters. Subsequently, the formal data model for the search index as well as the information flow for the users was defined. The search function was implemented using Karakun’s own  HIBU platform.

Agile implementation of market requirements

From the very beginning, the Chemberry platform was developed with a “Lean Startup” approach. It was brought to market at an early stage, development cycles were kept short, and each development step (as well as the viability of the business model) was tested on the market, findings being incorporated into the design of the next iteration. At the beginning of the project, a Proof of Concept (PoC) was thus created with few data and a simple user interface. This resulted, in just a few further iterations, in a Minimal Viable Product (MVP), with a far larger volume of data from many available supplier websites, basic functions and improved, more comprehensive overall presentation of information.

Meanwhile, new features and entire thematic function blocks have been regularly developed and rolled out in an agile approach. Thus, in addition to the market segment “Personal Care” (body care), the segment “Home Care” (detergents and cleaning agents) was developed. When searching for products, users now additionally have access to dynamic, intelligent correction functions, personalized functions such as search history and bookmarks/favorites as well as a search within the bookmarks. New features also include flexible graphical data mining tools that can be used to detect new trends in product data and (anonymized) user data. Besides, various subscription models have been integrated as well as convenient contact features for buyers and suppliers.

Milestone attained

Together with our customer, we have created and introduced a radically new global industry platform. The USP of Karakun in this project was a mix of comprehensive expertise from different areas. While the UX team from the very start focused the project on the user, our specialists in the areas of language technology, search and software engineering ensured that customer requirements were implemented on time and within budget, using an agile approach.

The platform, operated on the Amazon cloud AWS, has a rapidly growing user base and over 40,000 registered products. Regular web crawling ensures that data are continuously updated, reducing manual effort and costs for manufacturers, and giving buyers access to up-to-date information. Karakun provides further development and maintenance of the application as well as support regarding the technical operation, customer onboarding and users. Software-related measures for search engine optimization (SEO) are also an ongoing task.

Together towards the future

A long-term vision exists too for the future. With the requisite input from Clariant AG, Karakun will continue to develop the platform to improve usability and collaboration between all parties involved.

Did we spark your interest? Get in touch with us!

write email
Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google