Led by co-founders Andrew Raslan and Keyvan Jodeiri, Pipeline Organics is developing microbial fuel cells to help food and beverage manufacturers treat wastewater and recover energy as electricity.
Updated
November 16, 2026 12:32 PM

Concept visualisation of Pipeline Organics’ planned TankArc wastewater treatment and energy recovery system at a brewery. IMAGE: PIPELINE ORGANICS
A glass of beer or a bottle of soft drink leaves plenty behind before it reaches the shelf. Producing it requires water and electricity, then creates wastewater that manufacturers must pay to treat. For breweries and other food and beverage manufacturers working with tight margins, those bills can leave less money for new equipment, products and people.
Pipeline Organics, led by Andrew Raslan (commercial) and Dr Keyvan Jodeiri (technology), sees a resource in that waste. The Nottingham-based cleantech startup, Pipeline Organics, is developing microbial fuel cells that treat food and beverage wastewater while generating electricity. The aim is to help factories lower their operating costs by recovering value from a stream they already produce every day.
Founded in August 2021, Pipeline Organics grew out of the University of Nottingham’s Young Entrepreneurs Scheme, YES20. The founding team won its Engineering, Energy and Environment stream before establishing the company. Andrew, now CEO, brought a background in molecular microbiology and antimicrobial research, later moving into project management and commercialization.
Co-founder and chief scientific officer Keyvan Jodeiri brought a different piece of the puzzle. His research explored biofuel cells that could use sugars in blood to generate electricity for medical implants. The team began asking whether related principles could work outside the body, using organic material in industrial wastewater as fuel. Turning that idea into a business meant finding an application where the environmental benefits came with a clear financial incentive.
Food and beverage manufacturing offered that opportunity. Breweries and other food and beverage manufacturers produce wastewater rich in biodegradable organic material such as leftover carbs and fats or dead proteins, making it suitable food for microorganisms. Treating it at the factory also gives the company a more predictable waste stream than the mixture arriving at a general sewage treatment plant.
“What is filthy for you as a manufacturer is food for the bacteria,” Andrew explains.

The company’s system, TankArc, contains reactors with specially designed, 3D-printed lattices. Microorganisms growing on the anode break down organic material in wastewater, releasing electrons that electrodes capture as electrical current. This reduces the organic pollution load while recovering some of its energy. Reactors can be grouped into racks or, eventually, containers equipped with plumbing, batteries and controls to serve different factory sizes.
Andrew describes the system as being designed to become self-powering, provided its electricity output scales as expected, with surplus energy available for use on site. At the moment, replacing a brewery’s entire electricity supply is beyond the immediate promise, Andrew admits. The more practical proposition is reducing the amount of power a manufacturer needs to buy through site efficiency upgrades, while cutting its wastewater treatment burden.
The treated wastewater would then go into the sewer for further treatment. Since it contains fewer pollutants, manufacturers could pay less in treatment charges or, in some cases, avoid them altogether. Pipeline Organics is also exploring ways to take the process further by working with partners to make water reuse possible. This could allow manufacturers to reuse the treated water for tasks that do not require high-purity water, such as post-production washing, which accounts for a large share of fresh-water use in the industry.
Much of TankArc’s engineering sits in the lattice itself. It needs sufficient surface area for the biological process while allowing wastewater to flow through without clogging. Different waste streams require different designs. Pipeline Organics combines engineering calculations with proprietary AI-assisted algorithms to adapt the geometry for applications such as beer, wine or fruit juice production.

Andrew sees this design process as a competitive advantage. Once the geometry has been developed, components can be manufactured from the resulting 3D models. The difficult part is knowing how to design a cell that performs in a particular environment.
The company is competing with established wastewater treatment and energy recovery methods. Anaerobic digestion, for example, produces biogas that can subsequently generate heat and electricity. Pipeline Organics is pursuing direct electricity recovery through compact, modular equipment. Its suitability will depend on the site, the wastewater and the savings it can deliver.
Early brewery trials have helped the team test those assumptions. At Little Ox Brewery, Pipeline Organics used a compact four-reactor system with real wastewater to assess compatibility and electrical output. The trial also provided practical lessons about monitoring, handling and operating equipment around a working production site. The company is working with Castle Rock Brewery in Nottingham as another development partner and have achieved onsite results that are close to commercial readiness.
These demonstrations represent an early step towards industrial deployment. During our interview, Andrew said Pipeline Organics had begun selling paid feasibility pilots that measure performance using customers’ wastewater under actual operating conditions. Larger reactor racks would be at the next stage, followed by containerised systems for facilities producing much greater volumes of effluent. They expect to deploy full-scale containers in 2027.
Scaling brings another set of challenges. The team is developing repeatable methods for producing conductive electrodes, maintaining wastewater flow and assembling larger systems. Reducing manufacturing costs while maintaining treatment performance is a central part of this work.

There will also be useful discoveries along the way: Chief Scientific Officer Keyvan says longer-term ambitions include developing the technology for wastewater sensing and exploring how recovered electricity could support electrochemical production of higher-value chemicals. These could open additional applications for the platform, while the immediate priority remains manufacturing and scaling the wastewater treatment system.
The proposed leasing model reflects the focus on customer economics. Manufacturers would rent equipment rather than purchase it upfront, retaining part of the savings after paying Pipeline Organics. Making that arrangement attractive requires dependable treatment, manageable maintenance and savings that hold up over time.
Andrew’s and Keyvan’s longer-term vision includes a wider portfolio of environmental technologies. For now, the next test is closer to the brewery floor: can the company turn promising small reactors into equipment food and beverage manufacturers can rely on?
“One man’s waste is another man’s raw material if you’re smart about it,” Andrew says. Pipeline Organics is building its business around that possibility, starting with the water left behind by a drink.
Keep Reading
As workplace knowledge spreads across chats, AI firms are building systems that can structure, retrieve and preserve it over time.
Updated
August 10, 2026 5:56 PM

A messaging app on a phone. PHOTO: ADOBE STOCK
Votee AI, an enterprise AI company headquartered in Hong Kong, has partnered with its Toronto-based research lab Beever AI to launch Beever Atlas. The new platform is designed to turn workplace chats into searchable knowledge that AI systems can retrieve and understand.
The release focuses on a growing issue inside organisations. Much of today’s workplace knowledge now exists inside chat platforms such as Slack, Microsoft Teams, Discord and Telegram. Important discussions, project decisions and technical information often disappear into long message histories that are difficult to search later.
Beever AI developed the platform to organise those conversations into a structured system for AI assistants. The software connects with Telegram, Discord, Mattermost, Microsoft Teams and Slack, then converts conversations into linked records of people, projects, files and decisions.
The collaboration combines Votee AI’s enterprise infrastructure work with Beever AI’s research around AI memory systems. The companies are releasing two versions of the product. The open-source edition is aimed at individual developers, researchers and creators. The enterprise edition is designed for banks, government agencies and larger organisations with stricter security requirements.
The release also reflects a broader shift happening across the AI industry. Companies are increasingly looking at how AI systems store and retrieve long-term knowledge, rather than relying solely on large context windows or search-based retrieval.
Earlier this year, OpenAI founding member and former director of AI at Tesla Andrej Karpathy discussed the growing need for what he described as “LLM Knowledge Bases.” He argued that AI systems need structured and evolving memory rather than depending only on context windows and vector search.
Beever Atlas approaches that problem through workplace communication. Instead of focusing mainly on uploaded files, the system is designed around conversations that happen daily across team chat platforms. It can also process images, PDFs, voice notes and video files within the same searchable system.
The companies say the software is designed to work directly with AI assistants and coding tools such as Cursor, AWS Kiro and Qwen Code. Integrations for OpenClaw and Hermes Agent are expected later in 2026.
Pak-Sun Ting, Co-Founder and CEO of Votee AI said: "Hong Kong has always been known for property and finance. Beever Atlas is proof that world-class AI infrastructure can emerge from an HK-headquartered company and be shared openly with the world. Every growing organization faces the same silent liability: conversational knowledge loss. Beever Atlas turns this perishable resource into a compounding organizational asset."
A large part of the enterprise version focuses on privacy and access control. The system mirrors permissions from Slack and Microsoft Teams so users can only retrieve information they are already authorised to access. Permission updates are reflected automatically when access changes inside company systems.
The enterprise edition also includes audit logs, encryption controls and data retention settings for organisations handling sensitive internal data. Companies can run the software entirely inside their own infrastructure using Docker and connect it to their preferred AI models through LiteLLM.
The companies argue that organising information is more useful than simply storing chat archives. Jacky Chan Co-Founder and CTO of Votee AI said: "The key technical decision was to treat agent memory as a knowledge engineering problem, not a retrieval problem. Structure beats similarity — a typed graph of who works on what is more useful to an AI than vector search over a Slack archive."
The software also includes protections against prompt injection attacks and systems designed to reduce hallucinated responses. According to the companies, the AI is designed to return “I don't know” with citations when confidence is low instead of generating unsupported answers.
As workplace communication becomes increasingly fragmented across chat platforms, companies are beginning to treat internal conversations as information that AI systems can organise, retrieve and build on. Beever Atlas reflects a broader push to turn everyday workplace communication into long-term organisational memory.