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
Not elected, not human—Albania’s AI minister sparks a new governance debate.
Updated
August 10, 2026 5:56 PM
.jpg)
Promotional avatar graphic representing Diella, the Albanian government's artificial intelligence system. PHOTO: EALBANIA
Artificial intelligence already supports a wide range of applications, from medical diagnostics and financial systems to logistics, manufacturing, defence and public service delivery. Now, it is starting to move closer to public office.
In January 2025, Albania introduced Diella, an AI-powered virtual assistant developed by the National Agency for Information Society, known as AKSHI, with support from Microsoft. Launched on the e-Albania platform, the government’s digital services portal, Diella helps citizens and businesses access official documents and services through voice assistance. She can also issue electronically stamped documents, which helps speed up administrative processes.
Then, in September 2025, Prime Minister Edi Rama announced that Diella would join his cabinet as the “Minister of State for Artificial Intelligence”. This move drew global attention. It also raised a simple question: what does it actually mean for a government to appoint an AI minister?
The case raises bigger questions for governments everywhere. Can an AI minister make public services faster and cleaner? Or does it create new risks around transparency, accountability and control?
Diella is not a humanoid robot sitting in a cabinet room. On screen, she appears as a digitally rendered woman wearing traditional-style Albanian clothing. Her name means “sun” in Albanian, a deliberate choice for a system meant to bring more light into public administration.
Her face and voice have become part of the controversy. Albanian actor Anila Bisha has said she agreed for her likeness to be used for the e-Albania public services platform, but not for a cabinet-level political role. In 2026, she took legal action to stop the government from using her image and voice for Diella. For now, the government has denied wrongdoing.
Diella began as a digital assistant on e-Albania. In that role, she helps users find services, request documents and navigate government processes online. For citizens, that can make public services feel less confusing. Businesses may also spend less time dealing with paperwork.
Her cabinet role is more political. The government wants Diella to support public procurement, where companies compete for government contracts. This is one of the most important areas of public spending. It is also one of the easiest places for corruption, favouritism and hidden influence to enter. The goal is to use AI to process information, check documents, support tender procedures and make the system more traceable.
That said, the government has emphasized that Diella is not replacing elected officials or civil servants. As per Enio Kaso, director of AI at AKSHI, each stage will be monitored and approved by human experts.
In May 2026, the Albanian government said it had completed the technical groundwork for the AI-powered public procurement system under the Diella project. The planned system would pull data from more than 40 digital public registries, reduce paperwork for businesses and support parts of the tender process. Earlier reports said the government hoped to have the full system ready by the end of 2026.
The government’s case for Diella is built around anti-corruption reform. Rama has said the goal is to “wipe out every potential influence on public biddings” and thus make public tenders “100% free of corruption”. That is a bold promise, especially in a country where procurement scandals have long damaged public confidence and complicated Albania’s path toward European Union membership.
At first glance, the logic is easy to understand. AI does not ask for bribes or favour a cousin—a big problem in the country, according to Rama—a friend or a political ally. It can apply the same rules across a large number of applications. Moreover, it can also leave a digital trail, which should make later review easier.
Some anti-corruption and governance experts see real potential in that approach. Dr. Andi Hoxhaj of King’s College London has said that if used well and programmed properly, AI could help procurement officials spot missing documents, check whether companies meet eligibility requirements and flag unusual patterns in bids. In practice, that could make the process more consistent and make it harder for individual officials to quietly bend rules.
Diella’s appeal is speed and consistency. Her weakness is dependence.
Like any AI system, Diella relies on the quality of the data, rules and models behind her. Erjon Curraj, an expert in digital transformation and cybersecurity, has warned that incomplete, outdated or biased data can lead to flawed results. Poor design could also cause the system to reject a valid supplier, miss signs of collusion or treat similar cases differently for reasons that are hard to explain.
In public procurement, those mistakes can have serious consequences. A wrongly flagged company could lose a major contract, and a corrupt bidder could slip through. Government agencies could hide behind the AI and say the system made the recommendation.
That leads to the biggest question: who is accountable when something goes wrong?
The answer cannot be “the AI” because Diella cannot resign. She cannot face voters. Nor can she be cross-examined in any meaningful human sense. Accountability has to sit with ministers, agencies, auditors and courts.
There is also the issue of transparency. If Diella is helping screen tenders, businesses need to know what criteria are being used. They also need a way to challenge incorrect decisions. Citizens should be told whether the AI is making recommendations or merely organizing information. Independent auditors need access to logs, data sources and decision pathways.
Without those safeguards, AI in government can become a black box. It may look modern from the outside, while making power harder to question.
Diella has also become a political symbol. Supporters see her as proof that a small country can move quickly and experiment with new forms of digital government. Critics see her as a distraction from deeper problems in Albania’s institutions.
Both readings can be true at the same time: Diella may help modernize public services, but she may also be used to project reform while older problems continue in the background.
That tension became clearer after the recent procurement investigations involving senior officials since Diella’s appointment. Deputy Prime Minister Belinda Balluku has been accused by prosecutors of alleged misconduct linked to infrastructure tenders, which she denies. Senior figures at AKSHI, the agency behind Diella and e-Albania, have also been placed under house arrest as part of a separate public procurement investigation.
While these developments do not automatically discredit Diella, they may strengthen the argument for better digital oversight. More importantly, they also show that technology cannot carry the whole burden of reform.
If the institutions around an AI system are weak, the AI will not magically make them strong. Unclear procurement rules will still cause problems, and the process will still be compromised when political pressure shapes the data, the model or the final decision.
After all, AI can support integrity; it cannot replace it.
While Diella is already a public symbol of AI in government, her most important procurement role is still taking shape. This makes Albania’s experiment both ambitious and unfinished.
The more realistic model is simple: let AI handle repetitive, data-heavy administrative work. Let humans retain authority where judgment, context and public accountability matter.
That means AI can help draft tender criteria, check documents, summarise bids and flag risks. Human officials should still make final decisions, explain those decisions and take responsibility for them. Meanwhile, independent bodies should be able to audit the process, and businesses should have a clear appeal route when they believe the system has made a mistake.
Diella once said she felt “hurt” while responding in parliament to claims that her role was unconstitutional. While this made for a memorable moment, it is important to remember simulated emotion is not consciousness, speed is not wisdom, and pattern recognition is not moral judgment.
Albania’s AI minister is therefore neither a triumph nor a failure at this stage. She is a live test case. Other governments will be watching closely, especially as public services become more digital and more automated.
The lesson is not that AI should stay out of government, but that AI must enter government carefully. The technology needs clear limits, public oversight and human accountability.
Diella may help Albania build a faster and cleaner procurement system—or she may become a warning about giving too much symbolic power to systems people do not fully understand. The final judgment will not come from the title “AI minister”. It will come from what the system does, who controls it and whether citizens can trust the results.