June 8, 2021
From Rehab
Rehab Agency

Pill-ID - our latest hackweek!

We can finally reveal our latest creation! ūüĎÄ

Our hack week programme explores how technology can be used for good and this time, working alongside Herezie earlier this year, we created Pill-ID.

Pill-ID is a prototype experience that uses machine learning to help identify MDMA based pills using your phone camera as the input. It analyses the photo and then references a database to provide information on what the pill may contain.

More detail about the experience can be found on the website here: https://www.pill-id.info

And the press release is below:

UK and French Agencies Unite - Life-Saving App Developed to Scan MDMA Pills

  • Rehab and Herezie, through ‚ÄėBy The Network‚Äô collective, have teamed up to develop a working prototype of life-saving app
  • With drug usage on the rise and nightclubs looking to re-open this summer, harm reduction from drug use has never been more important¬†

London, 8th June 2021 - UK creative technology agency Rehab and French advertising agency Herezie have today announced the prototype for Pill-iD, an app that allows users to scan pills used in recreational drugs with a phone camera, giving them an instant identification of the pill, it’s likely dosage, risk-level and predicted side effects. 

Class A drug-taking is at record levels in the UK - the ONS crime survey 2020 shows that around 1.3 million adults aged 16-59 took a class A drug last year. Contrary to beliefs, the rise isn‚Äôt just limited to young students, but also people working office jobs, parents, business owners - it‚Äôs people from all walks of life. As the roadmap out of lockdown is now known and people begin to anticipate festivals and nightclubs opening, the need for drug harm reduction has never been more urgent. Some relevant charities are worried that ‚Äėpent-up‚Äô energy could increase the amount people take.

Users simply open the app and can either use their camera to take a photo of a pill, or upload an existing picture. The app’s machine learning model, tensorflow.js (a google technology) will then try to identify the drug by searching Nuit-Blanche, a database on different known narcotics in the European market, before showing the user a likely match. All user data is kept completely anonymous and is untraceable. The app strictly never encourages drug use, but simply educates on the known risks and information of each one. The aim of the project is to recognise the widespread usage of recreational drugs like MDMA and reduce harm - it was developed with the founding principle of hoping to save just one life.

The app is the latest output to come from ‚Äė‚ÄėBy The Network‚Äô, a democratic network of 16 independent agencies curated by Per Pedersen - where agencies share brief across disciplines to deliver exciting innovations. The idea was born out of Herezie and made possible by Rehab‚Äôs ‚ÄėHack Week‚Äô programme, where the agency sets aside a week to find creative solutions to pertinent societal issues. Each ‚Äėhack‚Äô focuses on a topic the team feels passionately about and utilises Rehab‚Äôs diverse skills and expertise as creative technologists, using the same creative process that the business employs on its client work.¬†

Pill-iD currently exists as a working prototype, with the goal of being released by Winter 2021. It offers an exciting example of how machine learning and AI can be used to help people and even save lives. 

Rob Bennett, CEO of Rehab, commented: ‚ÄúThe issue of recreational drugs and the need for harm reduction are a critical health problem across Europe, and we‚Äôre proud to have developed this app with Herezie. The topic is undoubtedly taboo for some, but our Hack Weeks all aim to address real, societal issues - which this very much is. Recreational drug use should not be encouraged, but using technology to help people absolutely should be. If we can save just one person‚Äôs life with this app, then we‚Äôve done our job.‚ÄĚ

Visit www.pill-id.info for more information and to view a video of Pill-iD working.


Rehabstudio Limited and Herezie Group do not, in any way, condone recreational drug use. The purpose of this tool is explicitly for informational purposes and harm reduction. Completely accurate identification of drugs cannot be guaranteed and you should not take any drugs based on identification by this tool. The database used is nuit-blanche.ch and you can read their full legal notice there. The possession, consumption and trade of most of the substances on this database are illegal (and, as such, you should not take them), and all of the substances should be assumed to carry significant health risks. We are not qualified to express an opinion that you are fit to safely take any drugs. All information and images shared are anonymous and untraceable. In the absence of any negligence or other breach of duty by Rehabstudio Limited or Herezie Group, use of this tool is entirely at your risk.

Heading 1

Heading 2

Heading 3

Heading 4

Heading 5
Heading 6

Heading 1 Link

Sample text is being used as a placeholder for real text that is normally present. Sample text helps you understand how real text may look on your website. Sample text is being used as a placeholder for real text.

  • Type:¬†Unordered - Style:¬†No Bullets
  • Type:¬†Unordered - Style:¬†No Bullets
  • Type:¬†Unordered - Style:¬†No Bullets
  • Type:¬†Unordered - Style:¬†Bullets
  • Type:¬†Unordered - Style:¬†Bullets
  • Type:¬†Unordered - Style:¬†Bullets
  1. Type: Ordered - Style: Bullets
  2. Type: Ordered - Style: Bullets
  3. Type: Ordered - Style: Bullets

This is bold text

This is italic text

This is a link

The details are not the details.
They make the design.
This is an image caption
Cookies Preferences
Close Cookie Preference Manager
Cookie Settings
By clicking ‚ÄúAccept All Cookies‚ÄĚ, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage and assist in our marketing efforts. More info
Strictly Necessary (Always Active)
Cookies required to enable basic website functionality.
Made by Flinch 77
Oops! Something went wrong while submitting the form.