Devoteam helps deliver proof of concept for puzzle automation at Empire Games
Empire Games decided to automate the creation of playable levels for its mobile puzzle games, to reduce manual effort and time-to-market. Consultants from Devoteam reportedly helped design a scalable tool which could algorithmically generate puzzles quickly and effectively.
Over the last decade, revolutions in the computing power of smart phones – as well as the strength of mobile internet – have enabled gamers to deploy their devices as miniature games consoles. Smartphone gaming revenue is projected to surpass $100 billion in the near future – accounting for around 40% of the video-gaming market – and game designers and manufacturers are eager to capture share in this ever expanding, fast-growth market.
Empire Games is a London-based gaming studio, which focuses on creating competitive mobile games that offer players both fun, and the chance to win real cash. One of the studio’s key titles is Nuts & Bolts Screw Wood Puzzle, a competitive, skill-based single player puzzle game – while the firm is also known for Empire Bingo, a narrative-driven bingo experience set across varied thematic backdrops like Ancient Egypt and Victorian England.
To increase the profitability of this business model, Empire Games determined it should automate the creation of its games, where possible. The challenge it therefore faced was to create a scalable and reliable platform, which could generate valid puzzles from defined parameters, with minimal human intervention.
To do that, it tasked Devoteam – in collaboration with AWS – to create a proof-of-concept, to show the feasibility of streamlining Empire Games’ level creation process using GenAI and cloud-based technologies. The resulting pipeline had to be scalable, fault-tolerant, reusable, reliably interpret prompts to produce valid puzzles with minimal manual input, and be highly automated and low-friction for developers and end users.
The solution the team developed centred on building a proof-of-concept for a fully LLM-driven workflow, which could “handle every stage of gameboard generation from start to finish”. The plan focused on using Claude thinking tokens, to interpret the initial input and guide subsequent requests, ensuring the logic of each gameboard aligned with the intended puzzle design. Tool integrations were then applied to execute specific operations, which Devoteamsays reduces “the risk of errors or inconsistencies” – with a seven-in-ten success rate already.
Results
According to the consultancy’s release on the project, “Every gameboard produced was validated against a defined schema before delivery, providing a safeguard for quality and playability. To maintain coherence throughout the process, an agentic approach was adopted, preserving context across iterations and allowing the system to generate consistent, reliable outputs at scale.”
The chosen methodology was a Python-based orchestration integrated with Amazon Bedrock, with schema validation and an agentic workflow to preserve context throughout generation. Once this was delivered, the proof-of-concept successfully demonstrated that LLM’s and AWS Cloud technologies could automate playable level generation, according to the consultants.
Nathan Merola, enterprise account manager at AWS, said of the work, “This project exemplifies the transformative potential of Generative AI on AWS for game development. Working with Devoteam, we were able to create an innovative, LLM-driven workflow that significantly streamlined Empire Games’ level creation process. The impressive 70% success rate achieved in the initial proof of concept demonstrates both the power of our technology and the expertise Devoteam brought to the table. We’re thrilled to see how this solution has positively impacted Empire Games’ efficiency and look forward to supporting their continued innovation in the gaming industry.”
Devoteam believes that the project also shows that “automated generation was shown to be more cost-effective and scalable than manual methods”. Meanwhile, looking ahead, the project identified areas for improvement in pattern consistency, which the team asserts can “further enhance quality and reliability” – something which the Empire Games leadership team is very enthusiastic about.
Alex Palaghita, the company’s founder and CTO, added, “What we valued most about working with Devoteam was their ability to design a proof-of-concept that was technically sound. Their added value was in bringing structure and automation, with potential for large scale to a process that was fully manual and as such, slower. For other companies facing similar challenges, my advice would be to focus on building a clear validation pipeline early. Automating content generation is only useful if the outputs can be trusted. Partnering with a team like Devoteam that understands both the cloud infrastructure and AI workflow design made that possible for us.”
