AI Tech Brews: Every Token Counts – The Art & Science of Token Optimisation
Details
Register at this link to join as we explore the art of token optimisation and the emerging field of AI token economics (tokenomics).
In the world of AI, tokens are more than just units of text processing. They are the currency that powers Large Language Models (LLMs), influencing cost, performance, scalability, and user experience. Just as economies are built around the production, allocation, and consumption of resources, AI systems operate within a token economy where every token has value.
Discover how to maximise value from every token, balance cost with quality, and build AI solutions that scale efficiently. From prompt engineering and context management to practical strategies for reducing token waste, this session will provide actionable insights for designing smarter, faster, and more cost-effective AI systems.
Talk 1: Beyond AI Agents: Building Production-Grade AI Systems
This session argues that the future of AI is not about building bigger, more autonomous agents, but about designing production-grade AI systems where AI is used selectively and efficiently.
Rather than assuming every problem should be solved by an LLM, the focus is on understanding when AI should reason and when traditional software should be executed. The most effective systems combine LLMs with deterministic components such as databases, APIs, workflows, retrieval systems, automation, and human review, creating solutions that are reliable, scalable, and cost-effective.
Talk 2: Enterprise AI Economics: Understanding and Controlling AI Cost
Enterprise AI Economics explores how AI costs evolve in production, beyond simple token pricing. It covers the key drivers of AI to spend across prompts, retrieval, agents, and tools, along with techniques like caching, model routing, and context optimization to improve efficiency. The session also highlights how mature organisations use observability to track usage and shift from measuring cost per token to cost per successful business outcome
Talk 3: Put AI on a Token Diet
Every AI interaction comes with a cost. As organizations increasingly adopt AI assistants, coding copilots, and agentic workflows, uncontrolled token consumption can impact both performance and spend. This session explores practical techniques to reduce token waste while improving response quality and system efficiency
Whether you're an engineer, product manager, architect, data scientist, or AI enthusiast, come learn, share ideas, and discover why every token counts. 🚀☕