Tools

Eduards Ruzga explores how the AI community debates local LLMs versus cloud APIs versus subscriptions – but almost entirely on vibes. He attempted to address this by building an open-source tool that calculates quality-adjusted tokens per dollar across all three options.
He shares surprising findings: running GLM-4.7 Flash locally on a $3,500 MacBook delivers 22×worse value than calling the same model via API. ChatGPT Pro provides 6.4× more tokens than Claude Max at the same price point.
The methodology – combining benchmark scores, hardware costs, subscription limits, and API pricing into one comparable metric – is open for scrutiny and contribution. Attendees leave with a live tool, a framework for evaluating AI cost-effectiveness, and concrete data to replace opinions with math.
Tool and source: https://wonderwhy-er.github.io/llm-value-comparison/
Full analysis: https://wonderwhy-er.medium.com/51fc0ad0dbd7

Burak Güneli’s talk is divided into two main sections. First, he will provide insights into the sustainability of both the web and AI. Drawing on his experience as a Coordinator, Data Analyst, and Author for the Web Almanac, Burak will share calculated statistics, including exclusive sustainability data that is currently unavailable online, as this year’s Sustainability chapter has not yet been released.
In the second section, Burak will present an approach to optimize agent connections in applications. This will feature a demonstration of semantic caching for prompts, a technique that saves prompts as vectors in IndexedDB and applies cosine similarity to prevent sending redundant prompts to the agent. This allows applications to instantly display cached answers, completely bypassing wait times and cost-heavy AI calculations.

Generative AI agents can deliver impressive demos. But the transition from a compelling proof of concept to a reliable production system often fails—not because of scale, but because of trust.
In this session, Stanko Kuveljić presents a candid postmortem of a production-grade scheduling agent that exposed a structural vulnerability: a conflict between “politeness” and policy compliance. In attempting to be helpful, the agent overrode business constraints, revealing how probabilistic models optimize for plausibility rather than strict rule enforcement.
This talk explores what it means to operationalize generative AI responsibly. Rather than increasing autonomy, Stanko presents a practical approach he refers to as the concept of “Bounded Autonomy,” wrapping probabilistic models within deterministic control flows to enforce business invariants.
Attendees will learn:
Why large language model (LLM) agents drift toward conversational compliance over business policy, and how “helpfulness” becomes a production risk.
A practical architecture for embedding probabilistic reasoning inside deterministic control flows with non-bypassable invariant enforcement.
How to treat agent actions as testable behaviors instead of prompt outcomes, implementing deployment gates that reduce manual regression validation effort in production.
A reusable reference architecture and behavioral testing checklist that can be applied to agent-based systems.
This session is designed for leaders responsible for moving AI systems from experimentation to enterprise-grade reliability.”

Understanding users is key to building successful digital products. Qualitative research uncovers why users behave as they do – their motivations, needs, and pain points. In this session, Nina Bordet explores how AI tools can streamline and enhance user research, sharing real-world examples from different stages of research projects. She highlights where AI adds value, how to use it effectively, and the limitations to watch for – ensuring that insights remain meaningful, actionable, and always user-centered.

AI agents accelerate writing code, but they also speed up the spread of patterns in a codebase – any patterns. When there are no clear rules, bad code and poor design choices spread quickly and become hard to fix. AI assistants cannot tell the difference between code that merely works and code that is well-designed. This makes their uncontrolled use risky for large and evolving systems.
To reduce this risk, people must stay in the loop, but that is not enough on its own. Tests, code quality tools, and architectural checks are no longer optional. AI agents also need clear instructions on what maintainable, secure, and performant code looks like.
In this talk, speaker Eugene Fidelin shares insights based on a year of intensive, real-world use of AI agents by multiple teams, highlighting practical lessons on what worked, what failed, and what scales.

Curious about AI but unsure where to begin? In this session, speaker Kalle Sirkesalo provides a clear roadmap for leveraging the power of Artificial Intelligence, specifically within your organisation’s suite. He demystifies Large Language Models (LLMs) and their role in today’s AI landscape, then explores the essential building blocks of effective AI interaction: prompting and tokens, explaining how and when to use different tools.

Through live demonstrations, he showcases the low-code ability to automate complex tasks, instantly summarize and expand upon critical information, and serve as an invaluable assistant, fundamentally changing how you work. Learn how he empowers organizations to integrate and adopt AI seamlessly into their operations and guides customers on their own AI journey.

In this workshop, Raghav Matta explores a real-world scenario of performing real-time social media analysis using Databricks with SQL AI Functions for LLM‑powered enrichment.

The session begins with the business problem, focusing on how organizations monitor sentiment, trends, and reactions on social platforms.

Next, the talk walks through the Databricks architecture, including Event Hubs, Unity Catalog, and Azure Databricks, with a focus on SQL AI functions such as ai_analyze_sentiment, ai_extract(), and ai_classify().

The session then demonstrates how to ingest live or simulated social content into Databricks, apply SQL AI Functions to analyze sentiment and topics, store results in Delta Lake, and create visual insights using Databricks AI/BI.

Additionally, Raghav shows how to use Databricks Genie to interact with the analyzed data and derive further insights.

Reference: https://www.youtube.com/watch?v=BzL-8iM_YOM

In a moment when AI-generated video is widely criticized as “AI slop,” it is, paradoxically, also being watched, shared, and created at an unprecedented scale. This talk explores that contradiction—and argues that the real issue is not the use of AI itself, but the absence of intention, authorship, and responsibility behind much of the content produced.

In Beyond AI Slop, speaker Marina Meli examines how and when AI should be used in video to enhance business value without eroding trust or meaning. Drawing on her background in Psychology and Filmmaking, alongside hands-on experience in B2B IT sales and corporate video production, she approaches AI not only as a technological tool, but as a medium that shapes perception, attention, and audience trust.

The session presents real-world case studies from B2B technology and corporate environments, including examples from cybersecurity, enterprise IT, and AI-enabled sales environments, walking through the original communication challenge, the AI-assisted workflow design and tool choices, and the resulting impact on production speed, message clarity, and sales enablement.

Marina introduces a clear ethical framework grounded in both human psychology and filmmaking practice, helping organizations distinguish between AI that amplifies human intent and AI that merely substitutes it. She connects questions of authorship, authenticity, and responsibility to how audiences cognitively and emotionally process video content—especially in environments saturated with automated media.

The talk also includes a practical, easy-to-follow walkthrough of some of the newest and most relevant AI tools used in video creation, demonstrating how they can be integrated into real production workflows in a way that remains transparent and ethical. Crucially, the principles, frameworks, and decision-making processes presented are designed to be transferable across a wide range of AI tools and use cases, and are not limited to video creation alone. Rather than focusing on automation for its own sake, the session highlights where AI meaningfully supports clarity, speed, and accessibility—and where human judgment must remain central.

By combining philosophical grounding with practical application, this session shows how ethical AI use can directly enhance sales and business communication—making complex products easier to understand, messages more consistent, and interactions more effective across marketing, sales, and internal teams. Attendees will leave with both conceptual clarity and actionable frameworks, workflow templates, and ethical checkpoints they can apply immediately—without contributing to low-value automated content or triggering reactionary backlash against new technologies.