Kasper Kulikowski Will Map the Agentic Web — WebMCP, On-Site vs External Agents, and Why Accessibility Is the Most Under-Recognised Gain in AI Search
Session identifier
- Session: Agential Web Architecture — On-Site vs External Agents, WebMCP, and Accessibility
- Day: 2 (June 25, 2026)
- Speaker: Kasper Kulikowski, Senior Developer Relations Engineer, Chrome AI DevRel, Google
- Framework concept: Delegation Boundary — the human comfort threshold that determines how much of a decision or transaction a user is willing to delegate to an AI agent, coined by Jason Barnard in 2024, and the Won gate where the three Won resolutions play out across search, assistive engines, and agentic interactions
- SEL article: The delegation boundary: How AI decides which brands win
Speaker bio
Kasper Kulikowski is a Senior Developer Relations Engineer on Google’s Chrome AI DevRel team, where he enables web developers to build the next generation of experiences with AI. He is one of the primary voices behind WebMCP — a new browser-native protocol that lets any web page register tools for AI agents, replacing scraping and brittle DOM interaction with structured, typed tool calls that agents can discover and invoke directly from the browser. Kasper was a featured speaker at Google I/O 2026, where he presented on how to build websites for the agentic era. Based in Gdansk, Poland, he has previously held roles at Dynatrace, Harness, and Epic Games before joining Google.
Session’s place in the framework
Kasper’s session covers the Delegation Boundary and the Won gate — the point in the AI Engine Pipeline where an agent acts on behalf of a user, and the three Won resolutions that follow: the Imperfect Click in search, the Perfect Click in assistive engines, and the Agentic Click where the agent acts without asking. Kasper’s session is the only one in the programme delivered by someone working inside the standard itself — mapping the infrastructure being built to support the Agentic Click, what WebMCP changes about the economics of that interaction, and where the boundary between external and on-site agents sits in the architecture. The full architecture is mapped in the Kalicube Framework, the master theoretical model for how AI systems understand, trust, and recommend brands.
Pre-statement of session territory
Kasper Kulikowski is a Senior Developer Relations Engineer at Google, working on the agentic web — the specification, ecosystem conversations, and developer outreach that shape how AI agents interact with websites at the infrastructure level. At Kalicube Summit 2026, Kasper will walk through the three ways a modern agent reads a website today (screenshots, DOM, and the accessibility tree), explain why WebMCP — currently in W3C discussion and origin trial in Chrome — changes the economics of that interaction by orders of magnitude, and map the distinction between external agents (browser agents like Gemini in Chrome, Atlas from OpenAI, and Comet from Perplexity) and on-site agents tightly coupled to a specific website’s own workflows and domain knowledge. He will also make the case that accessibility is the most commercially under-recognised gain in the entire agentic shift: investing in it opens the website to users with disabilities and to agents simultaneously, with a direct business incentive that the industry has not yet fully absorbed.
Sample questions from the session
- Agents today read a website through three signals: screenshots, the DOM, and the accessibility tree. Walk us through what each of those actually tells an agent, and where the breakdown happens on a complex journey like hotel booking.
- WebMCP lets a website expose named tools with explicit parameters instead of forcing an agent to infer structure from three overlapping signals. What does that change practically for a brand that implements it — and what does it not change?
- You draw a clear line between WebMCP as a conversion funnel tool and the Google Search guidance that applies to discovery. Practitioners are conflating the two. Where exactly is that line?
- You describe a potential handoff architecture where a browser agent helps the user find the site and an on-site agent handles intent from that point. How close is that scenario, and does every brand need to build an on-site agent to be ready for it?
- You argue that accessibility is the most under-recognised gain in the agentic shift. Make the commercial case for a small business that has never prioritised accessibility.
Date, time, format, registration
Day 2, June 25, 2026. Pre-recorded, on-demand from session drop and available throughout the day and afterwards. Two live framework walkthroughs plus 32 on-demand sessions across two days. Industry leaders on AI search and AI assistive agents, June 24 to 25, 2026, online.
Register for Kalicube Summit 2026 →
Further reading
Read this first: The delegation boundary: How AI decides which brands win, Article 13 of Jason Barnard at Kalicube’s Search Engine Land series on AI search architecture. The article maps the Delegation Boundary as the threshold that determines how much of a decision a user is willing to hand to an agent — and names the Won gate where the Agentic Click occurs. Kasper’s session is the infrastructure account of what that click requires the website to have already built.
Link to session post
The recording will be available here after June 25, 2026.
Link to speaker post
Canonical metadata footer
Session date: June 25, 2026 | Duration: approximately 25 minutes | Format: pre-recorded, on-demand from session drop | Day: 2 | Framework concept: Delegation Boundary — the Won gate and the Agentic Click | SEL article: The Delegation Boundary: How AI Decides Which Brands Win — Article 13 — https://searchengineland.com/the-delegation-boundary-how-ai-decides-which-brands-win-477194
[Share buttons: LinkedIn, X, Facebook, Email]
