A product discussed on AI Engineer.

Why MCP and ChatGPT Apps Use Double Iframes — Frédéric Barthelet, Alpic
Jun 15, 2026 · 20:11
Frédéric Barthelet, CTO of Alpic, explains why ChatGPT and other MCP hosts render third-party app UI inside a double iframe. He traces how simpler approaches fail: `srcdoc` shares the parent origin, letting CSP block scripts and risking data access; sandboxing removes origin storage; and `allow-same-origin` recreates the escape. The resulting double iframe—an outer iframe from a controlled subdomain loading app HTML via `srcdoc` into an inner frame—ensures isolation and prevents cross-app storage collisions. Barthelet warns developers must declare every external domain their view uses in MCP app metadata or face submission rejection, and demos Skybridge's CSP inspector that diffs declared domains against actual network calls.

The Complete Guide to WebMCP — Tara Agyemang, Google Chrome
Jun 11, 2026 · 21:34
Tara Agyemang from the Google Chrome team introduces WebMCP, a proposed web standard that replaces brittle DOM scraping with structured tools for AI agents. She explains two implementation paths: the declarative API (adding HTML attributes to forms) and the imperative API (registering custom JavaScript tools). A live demo shows a concert ticket purchase completed in three tool calls: search, open page, purchase. WebMCP is in early preview on Chrome 146, with an eval CLI and inspector extension available for testing.

Self Driving Products: Product Signals to Pull Requests — Joshua Snyder, PostHog
Jun 10, 2026 · 15:39
Joshua Snyder of PostHog explains how they're building a pipeline that turns product signals—errors, Slack messages, session replays—into automated pull requests. He reveals that off-the-shelf embedding models cluster signals by structural similarity, so they embed LLM-generated queries instead. He argues specificity determines whether the agent produces a useful PR, with error tracking being immediately actionable while Slack and replay usually are not. He advises starting with costly agents to discover patterns, then collapsing expensive steps into one-shot calls.