<description>&lt;div class="uSg02"&gt; &lt;div class="DrnCK"&gt; &lt;div class="HwXOf"&gt; &lt;div class="kcAOr t9ThB" data-testid="RecipientWell"&gt; &lt;div data-tabster= "{"mover":{"cyclic":false,"direction":2,"memorizeCurrent":false}}"&gt; &lt;div id="MSG_gAD6KfRLAAA_TO" class= "___sj378o0 fly5x3f f1l02sjl f113hnb5" role="heading" aria-level= "3"&gt;&lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;div data-test-id="mailMessageBodyContainer"&gt; &lt;div class="XbIp4 jmmB7 customScrollBar GNqVo allowTextSelection"&gt; &lt;div id="UniqueMessageBody_25" class="OuGoX BIZfh" tabindex="0" role="document" aria-label="Message body" aria-live="polite" aria-atomic="false"&gt; &lt;div&gt; &lt;div&gt; &lt;div lang="en-US" xml:lang="en-US"&gt; &lt;div&gt; &lt;p&gt;What does it take to make AI reliable enough to design a bridge? Peggy Smedley sits down with Francois Valois, senior vice president of Bentley Open Applications at Bentley Systems, to unpack the MCP (model context protocol — an open, agnostic standard that connects AI agents to deterministic engineering tools like STAAD and MicroStation ensuring trust, validation, and accountability in engineering workflows.&lt;/p&gt; &lt;p&gt;They explore why generative AI alone needs to be more trustworthy for infrastructure design, how MCP bridges the gap between non-deterministic LLMs (large language models) and precise calculation engines, and what Bentley's open-source strategy means for the future of connected-infrastructure data.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Topics covered:&lt;/strong&gt;&lt;/p&gt; &lt;ul type="disc"&gt; &lt;li&gt;What MCP is and why Anthropic invented it&lt;/li&gt; &lt;li&gt;Why "90% accurate" isn't acceptable in engineering&lt;/li&gt; &lt;li&gt;How STAAD and MicroStation are now AI-accessible via MCP&lt;/li&gt; &lt;li&gt;The role of structured data (and dark data) in AI workflows&lt;/li&gt; &lt;li&gt;How to start experimenting with AI agents in your firm&lt;/li&gt; &lt;li&gt;The future of the engineer in an AI-augmented world&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;infrastructure.ai | connectedworld.com | peggysmedleyshow.com&lt;/p&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt; &lt;/div&gt;</description>

Peggy Smedley Show

Peggy Smedley

Model Context Protocol 101

JUL 1, 202631 MIN
Peggy Smedley Show

Model Context Protocol 101

JUL 1, 202631 MIN

Description

What does it take to make AI reliable enough to design a bridge? Peggy Smedley sits down with Francois Valois, senior vice president of Bentley Open Applications at Bentley Systems, to unpack the MCP (model context protocol — an open, agnostic standard that connects AI agents to deterministic engineering tools like STAAD and MicroStation ensuring trust, validation, and accountability in engineering workflows. They explore why generative AI alone needs to be more trustworthy for infrastructure design, how MCP bridges the gap between non-deterministic LLMs (large language models) and precise calculation engines, and what Bentley's open-source strategy means for the future of connected-infrastructure data. Topics covered: What MCP is and why Anthropic invented it Why "90% accurate" isn't acceptable in engineering How STAAD and MicroStation are now AI-accessible via MCP The role of structured data (and dark data) in AI workflows How to start experimenting with AI agents in your firm The future of the engineer in an AI-augmented world infrastructure.ai | connectedworld.com | peggysmedleyshow.com