90% of enterprise knowledge is locked in unstructured content. Most companies have no idea how to use it.

In this episode, Yashodha Bhavnani, Head of AI at Box, breaks down what it actually takes to get real value from AI in the enterprise. Not the buzzwords. Not the experiments bolted onto the side of a product. The real infrastructure decisions that determine whether your AI strategy succeeds or stalls.

She covers why the right model is irrelevant if your AI cannot see your data, how Box built its agent directly into its core product stack instead of shipping it as a sidecar experiment, and why enterprises face a governance and context problem that most AI vendors are not solving.

She also shares the three-part future of work every product team and executive needs to plan for, what the J-curve of AI adoption actually feels like from the inside, and why the word "agent" has officially become meaningless.

In this episode you will learn: [0:00] Why 90% of enterprise knowledge is stuck in unstructured content [1:26] Yashodha Bhavnani, Head of AI at Box, on the era of context [2:08] Why your AI strategy needs a content strategy first [5:03] How enterprises should organize their data for agents [8:06] The two layers of AI governance: hard security vs. contextual control [10:05] How Box thinks about permissions, compliance, and agent guardrails [10:53] The unstructured content explosion and what it means for your data stack [14:10] Principles Box uses internally to stay efficient and sane [16:27] How to build AI products that serve both humans and agents [18:26] Why this is a culture shift, not just a technology shift [20:43] The decision to build Box Agent into the core product, not alongside it [23:36] Three lessons for anyone leading an enterprise AI strategy [26:13] Will there be more agents than humans at work? [28:09] A real customer example: AI freeing analysts from lease compliance grunt work [30:25] How Box is adopting AI internally and what the growing pains look like [33:14] Rapid fire: the deeply held belief about AI that will be destroyed in two years [34:28] The one AI buzzword Yashodha would ban from every meeting [35:51] What she is most optimistic about with AI in the workplace

Whether you are a CXO, product leader, or enterprise builder trying to move from AI experimentation to real deployment, this conversation gives you the clearest framework yet for unlocking your unstructured data, governing your agents, and building AI that actually sticks.

#AIStrategy #EnterpriseAI #AIAgents #ProductManagement #FutureOfWork #BoxAI #UnstructuredData #CXO #KnowledgeWork #AILeadership

Wade Foster, CEO & Co-Founder of Zapier, reveals how a $5B company transformed overnight when GPT-4 launched. Learn his "Code Red" strategy, AI adoption secrets, and why the future of software belongs to AI agents.

When GPT-4 launched, Wade Foster didn't wait. He called a code red. In this conversation, he shares exactly how Zapier went from 10% to 97% company-wide AI adoption in months, why he focuses on building "AI fluency" over quick wins, and what he believes every CEO needs to know about the AI-driven future.

We cover: - The "Code Red" moment: Why and how Zapier decided to transform everything - From 10% to 97%: The real drivers behind achieving company-wide AI adoption - The AI Fluency Rubric: Building institutional AI capability vs. tactical AI use - The future of software: Why agents (not humans) will write and use software - The 3% that didn't adopt: Why some teams resist and how to bring them along - Advice for late-moving CEOs: What to do if you haven't started yet - Buzzwords Wade would ban from meetings - Why "context" and "agent" are overloaded terms in AI discussions

TIMESTAMPS: 00:00 - Intro 02:08 - How calling Code Red transformed the company 03:02 - The immediate impact: From 10% to 50% AI adoption 05:09 - Building the AI Fluency Rubric and institutional change 07:18 - How Zapier achieved 97% adoption (and what about the 3%?) 09:08 - The difference between adoption vs. sustained usage 12:37 - Making employees retry AI tools even when first attempts failed 15:59 - Infrastructure for embedding AI into workflows 19:25 - The future of software: Agents as creators and users 31:58 - What will Zapier look like in 3 years? Agent-native platforms 34:04 - Setting up governance for AI agents to write code safely 39:17 - What beliefs about AI building today won't make sense by 2028? 42:02 - Buzzwords Wade wants to ban from AI conversations 43:18 - Final advice for CEOs who feel they're late to AI

KEY INSIGHTS: - The quality gap between GPT-3.5 and GPT-4 was so vast it rewritten everything for Zapier - A company-wide hackathon forced everyone to play with AI (80%+ participation was key) - Building the muscle for AI adoption matters even when the initial output isn't directly used - Entrenched workflows and quality concerns are the biggest blockers to adoption - Support and encouragement to "try again in 3 months" is critical - The shift isn't just more software, it's that agents will write that software - Governance and guardrails for agents are the new infrastructure CEOs need to set up - AI maximalism paired with realistic change management is the winning approach

PERFECT FOR: - Product leaders and GTM professionals navigating AI transformation - CEOs and C-suite executives feeling pressure to move faster on AI - Engineering leaders building AI-fluent organizations - SaaS founders and entrepreneurs building AI-native products - Anyone curious about how category-defining companies adapt

Wade Foster brings the strategic clarity and operational rigor that made Zapier the automation standard. This episode cuts through the AI hype to the real work of transforming organizations.

#WadeFoster #Zapier #AI #CEOAdvice #AIAdoption #ArtificialIntelligence #SoftwareDevelopment #ProductStrategy #Automation #AIAgents #Leadership #GPT4 #Technology #BusinessStrategy #GTM

ABOUT WADE FOSTER: Wade is the Co-Founder and CEO of Zapier, the #1 automation platform connecting 7000+ apps. He's been building Zapier since 2011 and has grown it into a $5 billion company used by millions of businesses to automate daily workflows. Wade is deeply focused on AI's impact on software development and organizational productivity.

DISCLAIMER: This conversation reflects Wade Foster's views and experiences. Viewers should consult their own experts before making strategic or business decisions.

How Replit's VP of Ops Runs an AI-Native Company (And Why Most Enterprises Are Still Getting It Wrong)

Jonathan Eide has built and scaled operations at Meta, Coinbase, and now Replit, the company that's quietly become one of the fastest-growing AI-native businesses on the planet. In this conversation, he breaks down what's actually different about running a company where every function builds their own software, why "vibe coding" is too lightweight a term for what's coming, and the hiring shift every CXO will face in the next 24 months.

If you're a CXO trying to figure out how to move your org from "we use Copilot" to genuinely agentic operations, this is the playbook.

What we get into: The two archetypes Replit hires for, and why the "perfect candidate" has both Why Jon hasn't written a Linear ticket by hand in months (and what replaced it) The internal AI analyst tool that replaced an entire junior analyst function How Replit killed Google Slides internally with a self-updating, self-populating weekly wins deck Why measuring AI productivity by tokens or time saved is the wrong move (Theory of Constraints, applied) The hiring shift: from screening interviews to "build me a demo before we talk" What enterprise adoption actually looks like at Zillow, Atlassian, and old-school PE-backed manufacturers Why Replit's "plan" is to not have a plan, and why vision/mission still has to be rock solid The single-person companies hitting tens of millions in ARR Rapid fire: the deeply held belief about AI that Jon thinks will be gone by 2028

Chapters: 00:00 Intro 01:16 Jonathan Eide 02:00 What's fundamentally different about running ops at an AI-native company 04:20 How every function at Replit is building its own tools 07:35 Killing PowerPoint: the internal weekly wins deck built in Replit 11:35 Source of truth, guardrails, and avoiding the "everyone builds an app" sprawl 14:20 Can large or legacy companies actually adopt this operating model? 18:15 Why measuring tokens and time saved is the wrong way to track AI productivity 22:20 How Jon redesigned his interview process for AI-native hiring 25:35 Are AI-native companies hiring fewer people, or different people? 28:25 Why "AI native" will disappear as a hiring filter 29:15 Growing at Replit's pace: planning when the market resets every two weeks 32:24 Replit's three user segments: hobbyists, prosumer entrepreneurs, enterprise 34:41 Surprising businesses being built on Replit (and the single-person unicorn thesis) 37:30 The plan is to not have a plan: vision vs short-term flexibility 40:36 Rapid fire: the belief about AI that will be destroyed by 2028 41:32 Rapid fire: the one AI buzzword Jon would ban from Replit meetings 42:27 Rapid fire: what Jon is most optimistic about

About Jonathan Eide: Jonathan is VP of Operations at Replit. Prior to Replit, he held senior operating roles at Coinbase and Meta, leading data and operations functions through hypergrowth phases at both.

About the AI CXO Podcast: The AI CXO Podcast helps CXOs get actionable insights into how to navigate AI's reshaping of the business landscape. New episodes drop weekly.

Subscribe for more conversations with operators building the AI-native enterprise. https://www.youtube.com/@productfaculty #AI #Replit #CXO #VibeCoding #EnterpriseAI #AINative #AIAgents #FutureOfWork #ProductLeadership #Operations