Deployed: The AI Product Podcast

Superhuman charges $30/month for email when Gmail is free. That's always forced them to maintain a different quality bar from most products, and it shapes everything about how they build AI features too.Loïc Houssier is CTO at Superhuman Mail, and one of the most fun and energized engineering leaders I've gotten to work with. In this conversation, he walks us through what quality really means when you're building a "luxury" software product - and how that mindset applies to AI.We dig into the high-dimensional challenge of building great AI experiences around email, from auto-drafts to semantic search. We talk about how they approach evals when every user's inbox looks completely different, starting from the hardest queries they can find internally. And we get into how Superhuman is adopting coding agents across their engineering team - including their "quality week" practice and why they removed all procurement blockers for AI tools.Timestamps: 0:00 - Intro: What "luxury" means for a software product 2:12 - Loïc's background and why he joined Superhuman 6:02 - Game design principles in product development (not gamification) 10:14 - AI features at Superhuman: triage, search, and auto-drafts 15:34 - The challenge of building AI features in a high-dimensional space 20:00 - Building evals from the hardest internal queries (the "wood for my coffee table" example) 24:20 - Privacy and how they handle eval data 25:45 - Their mix of models: BERT, fine-tuned, open source, and frontier 28:19 - What quality means when your competition is free 30:10 - Quality week: dedicating the first week of every quarter to bugs and AI workflow improvements 32:44 - How they're adopting coding agents internally 35:30 - Removing all the blockers for AI tools (e.g. 24-hour security approval, unlimited budgets) 38:06 - How Loïc ramped up on AI as a leader 40:15 - Parting advice: choose your vendors wisely, and enjoy this moment as a builderLinks:Superhuman: https://superhuman.comFind Loïc on LinkedIn: https://www.linkedin.com/in/loichoussier/

On this episode of Deployed we talk with Lijuan Qin, Head of Product for Zoom AI, about how her team is moving beyond AI meeting transcriptions and note-taking to a mission of agents helping from "conversation to completion." That's how Lijuan describes her vision of the future for Zoom AI, where AI doesn't just summarize your meetings, it actually follows through on the work that comes after.Lijuan has a PhD in AI and spent 20 years at Microsoft working on NLP and video understanding before joining Zoom. She brings a long-arc perspective on what's changed and what hasn't in AI, and shares how her team thinks about building an AI companion that acts more like a team member than a search engine.Key insights for builders include:* Why high engagement with an AI product can be a negative signal. i.e. if users keep going back and forth with your AI, the product might be failing them ("you got it wrong! try again").* How Zoom measures AI quality by *output* value and task completion, instead of usage metrics or individual response accuracy* Their "AI-first, intent-driven" approach: starting from what the user needs to get done, not which tool to use* How they personalize AI features in stages: role-based outputs first, then memory, then live conversation context, rather than trying to build something like a full "digital twin" on day one* A concrete example: Drafting different kickoff documents for each meeting attendee that is personalized for the priorities of their role (PM vs. engineer vs. CTO)* Why transparent decision frameworks let big organizations experiment fast without approval loops* How the Zoom AI team balances speed and enterprise trustLinks from our conversation:* Zoom AI Companion: https://ai.zoom.us* Find Lijuan on LinkedIn: https://www.linkedin.com/in/lijuanqin/* Freeplay (that's us): https://freeplay.ai

Kevin Stanton has spent 13 years at Sprout Social, most recently running infrastructure for a platform that processes billions of social posts. When generative AI emerged, their team saw an opportunity to solve one of their hardest problems: helping customers make sense of massive amounts of unstructured social data.Now Kevin is building Trellis, Sprout's AI agent for social listening and competitive intelligence. In this conversation, he shares what it's looked like to shift an engineering team toward building agents — and the practical lessons they've learned shipping to thousands of customers.We cover details like why MCP felt more natural than RAG for their architecture, how they use chat as a strategy for seeding eval datasets, when to let agents reason versus when to collapse tools and write deterministic code, and why they pulled evals out of CI/CD after learning the hard way how non-deterministic tests can break things.Links from our conversation:Sprout Social: https://sproutsocial.comSprout Social Insights Blog: https://sproutsocial.com/insightsTrellis: https://sproutsocial.com/insights/press/sprout-social-unveils-trellis-its-ai-agent-that-turns-social-data-into-instant-enterprise-intelligence/Find Kevin on LinkedIn: https://www.linkedin.com/in/kevinstanton/

On this episode of Deployed, we sit down with Shuhao Zhang, co-founder and CPO of TinyFish, on launch day for Mino (mino.ai) - an enterprise web agent platform that handles reasoning, multi-step execution, and parallel browser sessions at scale.Shuhao shares his vision for the "operational web" where AI agents become the primary operators of the web, unlimited by human constraints. He shares a live demo and customer stories, like working with Google to connect tens of thousands of Japanese hotels to consumers, and with ClassPass to maintain up-to-date pricing across 30,000 wellness studios.Key technical insights for builders include:- Why public benchmarks for web agents are saturated today, and you need your own evals- How they built infrastructure to replay sessions like a "time machine" for data iteration- Why they fix issues through data improvement rather than custom patches / rule-based systemsLearn more:- Minnow: mino.ai- Tiny Fish: tinyfish.ai- AgentQL: agentql.com- Find Shuhao on LinkedIn (https://www.linkedin.com/in/shuhao/) and Twitter (https://x.com/shuhao_friday)

On this episode of Deployed, we sit down with Ajit Varma, VP of Product at Mozilla Firefox, and former product leader at Google, Meta, Square, and WhatsApp. Ajit brings a unique perspective: while venture-backed AI browsers race to build what increasingly look like walled gardens, Mozilla has spent months quietly shipping privacy-first AI features that put user choice above everything else.It's a thoughtful conversation with candid insights into why Firefox offers multiple AI chat providers in their sidebar instead of forcing users into a single model (and how this philosophical stance shapes every technical decision they make), the reality that privacy-preserving AI requires completely rethinking architecture, and why their AI features prioritize on-device processing whenever possible. We also get into the technical challenges that come with balancing local and cloud AI (users want SOTA quality but also want their data to stay private), the business model constraints of being a nonprofit foundation competing against VC-funded competitors who can burn cash on flashy features, and why Mozilla believes keeping the web open matters more than winning the AI browser wars. Whether you're interested in privacy and the open web or just trying to understand what it takes to integrate cutting-edge AI into existing products, Ajit's perspective offers practical lessons from someone navigating a challenging balancing act.

On this episode of Deployed, we sit down with Surojit Chatterjee, CEO and founder of Ema, and former VP of Product at Google and Chief Product Officer at Coinbase. Surojit brings a rare perspective: he started building enterprise AI agents in early 2023—well before "agentic AI" became a buzzword- and has spent two years getting them to production quality that companies like Hitachi actually trust. Surojit gives us refreshingly candid insights into why Ema calls their products "AI Employees" instead of agents (and how this completely changes their approach to feedback and evaluation), the reality that most enterprise AI projects fail because companies try to automate broken processes instead of redesigning them, and why multi-agent systems are essential for handling real enterprise complexity. We dive into the technical challenges that remain unsolved (complex dynamic planning with long tool chains is still hard), his forward-deployed "agentic clinics" approach to customer success, and why sustainable scale matters more than flashy demos. Whether you're building AI products for the enterprise or trying to understand what it really takes to transform critical business processes with AI, Surojit's battle-tested perspective offers practical lessons from someone who's been in the trenches longer than most.

In this episode of Deployed, we sit down with Ryan Carson, Builder in Residence at Amp (Sourcegraph's coding agent) and founder of Treehouse, which taught over a million people to code. Ryan brings a rare dual perspective: he's both building his own company with AI tools and helping create enterprise-grade AI coding infrastructure.Ryan gives us refreshingly honest insights into the hyper-competitive coding agent landscape, why traditional evals don't work for open-ended coding tasks, and the "dirty secret" that most quality decisions still come down to "dev vibes." We dive into the technical reality of competing with well-funded teams, his systematic framework for building with AI agents (which has 5,000+ GitHub stars), and why success isn't just about model capabilities — it's about solving real developer problems through obsessive attention to user experience.Whether you're building AI products or trying to understand what it really takes to compete in this space, Ryan's grounded perspective cuts through the hype with practical lessons from the trenches.Retry

On this episode of Deployed, we talk with Kelly Schaefer, a Product Director at Google Labs and who’s been recognized as one of the Top 100 Women in AI. Kelly has led a portfolio of experimental AI products like NotebookLM and the Jules coding agent. The Google Labs team helps turn DeepMind research into real products that can work at Google scale.She shares what actually works when shipping AI features, from how her teams use evals to drive product quality, to why speed matters more than perfection. We also talk about how PM and UX roles are evolving in the AI era, and why she hires “dot connectors” who can bridge across domains.If you’re building AI products, managing product development teams, or just trying to stay ahead of how this field is evolving, this conversation offers a clear look into what actually works inside one of the world’s most influential AI product orgs.To see more of Kelly and her team’s work, check out https://labs.google/

On this episode of Deployed we talk with Kwindla Hultman-Kramer, co-founder of Daily (daily.co) and creator of Pipecat (pipecat.ai), the most widely used open source framework for voice agent orchestration.Kwin shares insights from building voice AI infrastructure since before it was cool, including why he thinks we've hit an inflection point now where voice agents are quickly moving from demos to real production deployments with real ROI. He breaks down the technical stack that actually works in production in July 2025, explains why most audio-specific evals are still "vibes" (and why that's okay if you get your text evals right!), and shares tactical advice that could save months of trial and error — like why you should use WebRTC instead of WebSockets, and why speech-to-speech models aren't quite ready for production yet.Whether you're curious about voice AI or already building voice agents, this conversation offers practical guidance from someone who's seen hundreds of teams navigate the journey from prototype to production scale.If you want to go deeper on this content, check out Kwin's Voice AI & Voice Agents book (https://voiceaiandvoiceagents.com/) and his popular Maven course (https://maven.com/pipecat/voice-ai-and-voice-agents-a-technical-deep-dive).

On this episode we talk with Nathan Sobo, co-founder and CEO of Zed, the high-performance code editor that's reimagining how AI agents can improve developer workflows. Nathan shares lessons from building one of the most natural agentic coding experiences available, including why investing up front to automate the feedback loop to improve the quality of AI systems is worth it. He also shares some great product design insights that go beyond the code editor -- including how they were able to weave an AI agent into the UX of their already-collaborative product (just like a human collaborator), and how their "subtle mode" for code completion has helped win over AI-skeptical developers. Whether you're building coding tools or another AI product, this conversation is a fun listen for anyone who cares about crafting great products and incorporating AI in smart ways.

On this episode we talk with Sarah Guo, founder of Conviction — a VC firm focused on early-stage AI investments. Sarah shares insights from her unique position at the intersection of AI research, startups, and enterprise adoption that are relevant to people building with AI. Topics like: How successful teams keep up with rapid changes in the AI landscape, how AI labs vs. enterprises approach problems differently, thoughts on why many AI initiatives struggle to move from prototype to production. She also shares some good advice for leaders on setting an ambitious roadmap and staying competitive in the current market. This conversation provides practical perspective on what's working with leading AI teams, and hopefully some advice others can learn from.

On this episode we talk with Tyler Phillips, AI Product Lead at Apollo.io, about what it really takes to build successful AI products in sales. Tyler shares surprisingly candid insights about the "unsexy" but critical work that great AI PMs do - from spending hours evaluating AI outputs to building systematic quality frameworks. Learn why it can help for domain experts should write prompts instead of engineers, how Apollo measures AI quality across their products, and the practical strategies they've developed after some early missteps. Whether you're an aspiring AI PM or an engineering leader trying to structure your team effectively, this conversation offers useful lessons on what actually drives AI product success. 

On this episode of Deployed: The AI Product Podcast, we sit down with Ben Kus, CTO of Box, to unpack how they built a secure, scalable AI platform within their enterprise content management system. Ben shares candid insights from Box's journey integrating AI capabilities while maintaining enterprise-grade security for sensitive customer data. Learn practical strategies for evaluating AI quality without accessing customer data, building internal platforms that engineering teams want to use, and designing architecture that can evolve with rapid AI advances. Whether you're integrating LLMs into an established product or building new AI features, this conversation offers valuable lessons on balancing innovation with enterprise requirements. Join Ian, Co-Founder and CEO of Freeplay, for this in-depth discussion on scaling AI responsibly in the enterprise.

In this episode, we sit down with Arya Asemanfar, Product and Engineering leader at Sierra, to explore the future of AI-powered enterprise agents. Arya breaks down how Sierra is transforming customer experiences by building agents that go beyond traditional chatbots—taking meaningful actions, embodying brand voice, and scaling reliably for unique business needs.Learn how Sierra approaches agent development with their innovative “Agent OS,” solves challenges like tool hallucination, and co-designs solutions with customers. Arya also shares actionable insights for product and engineering leaders, from building better evaluation systems to designing intuitive feedback loops.Topics covered in this episode:What Are Enterprise Agents?The difference between traditional chatbots and AI-powered agents that take meaningful actions.Examples of how Sierra’s agents transform customer service interactions (e.g., returns, exchanges).Building Scalable AI AgentsThe importance of robust architecture for reliability and performance.How Sierra’s “Agent OS” supports the full lifecycle of agent development—from design to monitoring.Addressing tool hallucination and ensuring agents only take actionable, reliable steps.Using evaluation frameworks to test and refine agent behavior at scale.Collaborating with CustomersWhy each agent is treated as a unique product tailored to a customer’s brand, policies, and processes.The co-design process and how it ensures agents align with business needs.Actionable Advice for Teams Building AI AgentsStart with concrete customer examples to develop intuition and build better agents.Implement evaluation systems early to accelerate learning and iteration.Invest in tools and processes to streamline human feedback and testing.The Future of AI and Product DesignEmerging paradigms that will transform how users interact with software.Predictions for how AI will shape new user experiences beyond automation.

In this episode of Deployed: The AI Product Podcast, we talk with Nick Francis, CEO and Co-founder, and Luis Morales, VP of Engineering at Help Scout, about their journey integrating AI into their established (13 years in market!) customer support platform.Nick and Luis share candid insights on:• How they shifted from skepticism about AI to embracing it as a tool for delighting customers• Their process for experimenting with AI features, from summarization to automated email drafts• Challenges in prompt engineering and building effective RAG systems• Creating a new role for an AI product quality expert with deep customer knowledge• Transitioning to an experimentation-driven engineering culture• Making the bold decision to completely overhaul their business model and pricingThe conversation covers both high-level strategy and tactical details of Help Scout's AI development process. Nick and Luis offer valuable perspectives for any company looking to thoughtfully integrate AI capabilities into existing products.For product and engineering leaders navigating the complexities of AI adoption, this episode provides practical advice on balancing innovation with customer needs. Tune in to learn how Help Scout is leveraging AI to enhance the customer support experience while staying true to their values.

Kyle Nesbit, a longtime Googler and AI expert, joins us on Deployed to share lessons from his 17+ years at the forefront of distributed systems, machine learning, and AI-driven product innovation. Kyle has helped build foundational technologies like BigQuery and worked on early large language model (LLM) development at Google, giving him a unique perspective on how teams can successfully transition from traditional engineering to modern AI-focused workflows.In this episode, we explore:The challenges and opportunities of transitioning traditional engineering teams to LLM developmentWhy starting with evaluation metrics is the foundation for successPractical strategies for iterative improvement and guardrail designHow to balance product priorities and quality trade-offs when scaling AI systemsThe real story behind AI demos and how to communicate progress effectivelyFoundational issues in data discovery and access—and why solving them matters more than chasing trends

In this episode of Deployed, we sit down with Sara Beykpour, Co-founder and CEO of Particle, to discuss how they're using AI to transform how people consume news. Particle, which just launched last week, organizes news coverage across multiple sources into an easy-to-read, summarized, and personalized feed.What makes Particle particularly interesting is how seamlessly they've integrated AI into the core news reading experience. Rather than building yet another AI chatbot, they've created an intuitive news app where the AI works behind the scenes to deliver better summaries and insights.In this conversation, Sara shares valuable lessons about building AI products that actually work for customers, including:• How they approach quality and trust when using AI to summarize news• Their practical process for developing and improving AI features• Key learnings about evaluation pipelines and prompt engineering• Insights on working with publishers in the AI eraTune in to hear Sara's perspective on the future of AI in media and her advice for other founders building in this rapidly evolving space. Whether you're a product manager, engineer, or just curious about the intersection of AI and media, this episode offers actionable insights you can apply to your own work.Check out Particle at particlenews.ai!

Join us for an insightful conversation with Eliza Cabrera (Principal Product Manager) and Beau Lyddon (Principal Engineer) of Workday as they share their journey implementing generative AI at enterprise scale. As one of the first major enterprise software companies to roll out GenAI features, Workday offers valuable lessons for product and engineering teams navigating this technology.Learn how Workday approached everything from their first MVP features to scaling AI across their platform, including:How they identified the right initial use cases and measured successTheir approach to prompt engineering, model selection, and RAG architectures  Managing enterprise customer expectations around data privacy and complianceCreating an AI playbook to help teams across the company adopt GenAIBalancing innovation with enterprise-grade reliabilityThis episode offers practical insights for anyone working to bring generative AI capabilities to enterprise software products. Eliza and Beau share candid perspectives on what worked, what didn't, and how to think about scaling AI responsibly in complex enterprise environments.Whether you're just getting started with GenAI or working to scale it across your organization, this conversation provides valuable lessons from leaders who have successfully navigated these challenges at one of the world's largest enterprise software companies.

In episode #2 of Deployed: The AI Product Podcast, we meet with Mike Conover, co-founder & CEO of Brightwave to discuss the capabilities and challenges of building AI systems for financial research.Brightwave is an AI research assistant for financial professionals. Their product generates insightful and trustworthy financial analyses on demand.We get into the details of what it takes to make Brightwave work well, and lessons learned along the way including:Some of the limitations of LLMs, and what to do about them — especially when it comes to summarizing lots of content (tl;dr - long context windows don’t solve everything)How they’ve developed their eval suite through a practical iteration process among in-house finance experts, product, and engineeringThoughts on staffing AI engineering teams, including what he’s seen work to get strong software engineers up to speed working with LLMsLet us know what you think in the comments.

In this episode, Freeplay co-founder & CEO, Ian Cairns sits down with Jeff Seibert, co-founder & CEO of Digits to discuss the practical applications of AI in the finance world and the lessons learned from using AI in production. You can read a full recap with show notes here.Jeff emphasizes the importance of choosing the right type of AI model for each use case and highlights the limitations of generative AI models. He also shares examples of how AI has improved the product experience at Digits, including predictive models for AI bookkeeping, similarity models for transaction analysis, document extraction models for invoice processing, and autonomous agents for researching unknown transactions. We also dig into the challenges of closing the gap between AI accuracy and human expertise in accounting. Digits uses generative AI to help with transaction categorization and financial reporting. Digits is focused on solving customer problems and uses AI as a powerful tool to deliver value. Give the episode a listen and share your feedback!