A podcast for people who build with AI. Long-format conversations with people shaping the field about agents, evals, multimodal systems, data infrastructure, and the tools behind them. Guests include Jeremy Howard (fast.ai), Hamel Husain (Parlance Labs), Shreya Shankar (UC Berkeley), Wes McKinney (creator of pandas), Samuel Colvin (Pydantic) and more. <br/><br/><a href="https://hugobowne.substack.com?utm_medium=podcast">hugobowne.substack.com</a>
Vanishing Gradients
Claim This Podcastby Hugo Bowne-Anderson
4.8(22 reviews)
82 episodes
Updated Weekly
Accepts GuestsHas SponsorsLocation 🇺🇸
80
Podcast Authority
BetaExcellentBased on show quality, social media presence, reviews, charts, and more
Quality92
Social0
YouTube86
Engagement85
Podcast Overview
A podcast for people who build with AI. Long-format conversations with people shaping the field about agents, evals, multimodal systems, data infrastructure, and the tools behind them. Guests include Jeremy Howard (fast.ai), Hamel Husain (Parlance Labs), Shreya Shankar (UC Berkeley), Wes McKinney (creator of pandas), Samuel Colvin (Pydantic) and more. <br/><br/><a href="https://hugobowne.substack.com?utm_medium=podcast">hugobowne.substack.com</a>
Language
🇺🇲
Publishing Since
2/16/2022
Unlock The Full Podcast Authority Score Report
See how your podcast performs across key metrics
80
Podcast Authority
BetaExcellentBased on show quality, social media presence, reviews, charts, and more
Quality92
Social0
YouTube86
Engagement85
10
Excellent Areas
1
Good Performance
8
Growth Opportunities
excellent
Episode Length
45 minutes
Performing excellently!
good
iTunes Tags
6.9/10
Recommendations available
Unlock the full report to see detailed tips
needs improvement
Publishing Consistency
Every 22 days
Recommendations available
Unlock the full report to see detailed tips
+16 More Metrics
Unlock comprehensive insights including:
- • YouTube presence analysis
- • Social media reach metrics
- • RSS compliance scoring
- • Podcast 2.0 features
- • Technical standards
What's Included in Your Full Report
Detailed Analytics
- Complete breakdown of all 19 authority metrics
- Personalized recommendations for each metric
- Industry benchmarks and comparisons
- Technical RSS feed analysis and compliance scoring
Growth Strategies
- Step-by-step action plans for improvement
- Quick wins to boost your score immediately
- Pro tips from successful podcasters
Get your free podcast insights report
See how your show performs across every key metric
Instant delivery
No spam
Attract Better Guests
High authority scores make your podcast more attractive to industry leaders and influencers who want to appear on credible shows.
Secure Sponsorships
Sponsors look for podcasts with proven authority and engagement. Your score demonstrates your podcast's value to potential partners.
Grow Your Audience
Understanding your strengths and weaknesses helps you make data-driven decisions to expand your listener base effectively.
2 verified contact emails on file for Vanishing Gradients
Pitch yourself as a guest, propose sponsorships, or reach out directly to the host.
Recent Episodes
August 3, 2026
If Developers Build on Chinese Open-Weight Models, Who Leads AI?
Hugo Bowne-Anderson interviews AI researcher Sebastian Raschka about evaluating open-weight models and their impact on AI leadership.
July 25, 2026
Four Months Inside a Production AI Agent: What Real Users Changed
ML/AI Engineer William Horton shares how real user feedback reshaped Maven Assistant's roadmap and engineering, revealing crucial insights for production AI agents.
July 17, 2026
Building an Enterprise AI Agent for Healthcare
<p>Every capability in an agent needs its own evidence and release bar. A model-provider slip, an incorrect tool call, and a wrong fertility-benefits answer should not be held to the same pass rate.</p><p>William Horton, Staff AI Engineer at Maven Clinic, joined us the day after Maven Assistant reached its first external users. The agent helps members inside Maven Clinic’s women’s and family healthcare platform find providers, manage appointments, navigate Maven, and get basic health information. William had spent much of launch day reading chat traces and turning the surprises into product decisions and tests.</p><p>William shows how a production failure moves through Maven’s system: the trace becomes a regression case, code handles deterministic checks, and LLM judges cover behavior that cannot be reduced to exact outputs. Human labels calibrate those judges, while the consequence of a wrong answer determines whether the capability ships. You can apply the same release workflow to the agent you are building now.</p><p>“For a lot of our tool-call evaluation, I’ll accept that it runs ten times and passes nine times. Going for that ten out of ten is just not worth the effort.”</p><p>— William Horton, Staff AI Engineer, Maven Clinic</p><p>You can also find the full episode on <a target="_blank" href="https://open.spotify.com/show/3yuz89gqAhcMcdy3SZPe4X">Spotify</a>, <a target="_blank" href="https://podcasts.apple.com/us/podcast/vanishing-gradients/id1610318868">Apple Podcasts</a>, and <a target="_blank" href="https://www.youtube.com/watch?v=21IFkFUy9es">YouTube</a>.</p><p>👉 <strong>Want to build agents from the ground up? Registration is open for </strong><a target="_blank" href="https://maven.com/hugo-stefan/build-ai-agents-from-first-principles"><strong>Build AI Agents from First Principles</strong></a><strong>,</strong> <strong>a live workshop on the loops, tools, context, harnesses, and engineering decisions behind useful AI agents. You'll learn how to design agent systems from first principles, with enough structure to decide which harness patterns your product actually needs.</strong> <strong>Sign up today with </strong>vg-code<strong> for 10% off </strong>👈</p><p></p><p>In This Episode</p><p>* <strong>The architecture behind Maven Assistant.</strong> A stronger lead agent routes requests to four narrower specialists for appointments, provider search, health questions, and Maven support. Hard guardrails run before dynamic routing.</p><p>* <strong>Why an enterprise healthcare assistant only needs 15 to 20 tools.</strong> Maven divides a manageable toolset across its specialists instead of exposing one model to hundreds of choices. Existing APIs become safer agent tools, with user identity and other application state injected by code.</p><p>* <strong>Turn failures into the cheapest reliable eval.</strong> A response claiming the agent was “made by Google” became a string check, tool calls are verified deterministically, and LLM judges handle clinical accuracy and other qualitative behavior.</p><p>* <strong>Set release thresholds from the consequences.</strong> Nine passes in ten can be acceptable for a cheap failure. Maven withheld benefits answers that could influence tens of thousands of dollars and routes self-harm language directly to human support.</p><p>* <strong>Let production change the product and the test set.</strong> Early chats changed the roadmap, became regression cases, exposed weaknesses in the judges, and supplied realistic opening messages for simulated users.</p><p>Join the Four-Month Follow-Up</p><p>This episode was recorded live inside our Building AI Applications course the day after Maven Assistant reached its first external users. By the follow-up four months later, Maven will have a much larger body of real conversations. William will return to compare the launch assumptions with what members actually used, which evals changed, and how newer models altered the system.</p><p><a target="_blank" href="https://luma.com/wvlr4y93">Register to join the livestream or receive the recording afterwards</a>.</p><p>Resources</p><p>* <a target="_blank" href="https://www.mavenclinic.com/">Maven Clinic</a></p><p>* <a target="_blank" href="https://www.prnewswire.com/news-releases/maven-clinic-introduces-maven-intelligence-an-ai-powered-orchestration-layer-for-womens-and-family-health-302715171.html">Maven introduces Maven Intelligence</a></p><p>* <a target="_blank" href="https://developers.googleblog.com/agent-development-kit-easy-to-build-multi-agent-applications/">Google Agent Development Kit</a></p><p></p><p>👉 <strong>Want to build agents from the ground up? Registration is open for </strong><a target="_blank" href="https://maven.com/hugo-stefan/build-ai-agents-from-first-principles"><strong>Build AI Agents from First Principles</strong></a><strong>,</strong> <strong>a live workshop on the loops, tools, context, harnesses, and engineering decisions behind useful AI agents. You'll learn how to design agent systems from first principles, with enough structure to decide which harness patterns your product actually needs.</strong> <strong>Sign up today with </strong>vg-code<strong> for 10% off </strong>👈</p><p><strong>How You Can Support Vanishing Gradients</strong></p><p>Vanishing Gradients is a podcast, workshop series, blog, and newsletter focused on what you can build with AI right now. Over 70 episodes with expert practitioners from Google DeepMind, Netflix, Stanford, and elsewhere. Hundreds of hours of free, hands-on workshops. All independent, all free.</p><p>If you want to help keep it going:</p><p>* <a target="_blank" href="https://hugobowne.substack.com/subscribe">Become a paid subscriber, from $8/month</a></p><p>* Share this with a builder who’d find it useful</p><p>* <a target="_blank" href="https://www.youtube.com/@vanishinggradients">Subscribe to our YouTube channel</a></p><p>* <a target="_blank" href="https://hugobowne.github.io/workshops">Join one of our other workshops here</a></p> <br/><br/>Get full access to Vanishing Gradients at <a href="https://hugobowne.substack.com/subscribe?utm_medium=podcast&utm_campaign=CTA_4">hugobowne.substack.com/subscribe</a>
82 total episodes available with 54 transcripts
Recent guests on Vanishing Gradients
Guests from recent episodes — sign up to see every guest that has ever appeared on this show.
Sebastian Raschka
Guest
William Horton
Guest
Thomas Wiecki
Guest
Vincent Warmerdam
Guest
Wes McKinney
Guest
Jeremiah Lowin
Guest
Randy Olson
Guest
Bryan Bischof
Guest
Samuel Colvin
Guest
Alex Strick van Linschoten
Guest
Marcel Kornacker
Guest
Alison Hill
Guest
Similar Podcasts
Discover related shows you might enjoy
Talk Python To Me
Michael Kennedy
Super Data Science: ML & AI Podcast with Jon Krohn
Jon Krohn
Machine Learning Street Talk (MLST)
Machine Learning Street Talk (MLST)
The Pragmatic Engineer Podcast
Gergely Orosz
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Sam Charrington
Dwarkesh Podcast
Dwarkesh Patel
No Priors: Artificial Intelligence | Machine Learning | Technology | Startups
Conviction
Practical AI: Machine Learning, Data Science
Daniel Whitenack and Chris Benson
The Real Python Podcast
Real Python
Training Data
Sequoia Capital
DataFramed
DataCamp
Unsupervised Learning
by Redpoint Ventures
How I AI
Claire Vo
Last Week in AI
Skynet Today
The AI Breakdown: Daily Artificial Intelligence News and Discussions
Nathaniel Whittemore
Deep-dive analytics for Vanishing Gradients
Frequently asked questions
Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.
- What is Vanishing Gradients?
- How often does this podcast release new episodes?
This podcast updates weekly.
- Where can I listen to this podcast?
This podcast is available on 10 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.
- Does this podcast accept guests?
Yes, this podcast regularly features guests.
Legal Disclaimer
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at hey@podengine.ai for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.