AI agents will succeed because one tool is better than ten
AI agents can chat, use tools, and write new code all from one interface. That's why they'll last.
Loading…
Ryan Donovan
Who watches the watchers? LLM on LLM evaluations
While using LLMs to judge LLM outputs might seem like the fox guarding the henhouse, turns out it works pretty well (and scales better than humans).
Off with your CMS’s head! Composability and security in headless CMS
Ryan welcomes Sebastian Gierlinger, VP of Engineering at Storyblok, to talk about how headless content management systems (CMS) fit into an increasingly componentized software landscape.
What an MCP implementation looks like at a CRM company
Ryan chats with Karen Ng, EVP of Product at HubSpot, to chat about Model Context Protocol (MCP) and how they implemented it for their server for their CRM product.
Planning to Arm mobile devices with chips that handle AI
Ryan welcomes Geraint North, AI and developer platforms fellow at Arm, to dive into the impact of GenAI on chip design.
From punch cards to prompts: a history of how software got better
Ryan welcomes Darko Mesaroš, Principal Developer Advocate at AWS and all-around computer history buff, to chat about the history of software development improvements and how they made developers made more productive.
Robots in the skies (and they use Transformer models)
Ryan welcomes Nathan Michael, CTO at Shield AI, to discuss what AI looks like in defense technologies, both technically and ethically.
The Great Unracking: Saying goodbye to the servers at our physical datacenter
So long and thanks for all the bits!
Reliability for unreliable LLMs
Large language models are non-deterministic by design. Here's how you can inject a little bit of determinism into GenAI workflows.
You've vibe coded an app. Now what?
On this episode, Ryan chats with Vish Abrams, chief architect at Heroku, about all the work that needs to be done after you’ve vibe coded your dream app.
If an attacker can edit your mobile code, how do you defend your app?
Ryan is joined by Jan Seredynski, Mobile Security Researcher and Pentester at Guardsquare, to talk about how you protect your app when the attackers control the code and the device it runs on.
Stack Exchange knowledge is for everyone (and now available on Snowflake Marketplace)
Snowflake customers can now easily enrich their AI applications and agentic systems with some of the most trusted, highest-quality data available while respecting our community members who provide this content with proper attribution.
WBIT #8: Typescript for gut biomes
Kyle is joined by his former colleague Tyler McEntee, now a senior software engineer at Jona, to talk about doing everything all at once at a startup.
Whether AI is a bubble or revolution, how does software survive?
Money is pouring into the AI industry. Will software survive the disruption it causes?
Next-level observability: live breakpoint debugging
On this episode, Ryan chats with Henrik Rexed, Cloud Native Advocate at Dynatrace, about debugging cloud-based applications like you would a local app.
Without foundational governance, every AI deployment is a liability in disguise: Q&A with Jack Berkowitz of Securiti
Avoiding bad data is just as important in AI; it can open you to fines, lawsuits, and lost customers.
Visually orchestrating data diagnostics but platform agnostic
Ryan chats with Dataiku CEO and cofounder Florian Douetteau about the complexities of the genAI data stack and how his company is orchestrating it.
Generating components, not tokens
On today’s episode, Ben and Ryan chat with Laly Bar-Ilan, Chief Scientist at Bit.
WBIT #7: Exploring WebAssembly with the first SO user to get 10k rep
Kyle interviews Michael Stum, a former Stacker who started (and returned) to answering questions on the community site.
WBIT #6: Be curious, ask questions, and don’t argue with JavaScript
Kyle chats with Jesse Tomchak a software engineer at ClickUp about all the spicy backend takes they could find.
WBIT #5: Building a framework to lure web devs to mobile
Kyle interviews Maria Hutt about building the Ionic mobile framework.
A look under the hood: How (and why) we built Question Assistant
Evaluating question quality and determining the appropriate feedback required some classic ML techniques in addition to our GenAI solution.
How can AI perform on the edge?
What are the capabilities, constraints, and benefits of running AI models on edge devices?
WBIT #4: Using GIS to understand the rivers and the lakes that you’re used to
How a theater major became a fullstack engineer building software to manage climate change.