Poducer Logo
Chain of Thought | AI Agents, Infrastructure & Engineering

Chain of Thought | AI Agents, Infrastructure & Engineering

AI is reshaping infrastructure, strategy, and entire industries. Chain of Thought is the podcast where builders reason through what's changing. Host Conor Bronsdon sits down with the engineers and founders shipping AI in production to get past the hype into what's working and what isn't. Episodes cover model infrastructure, inference, agent frameworks, evaluation, and developer tools. Guests have come from NVIDIA, Google DeepMind, AMD, Databricks, Vercel, and more. Every episode carries a full transcript and show notes at chainofthought.show. New episodes weekly. Conor Bronsdon is an independent consultant and angel investor in AI infrastructure and developer tools. He led...

Episodes icon

10

First Code, Then AGI: 18 Months Later | Poolside Founders

First Code, Then AGI: 18 Months Later | Poolside Founders

<p>In May 2025, Poolside's founders, Jason Warner and Eiso Kant, told me the road to general intelligence runs through code. Their reason: code is one of the few places a model can try something, run it, and find out right away whether it worked.</p><p>In August 2026, NVIDIA paid $6 billion to license Poolside's Model Factory, the system Poolside uses to build and train its models, and invested another $1 billion in the company. Poolside wasn't sold. Jason and Eiso still run it.</p><p>They laid out the thesis 15 months before the deal.</p><p>In 2023, Jason and Eiso bet...

Ellipse
Writing Code Was Never the Bottleneck | CloudBees CEO Moritz Plassnig

Writing Code Was Never the Bottleneck | CloudBees CEO Moritz Plassnig

<p>Enterprises are spending tens of millions, sometimes hundreds of millions, on tokens for their engineers. Ask what they're shipping as a result and, Moritz Plassnig says, the answer can be just a few more pull requests.</p><p>In big companies, he says, writing code was never the bottleneck. Builds run for hours. Policies still require a human to review every line. Releases wait weeks for security and governance sign-off. Generating more code doesn't move any of that.</p><p>Moritz is the CEO of CloudBees and the founder of Codeship, the CI/CD platform CloudBees acquired in 2018. He...

Ellipse
This is the worst AI tutor we'll ever have | DataCamp

This is the worst AI tutor we'll ever have | DataCamp

<p>DataCamp tested an early version of its AI tutor against its classic courses, and the tutor won: willingness to pay, engagement and satisfaction were all higher. It was also easily ten to twenty times more expensive per hour of learning than DataCamp's previous setup. Financially, Jonathan says, shipping the better product would have made the business worse.</p><p>He expects that cost to fall until it looks like the cost of serving DataCamp's interactive courses. The only question, he says, is whether that takes four to eight weeks or another year.</p><p>He's building the tutor on...

Ellipse
The Infrastructure Behind Agents That Run for Months

The Infrastructure Behind Agents That Run for Months

<p>Tony Holdstock-Brown is the CEO and co-founder of Inngest, which built durable workflows for background jobs before the agent wave arrived. He says most Inngest customers no longer log into the UI. Their agents check on what they have built through the API, the CLI and MCP, and people who build with agents activate at about 93 percent, against roughly 40 percent before.</p><p>Holdstock-Brown defines a long-running agent as one that lives for months and builds up its own context. Running one means orchestrating sub-agents, sandboxes and state for every customer, and he argues that orchestration layer becomes the...

Ellipse
Asking Your Team to Automate Their Jobs With AI | Cloudera's Shayde Christian

Asking Your Team to Automate Their Jobs With AI | Cloudera's Shayde Christian

<p>Shayde Christian's team at Cloudera has built AI agents that can open a sales opportunity in the CRM and send a customer a 30% discount on training. He still isn't authorized to switch them on in production. Cloudera runs as conservatively as the regulated customers it serves, and the business owners want more proof of reliability and accuracy first. The AI tool his team does lean on every day is, in his words, barely AI.</p><p>Full transcript and chapters: https://chainofthought.show/podcast/82-asking-your-team-to-automate-their-jobs-with-ai-clouderas-shayde-christian/</p><p>Shayde Christian is Chief Data and Analytics Officer at Cloudera. He walks...

Ellipse
Agents Are Overtaking Humans in Search: Why Search Must Be Rebuilt

Agents Are Overtaking Humans in Search: Why Search Must Be Rebuilt

<p>Saahil Jain joined You.com as a founding engineer in 2020, when it was a consumer search engine competing with Google. Now its CTO, he builds search for AI agents, and he argues that however smart models get, they will still need tools to find out what is happening in the world.</p> <p>His analogy: we built the self-driving cars before the roads. He walks through which work he expects to move inside the model, why better models made harnesses matter less, and why cheaper open models and routing are giving harnesses a new job. He says he changed...

Ellipse
How Cisco Secures Personal AI Assistants for 90,000 Employees | DJ Sampath

How Cisco Secures Personal AI Assistants for 90,000 Employees | DJ Sampath

<p>Cisco is giving each of its 90,000 employees a personal AI agent. Some of those same employees are already connecting agents from outside the security boundary without asking IT. DJ Sampath, SVP and GM of AI Software and Platform at Cisco, walks through what had to be in place before the rollout: scanning every prompt, sandboxing each agent, keeping agents multi-tenant, scanning the skills and tools people bring in, and settling which identities an agent may act as.</p><p>New episodes, the ideas behind them and Conor's essays land in the Chain of Thought newsletter first. Subscribe: https://newsletter...

Ellipse
For AI Agent Fleets, the Model Is Rarely the Bottleneck | Theory Ventures' Andy Triedman

For AI Agent Fleets, the Model Is Rarely the Bottleneck | Theory Ventures' Andy Triedman

<p>Andy Triedman is a partner at Theory Ventures, and he is building his own software factory, while assessing how startups are leveraging theirs. His read after running agent fleets: the models are frankly good enough for most of the work. The vast majority of things you'd ask an agent to do are not intelligence limited. They are context limited. We have infrastructure work to do - but we can be more ambitious!</p><p>Full transcript and chapters: https://chainofthought.show/podcast/79-for-ai-agent-fleets-the-model-is-rarely-the-bottleneck-theory-ventures-andy-triedman/</p><p>So the hard part moves upstream. Deciding what the agents should build, what they...

Ellipse
What Breaks When Agents Become the Customer | Svix CEO Tom Hacohen

What Breaks When Agents Become the Customer | Svix CEO Tom Hacohen

<p>What breaks when agents become the customer? Most of the integration layer, APIs, SDKs and webhooks alike, was built for human developers and for servers that are always listening. Agents are neither.</p><p>Full transcript and chapters: https://chainofthought.show/podcast/78-what-breaks-when-agents-become-the-customer-svix-ceo-tom-hacohen/</p><p>When an agent runs on a laptop, closing the lid takes down the tunnel its webhooks come through. When the lid opens, it gets a storm of retries from 12 hours earlier. Svix founder and CEO Tom Hacohen's answer is to let the agent poll for what it missed.</p><p>Svix delivers webhooks for...

Ellipse
Switching Models Shouldn't Mean Starting Over | Walrus Protocol's Kimberly Logan

Switching Models Shouldn't Mean Starting Over | Walrus Protocol's Kimberly Logan

<p>If your agent's memory lives inside one model provider, switching models or harnesses means starting over. You need portable memory - yet when switching agent memory between models, you can swing accuracy by thirteen points or more, depending on which model reads them back.</p><p>Full transcript and chapters: https://chainofthought.show/podcast/77-switching-models-shouldnt-mean-starting-over-walrus-protocols-kimberly-logan/</p><p>Kimberly Logan, Head of Product at the Walrus Foundation, where she builds Walrus Memory, joins Chain of Thought to discuss how to build portable and verifiable memory for AI agents - and why Walrus's decentralized storage network has proved an apt primitive...

Ellipse
Poducer Logo