Thomas Schmidt: AI Agents, Shopify Culture, Remote Work, Agritech

https://is1-ssl.mzstatic.com/image/thumb/Podcasts221/v4/ce/23/5e/ce235e0b-2be8-cf4a-706a-fde969610166/mza_1574941168175972086.png/600x600bb.jpg

The AI and ML Conversations with Iavor Botev

Iavor Botev

5 episodes

2 weeks ago

Conversations with AI and ML experts on building real-world systems, navigating career growth, and exploring the future of generative AI. From messy data pipelines to scaling infrastructure, from proof of concept to production, we dive into the technical lessons, human stories, and big-picture impacts shaping the future of AI.

Technology

RSS

All content for The AI and ML Conversations with Iavor Botev is the property of Iavor Botev and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Technology

https://hosting-media.rs-prod.riverside.fm/media/podcasts/53dfbffe-e4f7-495d-b6d8-6b7fc4106fcc/episodes/64191487-e7de-470d-b0af-c2dc16d6ee1b/images/1fd92e60-e60b-4b2f-9ed4-3a910585838c.png

Thomas Schmidt: AI Agents, Shopify Culture, Remote Work, Agritech | AI and ML Conversations #5

The AI and ML Conversations with Iavor Botev

1 hour 27 minutes 20 seconds

3 weeks ago

Thomas Schmidt: AI Agents, Shopify Culture, Remote Work, Agritech | AI and ML Conversations #5

🎙️ In episode 5 of "AI and ML Conversations," I chat with Thomas Schmidt, an AI engineer at Metabase, who pivoted from agricultural science to data at Shopify and AI agent development. 🚀

Thomas shares his unique journey from a master's thesis on predicting farm animals health, to roles at an agritech startup, Shopify, and now building Metabase's AI analytics agent (Metabot).

We dive into key topics like the importance of context in decision-making and communication (like using TLDRs in Slack and "assume good intent"), remote work rituals (retrospectives for safe feedback), and the high technical standards at Shopify vs. startups.

Thomas then talks about practical AI agent challenges such as dealing with the AI overhype, benchmarks for evaluation (query correctness, hallucination rates), choosing frameworks like Langchain for control, and managing costs.

Thomas advises juniors to stay curious, follow unconventional paths, master communication to stand out, and use LLMs intentionally without blindly relying on them.

Links

Iavor Botev: www.linkedin.com/in/iavorbotev/

Thomas Schmidt: https://www.linkedin.com/in/thomas-heinz-schmidt/

Talk by Thomas at the AI Engineer conference - Everything That Can Go Wrong Building Analytics Agents (And How We Survived It): https://www.youtube.com/watch?v=EnvozxnWjP4

Article by Thomas on effective (data) communication: https://dataanalysis.substack.com/p/how-to-communicate-data-effectively

Timestamps
00:00 – Introduction
01:12 – Thomas’s background: From dairy farm to data science
06:46 – Learning to code & the transition from Excel to R
10:28 – Breaking into the industry at an agri-tech startup
15:25 – Simple solutions vs. AI hype in agriculture
20:03 – Why context is everything in remote communication
29:22 – The power of retrospectives & team rituals
34:51 – Working at Shopify: Trust batteries & engineering standards
45:33 – Using LLMs for personal productivity & coding
53:46 – Building AI Agents at Metabase: Reality vs. Hype
59:43 – Challenges in agent optimization & evaluation
01:06:38 – Tools & Frameworks: LangChain, LightLLM, Pydantic AI
01:11:57 – Managing the costs of LLM-powered features
01:16:56 – Career advice for juniors & staying curious
01:24:26 – Closing