How AI Is Built
by Nicolay Gerold
Latest episode
#056 Building Solo: How One Engineer Uses AI Agents to Ship…
#056 Building Solo: How One Engineer Uses AI Agents to Ship…
About this podcast
Real engineers. Real deployments. Zero hype. We interview the top engineers who actually put AI in production. Learn what the best engineers have figured out through years of experience. Hosted by Nicolay Gerold, CEO of Aisbach and CTO at Proxdeal and Multiply Content.
Episodes
The newest 20 of 63 episodes
- #056 Building Solo: How One Engineer Uses AI Agents to Ship Production Code · 1 h 12 minNicolay here, Most AI coding conversations focus on which model to use. This one focuses on workflow - the specific commands, git strategies, and review processes that let one…
- #055 Embedding Intelligence: AI's Move to the Edge · 1 h 5 minNicolay here, while everyone races to cloud-scale LLMs, Pete Warden is solving AI problems by going completely offline. No network connectivity required. Today I have the chance…
- #054 Building Frankenstein Models with Model Merging and the Future of AI · 1 h 6 minNicolay here,most AI conversations focus on training bigger models with more compute. This one explores the counterintuitive world where averaging weights from different models…
- #053 AI in the Terminal: Enhancing Coding with Warp · 1 h 4 minNicolay here, Most AI coding tools obsess over automating everything. This conversation focuses on the right balance between human skill and AI assistance - where manual context…
- #052 Don't Build Models, Build Systems That Build Models · 59 minNicolay here, Today I have the chance to talk to Charles from Modal, who went from doing a PhD on neural network optimization in the 2010s - when ML engineers could build models…
- #051 Build systems that can be debugged at 4am by tired humans with no context · 1 h 5 minNicolay here, Today I have the chance to talk to Charity Majors, CEO and co-founder of Honeycomb, who recently has been writing about the cost crisis in observability. "Your…
- #050 Bringing LLMs to Production: Delete Frameworks, Avoid Finetuning, Ship Faster · 1 h 6 minNicolay here, Most AI developers are drowning in frameworks and hype. This conversation is about cutting through the noise and actually getting something into production. Today I…
- #050 TAKEAWAYS Bringing LLMs to Production: Delete Frameworks, Avoid Finetuning, Ship Faster · 11 minNicolay here, Most AI developers are drowning in frameworks and hype. This conversation is about cutting through the noise and actually getting something into production. Today I…
- #049 BAML: The Programming Language That Turns LLMs into Predictable Functions · 1 h 2 minNicolay here, I think by now we are done with marveling at the latest benchmark scores of the models. It doesn’t tell us much anymore that the latest generation outscores the…
- #049 TAKEAWAYS BAML: The Programming Language That Turns LLMs into Predictable Functions · 1 h 12 minNicolay here, I think by now we are done with marveling at the latest benchmark scores of the models. It doesn’t tell us much anymore that the latest generation outscores the…
- #048 TAKEAWAYS Why Your AI Agents Need Permission to Act, Not Just Read · 7 minNicolay here, most AI conversations obsess over capabilities. This one focuses on constraints - the right ones that make AI actually useful rather than just impressive demos…
- #048 Why Your AI Agents Need Permission to Act, Not Just Read · 57 minNicolay here, most AI conversations obsess over capabilities. This one focuses on constraints - the right ones that make AI actually useful rather than just impressive demos…
- #047 Architecting Information for Search, Humans, and Artificial Intelligence · 57 minToday on How AI Is Built, Nicolay Gerold sits down with Jorge Arango, an expert in information architecture. Jorge emphasizes that aligning systems with users' mental models is…
- #046 Building a Search Database From First Principles · 53 minModern search is broken. There are too many pieces that are glued together. • Vector databases for semantic search • Text engines for keywords • Rerankers to fix the results •…
- #045 RAG As Two Things - Prompt Engineering and Search · 1 h 2 minJohn Berryman moved from aerospace engineering to search, then to ML and LLMs. His path: Eventbrite search → GitHub code search → data science → GitHub Copilot. He was drawn to…
- #044 Graphs Aren't Just For Specialists Anymore · 1 h 3 minKuzu is an embedded graph database that implements Cypher as a library. It can be easily integrated into various environments—from scripts and Android apps to serverless…
- #043 Knowledge Graphs Won't Fix Bad Data · 1 h 10 minMetadata is the foundation of any enterprise knowledge graph. By organizing both technical and business metadata, organizations create a “brain” that supports advanced…
- #042 Temporal RAG, Embracing Time for Smarter, Reliable Knowledge Graphs · 1 h 33 minDaniel Davis is an expert on knowledge graphs. He has a background in risk assessment and complex systems—from aerospace to cybersecurity. Now he is working on “Temporal RAG” in…
- #041 Context Engineering, How Knowledge Graphs Help LLMs Reason · 1 h 33 minRobert Caulk runs Emergent Methods, a research lab building news knowledge graphs. With a Ph.D. in computational mechanics, he spent 12 years creating open-source tools for…
- #040 Vector Database Quantization, Product, Binary, and Scalar · 52 minWhen you store vectors, each number takes up 32 bits. With 1000 numbers per vector and millions of vectors, costs explode. A simple chatbot can cost thousands per month just to…







