What 'evals' actually mean in practice

Aishwarya Naresh Reganti and Kiriti Badam have helped build and launch more than 50 enterprise AI products across companies like OpenAI, Google, Amazon, and Databricks. Based on these experiences, they’ve developed a small set of best practices for building and scaling successful AI products. The goal of this conversation is to save you and your team a lot of pain and suffering.

We discuss:

1. Two key ways AI products differ from traditional software, and why that fundamentally changes how they should be built

2. Common patterns and anti-patterns in companies that build strong AI products versus those that struggle

3. A framework they developed from real-world experience to iteratively build AI products that create a flywheel of improvement

4. Why obsessing about customer trust and reliability is an underrated driver of successful AI products

5. Why evals aren’t a cure-all, and the most common misconceptions people have about them

6. The skills that matter most for builders in the AI era

—

Brought to you by:

Merge—The fastest way to ship 220+ integrations: https://merge.dev/lenny

Strella—The AI-powered customer research platform: https://strella.io/lenny

Brex—The banking solution for startups: https://www.brex.com/product/business-account?ref_code=bmk_dp_brand1H25_ln_new_fs

—

Transcript: https://www.lennysnewsletter.com/p/what-openai-and-google-engineers-learned

—

My biggest takeaways (for paid newsletter subscribers): https://www.lennysnewsletter.com/i/183007822/referenced

—

Get 15% off Aishwarya and Kiriti’s Maven course, Building Agentic AI Applications with a Problem-First Approach, using this link: https://bit.ly/3V5XJFp

—

Where to find Aishwarya Naresh Reganti:

• LinkedIn: https://www.linkedin.com/in/areganti

• GitHub: https://github.com/aishwaryanr/awesome-generative-ai-guide

• X: https://x.com/aish_reganti

—

Where to find Kiriti Badam:

• LinkedIn: https://www.linkedin.com/in/sai-kiriti-badam

• X: https://x.com/kiritibadam

—

Where to find Lenny:

• Newsletter: https://www.lennysnewsletter.com

• X: https://twitter.com/lennysan

• LinkedIn: https://www.linkedin.com/in/lennyrachitsky/

—

In this episode, we cover:

(00:00) Introduction to Aishwarya and Kiriti

(05:03) Challenges in AI product development

(07:36) Key differences between AI and traditional software

(13:19) Building AI products: start small and scale

(15:23) The importance of human control in AI systems

(22:38) Avoiding prompt injection and jailbreaking

(25:18) Patterns for successful AI product development

(33:20) The debate on evals and production monitoring

(41:27) Codex team’s approach to evals and customer feedback

(45:41) Continuous calibration, continuous development (CC/CD) framework

(58:07) Emerging patterns and calibration

(01:01:24) Overhyped and under-hyped AI concepts

(01:05:17) The future of AI

(01:08:41) Skills and best practices for building AI products

(01:14:04) Lightning round and final thoughts

—

Referenced:

• LevelUp Labs: https://levelup-labs.ai/

• Why your AI product needs a different development lifecycle: https://www.lennysnewsletter.com/p/why-your-ai-product-needs-a-different

• Booking.com: https://www.booking.com

• Research paper on agents in production (by Matei Zaharia’s lab): https://arxiv.org/pdf/2512.04123

• Matei Zaharia’s research on Google Scholar: https://scholar.google.com/citations?user=I1EvjZsAAAAJ&hl=en

• The coming AI security crisis (and what to do about it) | Sander Schulhoff: https://www.lennysnewsletter.com/p/the-coming-ai-security-crisis

• Gajen Kandiah on LinkedIn: https://www.linkedin.com/in/gajenkandiah

• Rackspace: https://www.rackspace.com

• The AI-native startup: 5 products, 7-figure revenue, 100% AI-written code | Dan Shipper (co-founder/CEO of Every): https://www.lennysnewsletter.com/p/inside-every-dan-shipper

• Semantic Diffusion: https://martinfowler.com/bliki/SemanticDiffusion.html

• LMArena: https://lmarena.ai

• Artificial Analysis: https://artificialanalysis.ai/leaderboards/providers

• Why humans are AI’s biggest bottleneck (and what’s coming in 2026) | Alexander Embiricos (OpenAI Codex Product Lead): https://www.lennysnewsletter.com/p/why-humans-are-ais-biggest-bottleneck

• Airline held liable for its chatbot giving passenger bad advice—what this means for travellers: https://www.bbc.com/travel/article/20240222-air-canada-chatbot-misinformation-what-travellers-should-know

• Demis Hassabis on LinkedIn: https://www.linkedin.com/in/demishassabis

• We replaced our sales team with 20 AI agents—here’s what happened | Jason Lemkin (SaaStr): https://www.lennysnewsletter.com/p/we-replaced-our-sales-team-with-20-ai-agents

• Socrates’s quote: https://en.wikipedia.org/wiki/The_unexamined_life_is_not_worth_living

• Noah Smith’s newsletter: https://www.noahpinion.blog

• Silicon Valley on HBO Max: https://www.hbomax.com/shows/silicon-valley/b4583939-e39f-4b5c-822d-5b6cc186172d

• Clair Obscur: Expedition 33: https://store.steampowered.com/app/1903340/Clair_Obscur_Expedition_33/

• Wisprflow: https://wisprflow.ai

• Raycast: https://www.raycast.com

• Steve Jobs’s quote: https://www.goodreads.com/quotes/463176-you-can-t-connect-the-dots-looking-forward-you-can-only

—

Recommended books:

•  When Breath Becomes Air: https://www.amazon.com/When-Breath-Becomes-Paul-Kalanithi/dp/081298840X

• The Three-Body Problem: https://www.amazon.com/Three-Body-Problem-Cixin-Liu/dp/0765382032

• A Fire Upon the Deep: https://www.amazon.com/Fire-Upon-Deep-Zones-Thought/dp/0812515285

—

Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email podcast@lennyrachitsky.com.

—

Lenny may be an investor in the companies discussed.