Building AI agents that fix production incidents before engineers wake up episode artwork

EPISODE · Mar 12, 2026 · 42 MIN

Building AI agents that fix production incidents before engineers wake up

from The Chief AI Officer Show · host Front Lines

Diamond Bishop has spent 15 years building AI systems at Microsoft (Cortana), Amazon (Alexa), and Facebook (PyTorch) before founding an AI DevOps startup that Datadog acquired. Now running Datadog's AI Skunk Works, a deliberately small interdisciplinary team modeled on Lockheed's original, he's focused on a question most enterprise AI teams aren't asking yet: what does your product look like if humans are no longer the primary customer?That question drives everything from Bits AI, their production SRE and security agent, to a set of longer-range bets organized around three pillars: personalized agent learning, enterprise agent infrastructure, and eval. Diamond breaks down how he structures each one, why the demo-to-production gap comes down to data and eval rather than model capability, and where the real unsolved problems in agent development still sit.Topics discussed:Bits AI's capabilities in production across SRE incident response, security analysis and code generationThree-pillar agent development framework: personalized learning, enterprise infrastructure and evalLoRA-style adapter architecture for layering custom per-user agents on top of first-party agentsWhy SRE agent startups without proprietary observability data face a structural disadvantage at production scaleService graph and entity relationship context as a structured alternative to RAG for DevOps agentsSkunk Works team design: staying small and interdisciplinary to move like a startup inside a public companyThe shift from human-operated cloud services to ambient AI-native services built to run with fewer humans over timeCrawl-walk-run path for enterprise agent adoption: from LangGraph-based Python agents to continuously learning systemsWhy concentrating AI research investment in transformer scaling creates long-term architectural riskBuilding agent-native tooling rather than repurposing interfaces designed for humans

Episode metadata supplied by the publisher feed · Published Mar 12, 2026

Diamond Bishop has spent 15 years building AI systems at Microsoft (Cortana), Amazon (Alexa), and Facebook (PyTorch) before founding an AI DevOps startup that Datadog acquired. Now running Datadog's AI Skunk Works, a deliberately small interdisciplinary team modeled on Lockheed's original, he's focused on a question most enterprise AI teams aren't asking yet: what does your product look like if humans are no longer the primary customer?That question drives everything from Bits AI, their production SRE and security agent, to a set of longer-range bets organized around three pillars: personalized agent learning, enterprise agent infrastructure, and eval. Diamond breaks down how he structures each one, why the demo-to-production gap comes down to data and eval rather than model capability, and where the real unsolved problems in agent development still sit.Topics discussed:Bits AI's capabilities in production across SRE incident response, security analysis and code generationThree-pillar agent development framework: personalized learning, enterprise infrastructure and evalLoRA-style adapter architecture for layering custom per-user agents on top of first-party agentsWhy SRE agent startups without proprietary observability data face a structural disadvantage at production scaleService graph and entity relationship context as a structured alternative to RAG for DevOps agentsSkunk Works team design: staying small and interdisciplinary to move like a startup inside a public companyThe shift from human-operated cloud services to ambient AI-native services built to run with fewer humans over timeCrawl-walk-run path for enterprise agent adoption: from LangGraph-based Python agents to continuously learning systemsWhy concentrating AI research investment in transformer scaling creates long-term architectural riskBuilding agent-native tooling rather than repurposing interfaces designed for humans

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

Building AI agents that fix production incidents before engineers wake up

0:00 42:02

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Frequently Asked Questions

How long is this episode of The Chief AI Officer Show?

This episode is 42 minutes long.

When was this The Chief AI Officer Show episode published?

This episode was published on March 12, 2026.

What is this episode about?

Diamond Bishop has spent 15 years building AI systems at Microsoft (Cortana), Amazon (Alexa), and Facebook (PyTorch) before founding an AI DevOps startup that Datadog acquired. Now running Datadog's AI Skunk Works, a deliberately small...

Can I download this The Chief AI Officer Show episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!