Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

Platform Engineering Podcast

Platform Engineering Podcast artwork

AI-Native Ops: Making AI Safe for Production with William Collins

Apr 1, 20261 hr 3 minAudio
  • Apple Podcasts
ShareXLinkedInFacebookWhatsAppEmail

What happens when your “coworker” can generate code and changes faster than your team can review them, and production still has to stay up? William Collins breaks down what AI-Native Ops looks like when you take reliability seriously: where reasoning should stop, where deterministic automation should begin, and how guardrails like compliance checks, version pinning, and controlled workflows keep AI from turning into outage fuel. Cory and William also dig into why context windows and tool sprawl matter in real systems, how protocols like MCP and agent-to-agent communication are shaping day-to-day automation, and why regulated environments can’t adopt new tech with hype-driven shortcuts. If you’re a platform engineer trying to balance speed with safety, this conversation offers a practical way to use AI for the work that drags teams down, without giving up operational discipline. Guest: William Collins, Director of Technical Evangelism at Itential, AWS community builder, and the co-host of the Cloud Gambit podcast William Collins is a strategic thinker and catalyst for innovation. Over his career, he has helped enterprises build large-scale networks, driven modernization through cloud adoption, and excels at optimizing complex environments through good design practices and automation. Today, William works as Director of Technical Evangelism for Itential, where he focuses on evangelizing the Itential Platform, fostering strong relationships with customers to fully realize their goals, engaging with community, and advocating for the successful future of network, security, and automation infrastructure. As a content creator, William hosts The Cloud Gambit Podcast with Eyvonne Sharp, a show that unravels the state of cloud computing, markets, strategy, and emerging trends with industry experts. He is also a LinkedIn Learning Instructor (Automation, Cloud, and Network Engineering Content), AWS Community Builder (Network & Content Delivery), and is a group organizer for the USNUA - Kentucky User Group (KYNUG). Prior to Itential, William worked as a Principal Cloud Architect and Director of Technical Evangelism for Alkira where he helped grow the company from lean beginnings to being ranked 25th Fastest-Growing Company in North America and 6th in the Bay Area on the 2024 Deloitte Technology Fast 500. He also held various senior technical roles across the enterprise space in Financial Services and Healthcare, most recently at Humana as Director of Cloud Architecture. Outside of tech, his time is spent with family, woodworking, ice hockey, and guitar. Opinions expressed are solely his own and do not express the views or opinions of his employer. William Collins, Blog William Collins, YouTube William Collins, X William Collins, Instagram William Collins, TikTok William Collins, GitHub Itential “The Cloud Gambit” podcast Links to interesting things from this episode: Ghostty “Harness design for long-running application development” by Anthropic

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Guests

  • William Collins Guest Inferred

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. Taking a Summer Break: What Would You Like To Hear This Fall?

    Jul 15, 20263 minAudio

    We're hitting pause for the summer on new episodes of the Platform Engineering Podcast, but don’t worry, we’ve got some great episodes in the feed to keep you entertained in the meantime. If you’ve got suggestions for...

    • Apple Podcasts

    Credit the people on this episode

  2. What Do Service Meshes Actually Solve? (William Morgan, Buoyant/Linkerd)

    Jun 24, 202656 minAudio

    Network calls fail in ways function calls never do - and once a monolith becomes microservices, reliability problems show up fast: retries amplify load, latency spikes cascade, and “what talks to what?” becomes hard to...

    • Apple Podcasts

    Credit the people on this episode

  3. Continuous Integration at Agentic Velocity with CircleCI’s Rob Zuber

    Jun 10, 202650 minAudio

    When code gets cheaper to produce, feedback becomes the limiting factor - CI, reviews, and the handoffs between tools can quietly slow everything down. Rob Zuber breaks down what platform engineers are seeing as teams...

    • Apple Podcasts

    Credit the people on this episode

  4. Durable Execution for Real‑World Failures with Temporal’s Cornelia Davis

    May 27, 202646 minAudio

    A lot of infrastructure and automation fails for ordinary reasons: rate limits, flaky networks, partial permissions, long-running jobs, and retries that vanish when the process restarts. Durable execution is a way to...

    • Apple Podcasts

    Credit the people on this episode

  5. You Need AI Sysadmins Can Trust, With Cribl's Nikhil Mungel

    May 13, 202655 minAudio

    What happens when a non-deterministic AI system is asked to touch production telemetry or generate changes for an SRE pipeline? The cost of being “close enough” can be lost data, downtime, or a security incident....

    • Apple Podcasts

    Credit the people on this episode