DiscoverAlexa's Input (AI)
Alexa's Input (AI)
Claim Ownership

Alexa's Input (AI)

Author: Alexa Griffith

Subscribed: 7Played: 182
Share

Description

Alexa’s Input is a podcast about how technology actually moves forward. Hosted by Alexa Griffith, it features conversations with engineers, founders, CEOs, and leaders shaping today’s tech landscape. Each episode digs into the decisions behind the systems — what’s being built, what’s being questioned, and why it matters now.

Opinions are my own

Linktree: https://linktr.ee/alexagriffith
YouTube: https://www.youtube.com/@alexasinput
Podcast Website: https://alexasinputai.com/
Website: https://alexagriffith.com/
LinkedIn: https://www.linkedin.com/in/alexa-griffith/
X: @alexa_griffith_
70 Episodes
Reverse
A packed event tells you who showed up. But what did it actually do for the brand, and who should be invited next time?In this episode of Alexa’s Input (AI), I sit down with David Shedrick and Jason Allen, co-founders of PILOT, to talk about building event software and putting a number on influence.We get into the customer feedback that changed their business, measuring influence beyond follower count, privacy, and the work between an AI demo and a product people can use.PILOT brings guest lists, invitations, and check-in together with social intelligence. David and Jason explain how they connect attendance with public social activity and press coverage to help brands understand who is in the room and estimate the attention an event generates.From the episode:- Moving from nightlife into fashion, hospitality, and other experiences- How customer conversations changed the product they built- Engagement, reach, and audience authenticity beyond follower count- Connecting event attendance with estimates of earned-media value- Privacy and influential people who don’t have large online audiences- How people might change their behavior when they know they’re being scored- Building with AI, testing demos with customers, and getting a product ready for use- Founder risk, persistence, and learning when to change directionListen to this episode to learn how much a score can tell you about a person, and where you still need human judgment.---GENERAL PODCAST LINKSWatch: https://www.youtube.com/@alexasinputRead: https://alexasinput.substack.com/Listen: https://open.spotify.com/show/1tnV8Qk6SEw1Dr9Tqikr0HMore: https://linktr.ee/alexagriffith---LEARN MORE ABOUT THE HOSTWebsite: https://alexagriffith.com/LinkedIn: https://www.linkedin.com/in/alexa-griffith/---FIND OUT MORE ABOUT THE GUESTSPILOT: https://pilot.life/David Shedrick and Jason Allen: https://pilot.life/pilot/about---RESOURCESPILOT product overview: https://pilot.life/pilot/homepage
AI agents bring new demands to the infrastructure connecting them to models, tools, and data. Each agent can have its own permissions and state, and spend much of its time asleep before waking up to make another request. Supporting that behavior at scale changes how the network routes traffic, loads policies, and manages resources.In this episode of Alexa’s Input (AI), I sit down with Yan Avlasov, Staff Software Engineer at Google and a senior maintainer of Envoy, to talk about building the networking stack for agents.We get into why Google is building on Envoy, what changes between serving inference and supporting agents, and why enforcing policies for individual agents requires a more dynamic control plane. Yan also shares what he’s seeing from AI-powered security scanning, including how models combine subtle bugs into serious vulnerabilities and why fixing them can mean changing behavior that production systems have relied on for years.From the episode:- Model selection, cost controls, and fallback across providers- Loading policies dynamically as agent traffic changes- Managing personalized state and agents that suspend and resume- Where Model Context Protocol (MCP) fits alongside the protocols agents already use- Semantic routing and choosing models based on what a request needs- Security findings involving policy enforcement, path normalization, and JSON parsing- The engineering work and cost of making security scanning continuousChapters00:00 Introduction01:12 Welcome, Yan02:30 How AI is changing Google07:56 Yan’s networking background10:00 New networking layers for agents13:11 AI gateways, cost controls, and fallback16:38 Why Google builds on Envoy22:21 Per-agent policies and a dynamic control plane26:56 Inference versus stateful agents31:58 Project Substrate: running agents at scale33:31 MCP and the other protocols agents use37:32 Semantic routing and model costs40:40 AI security scanning and the work of fixing bugs43:55 Policy timing, path normalization, and JSON47:11 Making security scanning continuous50:40 What’s next for agentic networking53:32 ClosingRead the episode article on SubstackWatch on YouTube
In this episode of Alexa's Input (AI), I sit down with Alex Zenla, founder and CTO of Edera.Alex grew up in a small town in Alabama, found a computer young, and started building. Her story is unlike many in tech. She taught herself to program and got a job in tech at 14 years old. Since then, she's been actively building and involved in open source. She's currently the founder and CTO of Edera, a company whose product integrates security into the lowest layers of the platform without sacrificing performance or velocity.In this episode, we get into where that path started, what it costs to be different in founder and venture rooms, and what breaks when infrastructure still ships with security off by default.From the episode:Growing up in small-town Alabama without a path into techSouthern niceness as theory versus practiceFull-time work at fourteen and presenting to executives as a teenagerBeing one of very few trans founders in venture rooms, and the tension between visibility and being treated as a tokenElevator pitches that change with the audienceDetection and response after a problem has already occurredCommon Vulnerabilities and Exposures becoming untenable when tools like Mythos surface hundreds of findings per project per dayKubernetes and vendors selling yet another layer while the foundations underneath are misalignedSecure defaults as the path of least resistance for teams that just need a cluster that worksAlex's mission is to make secure computing the default. Today you work hard to get a secure environment, and she's building Edera to invert that. What stays with you is how personal that work is for her. The path from a small Alabama town into those rooms is not separate from the product. It's why the default being broken bothers her enough to build a company around fixing it.GENERAL PODCAST LINKSWatch: https://www.youtube.com/@alexasinputRead: https://alexasinput.substack.com/Listen: https://creators.spotify.com/pod/profile/alexagriffith/More: https://linktr.ee/alexagriffithLEARN MORE ABOUT THE HOSTWebsite: https://alexagriffith.com/LinkedIn: https://www.linkedin.com/in/alexa-griffith/FIND OUT MORE ABOUT THE GUESTLinkedIn: https://www.linkedin.com/in/azenla/Bluesky: https://bsky.app/profile/alex.zenla.ioEdera: https://edera.dev/GitHub: https://github.com/edera-devRESOURCESEdera docs: https://docs.edera.dev/
AI agents have created more possibilities for engineers than ever before. But what does daily life actually look like for the builders who've gone all in?In my very first panel episode, I sit down with Adam Anzuoni from Cursor, Taylor Dolezal from Dosu, and Peter Bell from Gather.dev. Three builders running agents every day for real work, not demos. Peter runs nine API plans across three Mac Minis, with built-in adversarial review. Adam manages cloud agents from his phone. Taylor is building the context infrastructure that makes agent knowledge portable across teams.We get into deterministic pipelines, skill systems that become their own technical debt, and what all three kept coming back to: attention is now the bottleneck. When agents can do everything, deciding what deserves your focus is the actual hard problem.Three setups. One shared constraint. A conversation worth hearing.Topics discussed:Attention as the real bottleneck when agents can do everythingDeterministic pipelines vs. agentic orchestration — when to use scripts and when to use agentsPeter's system: nine API plans, three Mac Minis, adversarial review, self-improving contextAdam on Cursor cloud agents and managing builds from his phoneTaylor on context distribution — making accumulated knowledge available to ephemeral agentsThe skill maintenance problem and why agent systems become their own technical debtThe ADHD-like productivity loop that agent-driven work createsPlans matter more than prompts — all three panelists converged on thisIntermediate artifacts as the key to quality outputProduct mindset as the engineer's next high-value skillSandboxes, governance, and why "approve, approve, approve" puts your hard drive at riskGeneral podcast linksWatch: https://www.youtube.com/@alexasinputRead: https://alexasinput.substack.com/Listen: https://creators.spotify.com/pod/profile/alexagriffith/More: https://linktr.ee/alexagriffithLearn more about the hostWebsite: https://alexagriffith.com/LinkedIn: https://www.linkedin.com/in/alexa-griffith/X: https://x.com/alexa_griffith_Find out more about the guestsAdam AnzuoniLinkedIn: https://www.linkedin.com/in/adamanz/Website: https://www.adamanzuoni.com/Cursor: https://www.cursor.com/Taylor DolezalLinkedIn: https://www.linkedin.com/in/onlydole/Website: https://onlydole.dev/Dosu: https://dosu.dev/Peter BellLinkedIn: https://www.linkedin.com/in/peterfbell/Gather.dev: https://gather.dev/O'Reilly Book: Scaling AI Adoption in EngineeringResources mentioned in this episodeCursor: https://www.cursor.com/Dosu: https://dosu.dev/Gather.dev: https://gather.dev/Anthropic Claude: https://www.anthropic.com/The Phoenix Project (book reference by Taylor)Kelsey Hightower productivity survey (referenced by Taylor)
Most engineers think reliability means avoiding outages. Vlad Leyberov learned the opposite lesson: sometimes you have to intentionally cause a 100% outage to fix the system faster.Vlad is a Site Reliability Engineer (SRE) at Google, running systems that handle billions of requests per second. Before Google, he kept critical infrastructure running at Meta (billions of events a day) and Amazon (millions of Alexa devices).In this conversation, we dig into cascading failures, incident responses, why consistency beats speed, how AI changes reliability engineering, and the philosophy behind running systems where downtime doesn't feel like an option.Topics Discussed:How cascading failures propagate unpredictably in distributed systems (like nature, not machines)Incident responses: virtual panic rooms, on-call, paging procedures, and how to narrow down failure pointsThe Alexa incident: why dropping an entire DynamoDB table was the right callCritical User Journeys (CUJ): measuring end-to-end customer experience vs individual SLOsCareer journey from the USSR to maritime academy to business degree in Australia to SRE at Amazon, Meta, and GoogleWhy consistency in API response times beats raw speedHow AI makes it dangerously easy to create complex systems with poorly understood interactionsScience fiction, the Borg as a distributed system, and the Three Body Problem trilogyHot takes on reliability: all software development is maintenance, overrated 9s, underrated global failure modesGeneral Podcast LinksWatch: https://www.youtube.com/@alexasinput Read: https://alexasinput.substack.com/ Listen: https://creators.spotify.com/pod/profile/alexagriffith/ More: https://linktr.ee/alexagriffithLearn more about the hostWebsite: https://alexagriffith.com/ LinkedIn: https://www.linkedin.com/in/alexa-griffith/Find out more about Vlad LeyberovLinkedIn: https://www.linkedin.com/in/vladleyberov/ Google SRE NYC Tech TalksResourcesGoogle SRE Resources:Google SRE Book: https://sre.google/books/Google Cloud Platform: https://cloud.google.com/Google Cloud Build: https://cloud.google.com/build (service discussed in outage story)Google Cloud Pub/Sub: https://cloud.google.com/pubsub (Vlad's previous role, billions of requests/second)Sci-Fi Books Mentioned:Three Body Problem trilogy by Liu Cixin (Vlad's current favorite)Foundation series by Isaac AsimovLeft Hand of Darkness by Ursula K. Le GuinSnow Crash by Neal StephensonInternal Google Systems Referenced:Borg: Google's internal cluster management system (Kubernetes predecessor), named after Star Trek BorgDynamoDB: AWS distributed key-value store (used in Alexa poison pill incident)Intro Music:PR1BVOV7R4F1ASZC
loading
Comments