AI Deployment Diaries

AI Deployment Diaries brings you stories from the front lines of enterprise AI deployment. Host Parth Mehta sits down with the operators and practitioners deploying AI inside real companies on what works and what doesn't.

Travis Frisinger built a software factory that builds itself. In this episode he takes it apart: what a software factory actually is (intent, an operator, a spec, standards, a harness), how he got it to bootstrap and woke up to 30 merged pull requests, and what changes when the agent starts reading its own transcripts to learn. We get into why engineers have to stop handing their minds fully to the agent, the ego hit of watching a machine decide your technical debt was never worth cleaning up, and what custom software looks like in 2027 when a client can get an app 3D printed instead of paying for a six-figure build.

Travis Frisinger is Head of Agentic AI at 8th Light, where he leads the Agentic AI Studio. He is the creator of HydraFlow, an open-source software factory, and writes about software manufacturing at aibuddy.software.

Read Travis's essay on the ideas in this episode, "Software Factories Need Building Codes":
https://aibuddy.software/software-factories-need-building-codes/

HydraFlow on GitHub: https://github.com/T-rav/hydraflow

How to get in touch with Travis:

LinkedIn: https://www.linkedin.com/in/travis-frisinger/

How to get in touch with Parth:

LinkedIn: https://www.linkedin.com/in/parthcmehta/

X: https://x.com/mr_parthmehta

#ai #aiagents #softwarefactory #enterpriseai

AI Deployment Diaries brings you stories from the front lines of enterprise AI deployment. Host Parth Mehta sits down with the operators and practitioners deploying AI inside real companies on what works and what doesn't.

We talk about the gap between a flashy demo and a product people rely on day to day, why an AI coding company needs a fraud team at all, how to actually get real work out of an agent (pick the right tool, give it a real job, decide where you sit in the loop), what evals look like in practice including one she built for mental health, and what changes when we stop putting AI on top of our old primitives and start building AI-native ones.

Nikita Sirohi has spent a decade shipping AI in production, from self-driving cars to large-scale storage to AI coding agents. Most recently she was an engineering leader at Augment Code, where she launched the self-serve product and stood up the growth, billing and fraud teams from scratch. She has now left to start her own company.

How to get in touch with Nikita:

LinkedIn: https://www.linkedin.com/in/nikita-sirohi-8690b979/
X: https://x.com/NikitaS341308

How to get in touch with Parth:

LinkedIn: https://www.linkedin.com/in/parthcmehta/
X: https://x.com/mr_parthmehta

#ai #aiagents #evals #enterpriseai

Introductory episode of AI Deployment Diaries. Real stories from the front lines of enterprise AI deployment. Host Parth Mehta sits down with the oprators and practitioners deploying AI inside real companies.

Most AI deployment advice comes from people who have never left Silicon Valley. Doug Qian sold his startup, walked into companies with no software engineers, and found operators still asking the questions the Valley asked in 2023. Enterprise AI deployment on the ground: dollar-valuing 45 hackathon ideas down to 1, building skills before agents, and turning the employee most threatened by AI into its biggest champion.

Doug Qian is the Founder & Managing Partner @ Strata (stratahq.ai), where he embeds inside mid-market companies to deploy AI end to end: strategy, custom MCP connectors, skills, agents, and training.

How to get in touch with Doug:

Email: [email protected]

LinkedIn: https://www.linkedin.com/in/douglas-qian/

How to get in touch with Parth:

Email:

LinkedIn: https://www.linkedin.com/in/parthcmehta/

X: https://x.com/mr_parthmehta