Notable verbatim quotes

"We're building a runtime intelligence layer for coding agents. So it's basically a sensor that runs with your app in production and captures what coding agents need to reason over production." — Hud's product, Section 2

"Code still finds creative ways to [fail in] production. And we still do that, like, with the best tools and the best engineers… And the coding agents have no idea how that actually behaves." — The core gap, Section 2

"We kind of ignore the issue and then it degrades and then it becomes a crisis. And now we have to prioritize it… That is a leaky bucket. By definition." — Why performance backlogs persist, Section 3

"It's kind of like taking something from the grocery store and then going all the way to the cashier just to know how much it cost so that you understand if you want it or not." — The research-cost problem, Section 3

"Our thought was to automate the investigation part. It wasn't even about fixing it. It was just about knowing what can be done." — The central reframe, Section 4

"We don't know. No one knows what's the best. There are seasons." — On model/harness neutrality, Section 5

"You don't just ship them. They are like code. You ship them and you find out something you just want to change between that little thing so that it will be easier to work with." — Agentic workflows are code, Section 5

"It's about reducing friction and finding that path of least resistance [rather than building] something else and see if it works." — Why GitHub Actions, Section 5

"Things that sound right are not necessarily the ones that are going to move the needle." — Plausible-but-unverified offers, Section 7

"What we call lazy fix, which means, oh, there's an exception. Let's catch it. This is great, but it's not helpful at all." — Lazy fix anti-pattern, Section 7

"If something works 90% of the time, it's not an automation. It's [streamlining] humans." — The automation-confidence bar, Section 8

"Prod to code, which is basically a mapping of what's going on in production to the function level." — Defining prod-to-code, Section 8

"I'm going to touch this. What does it impact? And should I care about it? Is it going to touch my payments and my authorization or not?" — The inverse question prod-to-code unlocks, Section 8

"The coding agent might need something that I cannot express in words. And that's why tools are not enough." — Why layered architecture, Section 9

"If you open a pull request, it's kind of like opening your DataDog and Sentry with like 700 issues. That's all they say is like, well. I'm not going to be able to fix this, so I'm not even going to try." — Why auto-PRs failed, Section 10

"We actually need to convince the human that it's worth the attention instead of convincing the agent that it's worth the [tokens]." — The mindset shift, Section 10

"We are not looking for the best optimizations. We are looking for the highest impact, lowest risk changes." — Scoring criteria, Section 11

"Merging to production did not become, it's not free, it's just cheaper." — The honest framing of human-in-the-loop, Section 11

"It is better to do less, but the right things. And if… in any time I would suggest something that won't work, we lose trust in the process." — Fourth takeaway, Section 12

"We're like an espresso shop. We only have an espresso, but it's the best one in town." — Hud's positioning vs. DataDog/Sentry, Q&A