Notable Quotes — Skills Everywhere

All quotes are verbatim from transcript.md. Speaker attribution: all quotes are Groetzinger unless otherwise noted.

On context vs. model intelligence

• "you don't really need a smarter model today. The models are perfectly capable of doing what you need for business value… The problem is really that you need smarter context and smarter context engineering." — Section 2
• "why can't I just use sonar for everything? And I found out I can. And today, for the last couple months, I largely use the medium tier model. I'm GPT medium reasoning." — Section 3
• "I challenge my engineers to really try to use that medium tier as their baseline. Right. And only jump into the greater field when they need to." — Section 3

On harness portability of skills

• "all the harnesses, all the models are training on skills, they're honoring skills. And so if you can lean into that, your context can actually transfer between the harnesses." — Section 3

On evals

• "the real unlock for that is evals. Evals are extremely important and you need to make sure that you're actually spending engineering effort learning how to build evaluations for your context." — Section 3
• "if you do that correctly, you can actually use extremely low end models in your workflows become much more deterministic" — Section 3
• "Evals are the same in this world with agentic. They are the unit test for your agents." — Section 8
• "We treat it just like we would a shared library… You cannot break functionality for other people. How do you validate that? The evaluations need to cover it." — Section 13 (Q&A)

On who the skill is for

• "Stop doing that. The skill is not for you. The skill is for your agent." — Sections 6–7
• "where your human spends the time, that is your most precious resource is your humans validating your tests, the quality, what actually matters. That's the eval and then the initial KB. The stuff in the middle, let the agent do it for you." — Section 7
• "if you want a smaller model to do this workflow, let the small model build the skill for itself." — Section 7

On the KB-to-skill pipeline

• "when the article changes, we kind of pipeline that… a GitHub action triggering when we update a knowledge base article that goes into a pipeline with an LLM that reviews the changes, determines if it's a minor change, moderate change, major, and then makes the change for itself to update its skill. And then it runs an eval" — Section 7
• "Your humans either go far on the left or far on the right, but in between, you should not be wasting your time. Should not be caring about the text if your engineers are reviewing text diffs on a skill, you are wasting a lot of time." — Section 7
• "new topic means new eval" — Section 7

On skill-as-onboarding-vehicle

• "meeting's not going to work… everyone has a coding agent in these development teams… Why don't we make a skill and then I can just have everyone install the skill and the agent can build the models for them." — Section 8
• "by the end of the week, every agent team kind of had a data set done the same way, similar metrics" — Section 8

On JSONL and dataset edits

• "each example for each eval is an individual line. Your coding agent can make more precise edits on the data set because again, we're not hand curating data sets. We absolutely don't have time for that." — Section 8

On the README-to-Confluence sync

• "there's no drift. So what my agents are reading, what their manager they're reading is all the same content." — Section 9
• "Don't have an LLM update Confluence. Many can do that too, but it's kind of token heavy. Just have your agent right a deterministic script to sync that markdown into a pretty HTML file" — Section 9

On the cultural reflex

• "Go ask, do we have a skill that explains this so I can install it in my agent? That needs to become the default reaction." — Section 10
• "I don't want 15 engineers creating 15 skills for the same thing… That's just extremely wasteful engineering" — Section 10

On semantic versioning of skills

• "if I go look at a skill and it's version 1.0, I expect it to do exactly what it's supposed to do on the first try with almost no friction. Right? And if it doesn't do that, you've lost my trust." — Section 11

Closing thesis

• "our agent architectures, they change every day… But your context is your durable investment… build your pipelines today because everything else is definitely going to change on you anyway." — Section 12