Vibe Coding Is Dangerous, Agentic Engineering Isn't ft. Wes McKinneyNew: The AI Analytics Eval Field GuideGet the Free Playbook

START FREE

GO BACK TO BLOG

Vibe Coding Is Dangerous, Agentic Engineering Isn't ft. Wes McKinney<br>2026/06/05 - 15 min read<br>BYSimon Späti

GO BACK TO BLOG

Vibe Coding Is Dangerous, Agentic Engineering Isn't ft. Wes McKinney<br>2026/06/05 - 15 min read<br>BYSimon Späti

This series interviews real practitioners to extract the patterns behind how they actually use AI in their data work today. This is the third interview in 'How to use AI with DE, and this time we have none other than Wes McKinney.

Creator of Pandas, probably the most widely used data analysis library for Python, Wes has shaped the era of data and is co-creator of Apache Arrow. He also created Ibis to address these issues with a different approach to Python dataframe libraries, by decoupling the dataframe API from the backend implementation.

The article is structured in four parts: (1) how to trust the outcome, (2) knowing what not to build, factoring in cost-per-token among others, (3) accountability of agents and the code they generate, and (4) philosophizing about the future of agentic engineering.

Introducing the Guest: #3 Wes McKinney<br>Besides creating the most popular dataframe libraries used by most data people, Wes McKinney now focuses full time on agentic engineering with his newly founded company Kenn Software, which focuses on the promise of building a new stack of development and knowledge systems for the agentic era. He's also doing AI and Python at Posit, where they work on a data science IDE. He's a part-time investor in various startups.<br>Wes has been running Claude Code, Codex, and Gemini CLI for months. Thousands of sessions, hundreds of thousands of messages. He has released multiple tools that help the agentic work (more on this later), and he is at the forefront of what's going on with his recent blog posts about "Why he uses programming languages built for agents, not humans" and Mythical Agent Month, with his recent insights into how to work with agents. Find all his takes at Wes McKinney.com.<br>I had the pleasure of asking Wes more about these topics, and we'll go into more details, plus many other things. Let's get started.

How to Trust the Outcome?<br>We started the interview with a critical question that stands above all others in the current AI landscape, and I asked him: "Can we trust the outcome? ". What if we need something important, other than a hobby project? What if the data must be correct (hospitals, banks)?<br>Similar to what Mark Freeman told us in our last interview about using spec-driven development with spec-kit, Wes uses a similar approach, but with an agentic skill framework called superpowers (currently 216k stars on GitHub). Compared to spec-kit, it specs out the requirements differently by (A) guiding you through the conversation , asking you the right questions to get to what you want to build, and (B) once you fire it off, it spawns a sub-agent that keeps the implementing agent on track. Wes said, "Superpowers looks for drift ", and course-corrects if the implementing agents drift off to non-relevant, or not even specified, tasks.<br>Wes spends a lot of time in this specification phase, sometimes hours, very detail-oriented and engaged. Even before he starts speccing, he has subconsciously worked over the topic and idea for a long while. He will not start implementing something when he doesn't know super clearly how it fits together. The insights, the architecture, come from him. But the interview style by superpowers helps him clarify his thinking .<br>He doesn't only give his feedback to the questions, but sometimes also fires up multiple agents and integrates their feedback. Codex models especially seem to work well for design questions.<br>He puts a lot of importance on the spec being:

Spec conformant : Meaning the agents act in accordance with your specific set of rules, standards, or specifications.

Code correctness and quality : This is where Wes uses e.g. Roborev, his own created AI-reviewer.

Correctness is crucial, which led to creating Roborev. Wes developed many tools that help him work agentically, and we'll hear about many more later. Roborev, for example, is a code reviewer that can be initialized with a hook on a git repository, and from that moment on, every commit will be auto-reviewed by Codex (the default, but you can choose others too).<br>I use Roborev myself, and this is what the interactive TUI looks like - showing the most recently fired hooks with their running status, but most importantly, whether the review passed (P) or failed (F):<br>If it failed, you can open the review and see detailed findings categorized into severity low, medium and high:<br>The convenient workflow is that you copy the review with y and feed it back to your running agent to let it fix things directly. The current agent that created the change works best, as it already has all the context,...