---
title: "Mousepower: agents that can’t be measured, can’t be managed."
category: "talks"
date: "2026-06-30"
time: "12:05pm-12:25pm"
track: "Design Engineering"
room: "Track 6"
speakers: ["Maximillian Piras"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Design Engineering"
scheduleRoom: "Track 6"
scheduleLabels: ["Design Engineering", "Track 6", "session", "confirmed"]
---
# Mousepower: agents that can’t be measured, can’t be managed.

## Conference Context
- Date/time: 2026-06-30 · 12:05pm-12:25pm
- Track/room: Design Engineering · Track 6
- Speaker(s): Maximillian Piras
- Session type/status: session · confirmed

- Track: Design Engineering
- Room: Track 6
- Session type: session
- Status: confirmed

## Session Description
Agents have a measurement problem, which makes them impossible to efficiently manage. You’ve likely heard many say execution is now cheap, but judgement is the new bottleneck. This is because our evaluation frameworks weren’t designed for systems that tirelessly output in parallel. The canary in the coal mine is code generation becoming largely solved at the expense of breaking code review. As agents reverberate across all knowledge work, the same fracture will spread to artifacts, actions, & decisions. Yet without a scalable quality measure, we can’t ascend to a higher level of abstraction because we won’t trust the foundation below. So how do we design measurements that are efficient, intuitive, & trustworthy? Past paradigm shifts offer inspiration, such as James Watt not just building a better engine but also inventing horsepower to map it onto existing mental models. We need an equivalent quantification to communicate the “mousepower” of agents. Information theory gives us the starting point: concepts like entropy, ergodic processes, and Hamiltonian problems point us toward the most tractable trajectories — easier to verify than they are to solve.

## Media Evidence
[The Bitter Layout or: How I Learned to Love the Model Picker — Maximillian Piras, Yutori](https://www.youtube.com/watch?v=BZtD0yYAgCQ) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

- Source video: `youtube-BZtD0yYAgCQ`
- Slide deck: [[youtube-BZtD0yYAgCQ-dense-slides|Dense Slides: The Bitter Layout or: How I Learned to Love the Model Picker — Maximillian Piras, Yutori]] — 2 visible slide image(s); 2 HTML recreation(s).
![[assets/dense-slides/BZtD0yYAgCQ/slide-001.jpg]]
![[assets/dense-slides/BZtD0yYAgCQ/slide-002.jpg]]
- Additional slide evidence: [[youtube-BZtD0yYAgCQ-slides|Slides: The Bitter Layout or: How I Learned to Love the Model Picker — Maximillian Piras, Yutori]], [[youtube-BZtD0yYAgCQ-reconstructed-slides|Reconstructed Slides: The Bitter Layout or: How I Learned to Love the Model Picker — Maximillian Piras, Yutori]]
- Slide-derived themes for `youtube-BZtD0yYAgCQ`: ship, future, programming, bret, victor, bitter, layout.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
- `youtube-BZtD0yYAgCQ` — 5 slide-derived text signals
- Slide-derived themes for `youtube-BZtD0yYAgCQ`: ship, future, programming, bret, victor, bitter, layout.
- Evidence links for `youtube-BZtD0yYAgCQ`: [[youtube-BZtD0yYAgCQ]], [[youtube-BZtD0yYAgCQ-slides]], [[youtube-BZtD0yYAgCQ-dense-slides]], [[youtube-BZtD0yYAgCQ-reconstructed-slides]]

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

## People
- [[maximillian-piras]]

## Supporting Slides
- [[youtube-BZtD0yYAgCQ-slides]] — extracted from the related public AI Engineer video.

## Slide Evidence
- Slide-only cropped deck: [[youtube-BZtD0yYAgCQ-dense-slides]] (2 viable slide images).
- Related slide/OCR pages:
- [[youtube-BZtD0yYAgCQ-dense-slides]]
- [[youtube-BZtD0yYAgCQ-reconstructed-slides]]
- [[youtube-BZtD0yYAgCQ-slides]]
- Slide-derived terms: `than`, `awss`, `graphite`, `windsurf`, `mongobb`, `mdaily`, `augment`, `code`, `workos`, `bitter`, `layout`, `maximilliannyc`, `ihelp`, `ship`, `doyou`, `want`, `tobuild`, `whatwill`

## Synthesis
### Synthesized Breakdown
# Mousepower: agents that can’t be measured, can’t be managed. ## Conference Context - Date/time: 2026-06-30 · 12:05pm-12:25pm - Track/room: Design Engineering · Track 6 - Speaker(s): Maximillian Piras - Session type/status: session · confirmed - Track: Design Engineering - Room: Track 6 - Session type: session - Status: confirmed ## Session Description Agents have a measurement problem, which makes them impossible to efficiently manage. You’ve likely heard many say execution is now cheap, but judgement is the new bottleneck. This is because our evaluation frameworks weren’t designed for systems that tirelessly output in parallel.

### Speaker And Company Context
- [[maximillian-piras|Maximillian Piras]] — Founding Designer at [[yutori|Yutori]].

### Topics Covered
- [[agent-security]]
- [[ai-sandboxes]]
- [[coding-agents]]

### Derived Links And Source Material
- [[youtube-BZtD0yYAgCQ]] — related YouTube source page.
- [[youtube-BZtD0yYAgCQ-slides]] — slide evidence.
- [[youtube-BZtD0yYAgCQ-reconstructed-slides]] — slide evidence.
- [[youtube-BZtD0yYAgCQ-dense-slides]] — slide evidence.

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.