---
title: "Agents Without Code: How Skills, YAML, and Filesystems Replaced Python"
category: "talks"
date: "2026-07-01"
time: "3:45pm-4:05pm"
track: "Harness Engineering"
room: "Main Stage"
speakers: ["Philipp Schmid"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Harness Engineering"
scheduleRoom: "Main Stage"
scheduleLabels: ["Harness Engineering", "Main Stage", "session", "confirmed"]
---
# Agents Without Code: How Skills, YAML, and Filesystems Replaced Python

## Conference Context
- Date/time: 2026-07-01 · 3:45pm-4:05pm
- Track/room: Harness Engineering · Main Stage
- Speaker(s): Philipp Schmid
- Session type/status: session · confirmed

- Track: Harness Engineering
- Room: Main Stage
- Session type: session
- Status: confirmed

## Session Description
Six months ago, building an agent meant writing a Python class with a `while` loop, tool definitions in dicts, manual state management or writing custom python functions. Today, you define an agent in a YAML file, drop a `SKILL.md` into a folder, and deploy. This talk traces the arc from "Agent in Python" to "Agent as filesystem". You'll learn the same agent built three ways: the hard way (Jan 2025), the simple way (Oct 2025), and the zero-code way (today).

## Media Evidence
[Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind](https://www.youtube.com/watch?v=cVzf49yg0D8) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

- Source video: `youtube-cVzf49yg0D8`
- Slide deck: [[youtube-cVzf49yg0D8-dense-slides|Dense Slides: Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind]] — 14 visible slide image(s); 14 HTML recreation(s).
![[assets/dense-slides/cVzf49yg0D8/slide-001.jpg]]
![[assets/dense-slides/cVzf49yg0D8/slide-002.jpg]]
![[assets/dense-slides/cVzf49yg0D8/slide-003.jpg]]
- Additional slide evidence: [[youtube-cVzf49yg0D8-slides|Slides: Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind]], [[youtube-cVzf49yg0D8-reconstructed-slides|Reconstructed Slides: Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind]]
- Slide-derived themes for `youtube-cVzf49yg0D8`: rule, gemini, interactions, zero, working, agentic, application, minutes.

## 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-cVzf49yg0D8` — 5 slide-derived text signals
- Slide-derived themes for `youtube-cVzf49yg0D8`: rule, gemini, interactions, zero, working, agentic, application, minutes.
- Evidence links for `youtube-cVzf49yg0D8`: [[youtube-cVzf49yg0D8]], [[youtube-cVzf49yg0D8-slides]], [[youtube-cVzf49yg0D8-dense-slides]], [[youtube-cVzf49yg0D8-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
- [[philipp-schmid]]

## Supporting Slides
- [[youtube-cVzf49yg0D8-slides]] — extracted from the related public AI Engineer video.

## Slide Evidence
- Slide-only cropped deck: [[youtube-cVzf49yg0D8-dense-slides]] (14 viable slide images).
- Related slide/OCR pages:
- [[youtube-cVzf49yg0D8-dense-slides]]
- [[youtube-cVzf49yg0D8-reconstructed-slides]]
- [[youtube-cVzf49yg0D8-slides]]
- Slide-derived terms: `tool`, `playground`, `search`, `google`, `function`, `result`, `text`, `output`, `live`, `voice`, `gemini`, `interactions`, `studio`, `json`, `code`, `history`, `documentation`, `real-time`

## Synthesis
### Synthesized Breakdown
# Agents Without Code: How Skills, YAML, and Filesystems Replaced Python ## Conference Context - Date/time: 2026-07-01 · 3:45pm-4:05pm - Track/room: Harness Engineering · Main Stage - Speaker(s): Philipp Schmid - Session type/status: session · confirmed - Track: Harness Engineering - Room: Main Stage - Session type: session - Status: confirmed ## Session Description Six months ago, building an agent meant writing a Python class with a `while` loop, tool definitions in dicts, manual state management or writing custom python functions. Today, you define an agent in a YAML file, drop a `SKILL.md` into a folder, and deploy. This talk traces the arc from "Agent in Python" to "Agent as filesystem". You'll learn the same agent built three ways: the hard way (Jan 2025), the simple way (Oct 2025), and the zero-code way (today).

### Speaker And Company Context
- [[philipp-schmid|Philipp Schmid]] — Staff Engineer at [[google-deepmind|Google DeepMind]].

### Topics Covered
- [[agentic-search]]
- [[coding-agents]]

### Derived Links And Source Material
- [[youtube-cVzf49yg0D8]] — related YouTube source page.
- [[youtube-cVzf49yg0D8-slides]] — slide evidence.
- [[youtube-cVzf49yg0D8-reconstructed-slides]] — slide evidence.
- [[youtube-cVzf49yg0D8-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.