# AI Engineer Paris 2026 Main Stage: Google DeepMind, ElevenLabs, Hugging Face & Stripe | Day 2

Source: [AI Engineer](https://www.youtube.com/watch?v=g0vqT_wZtXA)  
Feed7 permalink: https://feed7.dev/p/ai-engineer-paris-2026-main-stage-google-deepmind-elevenlabs-hugging-fac-1n74jdk  
Published: 2026-09-24T16:16:54.000Z  
Trust: Source Linked (source_linked)

## Why Included

This conference recording surfaces three useful checks for agent builders: shorten integration paths, tune inference for the workload, and reject tests that merely restate implementation details.

## Source Summary

The excerpts report **24% month-over-month** growth in iOS launches after agentic coding tools appeared and under six weeks from sandbox to first charge. An inference team reports **5.5×** more tokens per minute per GPU and about **400 vs 130 tokens/s** per user after workload tuning.

## Practical Implication

Build agent-native integrations that avoid dashboard handoffs, but measure the path to a real outcome rather than code produced. Tune serving separately for interactive agents and batch processing, and make generated tests exercise behavior instead of constants, source order, or mocked-away failures.

## Agent-Ready Context

The excerpts report **24% month-over-month** growth in iOS launches after agentic coding tools appeared and under six weeks from sandbox to first charge. An inference team reports **5.5×** more tokens per minute per GPU and about **400 vs 130 tokens/s** per user after workload tuning.

Build agent-native integrations that avoid dashboard handoffs, but measure the path to a real outcome rather than code produced. Tune serving separately for interactive agents and batch processing, and make generated tests exercise behavior instead of constants, source order, or mocked-away failures.

This is a partial transcript spanning unrelated talks and sponsor presentations. The adoption and performance figures are presenter-reported, their methodologies are absent here, and the recording does not establish that the reported improvements generalize.

## Connected Context

Feed7 judgment across 875 accumulated Signals:

This shifts the coding-agent case from output volume to end-to-end outcomes: adoption speed matters only if work reaches a real charge or other completed result, and serving gains depend on workload-specific tuning. It also reinforces that generated tests are not automatically useful; they must exercise behavior and preserve real failure paths. The reported growth and throughput remain local claims without enough methodology to generalize.

- [ExecCritic: Learn to Test, Test to Improve for Coding Agents](https://feed7.dev/p/2609-09133v1-0zfcxb4) — ExecCritic provides benchmark evidence for the talk’s warning about weak generated tests: unqualified tests can reduce resolution, while separated and frozen qualified tests improve the repair loop.
- [Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition](https://feed7.dev/p/building-ambitious-software-jonathan-kelley-dioxus-labs-cognition-05p0hll) — Dioxus’s focus on mergeability and real-device validation reinforces the same outcome-based judgment: generated code volume is less meaningful than whether changes survive integration and behavioral verification.
- [How to Kill the Code Review — Ankit Jain, Aviator](https://feed7.dev/p/how-to-kill-the-code-review-ankit-jain-aviator-0rku6kj) — Its proposal to review retained intent and verification evidence supplies an organizational consequence of the talk’s behavioral-testing requirement when agent output outgrows line-by-line review.

## Context Map

- Layer: agent
- Domains: coding
- Topics: coding-agents, mcp, agent-reliability

## Uncertainty

- This is a partial transcript spanning unrelated talks and sponsor presentations. The adoption and performance figures are presenter-reported, their methodologies are absent here, and the recording does not establish that the reported improvements generalize.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.