---
schema_version: "newruntime-agent-readable-v0.1"
type: "raw_signal"
id: "tg-2678"
slug: "uber-platform-for-thousands-of-agents"
title: "Uber built a platform layer for thousands of agents"
description: "Uber's internal approach focuses on common protocols, evaluation, identity, observability, and policy instead of one mandated agent framework."
observed_at: "2026-07-13"
why_it_matters: "At enterprise scale, governance and shared runtime services become more durable than the framework used to implement any one agent."
novelty: "structural"
verification_level: "source-linked"
signal_type: "field-report"
evidence_kind: "mixed"
status: "published"
telegram_message_id: 2678
telegram_url: "https://t.me/qwgai/2678"
topics: ["enterprise-agents","agent-platform","observability","mcp"]
entities: ["Uber","Agent Protocol"]
related_patterns: []
source_urls: ["https://youtube.com/watch?v=n9j4SaF37V0","https://github.com/langchain-ai/agent-protocol"]
import_batch: "telegram-2026-07-17-v1"
routes: {"html":"https://newruntime.com/signals/uber-platform-for-thousands-of-agents/","markdown":"https://newruntime.com/signals/uber-platform-for-thousands-of-agents.md","json":"https://newruntime.com/signals/uber-platform-for-thousands-of-agents.json"}
source_format: "telegram-export-normalized-json"
---

# Uber built a platform layer for thousands of agents

## Observation

Uber's internal approach focuses on common protocols, evaluation, identity, observability, and policy instead of one mandated agent framework.

## Why it matters

At enterprise scale, governance and shared runtime services become more durable than the framework used to implement any one agent.

## Provenance

Normalized from QWG AI Telegram message 2678. The original Russian-language record remains available at https://t.me/qwgai/2678.