Episode

Why long-running AI agents break on HTTP and how Ably is fixing it

Podcast: The New Stack Podcast
Published: May 6, 2026
Duration seconds: 1891
Processing state: not_requested
Canonical source: https://thenewstack.simplecast.com/episodes/why-long-running-ai-agents-break-on-http-and-how-ably-is-fixing-it-5oT4krRb
Audio: https://cdn.simplecast.com/media/audio/transcoded/317e9dbc-9a52-4da7-9725-c4578874b757/5672b58f-7201-4e0e-b0af-da702259d97f/episodes/audio/group/b5b5f6b2-10f7-4a45-aed8-3305011d403e/group-item/535a09ca-3d93-450d-892d-31b895e1e9f2/128_default_tc.mp3?aid=rss_feed&feed=IgzWks06
JSON: /v1/public/podcasts/the-new-stack-podcast-1092634/episodes/why-long-running-ai-agents-break-on-http-and-how-ably-is-fixing-it
Markdown: /podcast/the-new-stack-podcast-1092634/why-long-running-ai-agents-break-on-http-and-how-ably-is-fixing-it.md

Actions

POST https://stenobird.com/v1/public/podcasts/the-new-stack-podcast-1092634/episodes/why-long-running-ai-agents-break-on-http-and-how-ably-is-fixing-it/transcription-requests
Idempotently request low-priority transcript generation for this episode.
GET https://stenobird.com/podcast/the-new-stack-podcast-1092634/why-long-running-ai-agents-break-on-http-and-how-ably-is-fixing-it.md
Read the agent-friendly Markdown representation of this episode resource.

Summary

In this episode ofThe New Stack Makers, Matthew O’Riordan, CEO of Ably, explains how infrastructure originally built for human collaboration is now well-suited for long-running AI agents. While Ably initially resisted positioning itself as an AI company, the rise of agents that reason, call tools, and operate over extended periods revealed a natural fit for its real-time communication platform.