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

Long-running AI agents often fail due to limitations in HTTP protocols. Ably's platform addresses these issues by enabling durable sessions for AI agents. This improvement helps maintain continuous AI workflows without interruptions.

ArchiveAI AgentsHigh-signal source

Signal trust

High-signal sourceSingle sourceEarly signal

PublishedWednesday, May 6, 2026 at 9:48 PMMay 6, 09:48 PM

FreshnessArchive

Story ID#1324

Back to feed Original report

Original article excerpt

Server-side extracted preview paragraphs from the original source.

Ably CEO Matthew O'Riordan discusses the shift to durable sessions for long-running AI agents and solving HTTP limitations in this interview with The New Stack.

The source page did not expose a stable readable article body, so only the AI summary is available for now.

Opening the briefing

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

Original article excerpt

Signal trust

Related stories

Opening the briefing

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

Original article excerpt

Signal trust

Related stories

Replit’s vibe coding platform just got a Visa-backed identity layer for AI agents — and it changes how agents spend money

Anthropic releases Opus 4.8 with new ‘dynamic workflow’ tool

How Endava builds an agentic organization with Codex

Sesame, the conversational AI startup from Oculus founders, launches its iOS app