OpenAIAnthropicGooglexAIPerplexity
← Back to all updatesPublished ·Anthropic• Minor
Anthropic put Multi-agent sessions and Outcomes in public beta for Claude Managed Agents.
The read
Managed Agents now expose coordination, outcome definition, credential refresh, and webhooks as platform surfaces.
The frame
For builders using Managed Agents, sessions, vault credentials, and lifecycle events now sit behind documented platform hooks.
Primary source
Anthropic →Keep reading
See what Nova3 builds →Related updates
- Jun 12, 2026Anthropic publicly documented stop_details on refusal responses, with category and explanation fields for routing.
- Jun 12, 2026Claude Opus 4.8 defaults the effort parameter to high across all surfaces.
- Jun 12, 2026Claude Opus 4.8 lowers prompt caching’s minimum cacheable prompt length to 1,024 tokens versus Opus 4.7.
This is the world we build in. It moves this fast. We move with it.
Bring us your project →