News

Claude Platform (May 6, 2026): Managed Agents Multiagent Sessions, Outcomes, and Webhooks in Public Beta

Anthropic added Managed Agents webhooks, moved Multiagent Sessions + Outcomes into public beta, and later added monthly Claude Platform API credits for Max and Team plans.

By Authority AI Tools Editorial Team•2026-10-30•3 min read
Last reviewed: 2026-10-30
AATET
Authority AI Tools Editorial Team

Editorial Team

The Authority AI Tools editorial team maintains this directory using vendor documentation, dated source checks, product changelogs, and clearly identified hands-on observations where available.

Anthropic shipped a Claude Platform update on May 6, 2026 that expands what you can automate around Claude Managed Agents. The biggest addition is webhooks, plus a set of beta features (including Multiagent Sessions and Outcomes) being consolidated under the managed-agents-2026-04-01 beta header.

TL;DR

  • Webhooks are now supported for Claude Managed Agents (session + vault lifecycle events).
  • Multiagent Sessions and Outcomes are now in public beta under managed-agents-2026-04-01.
  • Vault credential background refresh is now supported for mcp_oauth credentials.

What Actually Shipped

According to Anthropic's official Claude Platform release notes:

  • Multiagent Sessions + Outcomes public beta: both features are now listed as public beta features under the standard managed-agents-2026-04-01 beta header.
  • Managed Agents webhooks: you can subscribe to webhook event types that include session lifecycle and vault lifecycle events.
  • Vault credential background refresh: background refresh is supported for mcp_oauth vault credentials.
  • Console UX improvements: the release notes also mention new filtering/sorting for sessions (by status) and events (by type/creation time).

Why This Matters

If you're using Managed Agents in production, webhooks make it easier to:

  • Trigger internal workflows when agent sessions start/finish
  • Pipe agent run lifecycle signals into monitoring/alerting
  • Keep credential management more reliable with background refresh for mcp_oauth

October 19 follow-up: monthly API credits for Max and Team

Anthropic's current Help Center lists $100 per month for Max 5x and $200 for Max 20x. Team Standard seats receive $20 each and Premium seats $100 each, pooled into a single workspace balance capped at $500 per month. Credits are available to active Max and Team plans, including discounted Team plans, after a new subscriber has been on an eligible plan for seven days; Free, Pro, and Enterprise plans are not eligible. An owner must also have the required Console organization role and claim the credits on claude.ai in a web browser. (https://support.claude.com/en/articles/17154008-monthly-api-credits-for-max-and-team-plans)

The credits cover the Claude API, Console Playground, Managed Agents, and Claude Agent SDK. claude -p and Agent SDK runs are covered when they use an API key from the linked Console organization. They do not cover interactive Claude Code in the terminal, IDE, desktop, or web, extra Claude or Claude Code usage, or usage through Amazon Bedrock, Vertex AI, or Microsoft Foundry. Unused credits expire at the end of each billing cycle and do not roll over. (https://support.claude.com/en/articles/17154008-monthly-api-credits-for-max-and-team-plans)

Claude Code logo
Claude CodeSubscription

Anthropic's terminal-based AI coding agent with Claude Opus 4.7, /ultrareview, Routines, /ultraplan, and 80.9% SWE-bench

Source

Free Resource

2026 AI Coding Tools Comparison Chart

Side-by-side comparison of features, pricing, and capabilities for every major AI coding tool.

No spam, unsubscribe anytime.

Frequently Asked Questions

What changed in the Claude Platform release notes on May 6, 2026?
Anthropic added webhooks for Claude Managed Agents, moved Multiagent Sessions and Outcomes into public beta under the managed-agents-2026-04-01 header, and added vault credential background refresh for mcp_oauth credentials.
What can you use Claude Managed Agents webhooks for?
Anthropic says Managed Agents webhooks can send lifecycle events for sessions and vaults, letting you integrate agent runs into internal workflows and monitoring.