{"schema":"postcutoff/event@1","as_of":"2026-10-23T13:24:00+02:00","url":"https://postcutoff.com/e/2026-10-22-claude-apps-auto-mode-default/","md":"https://postcutoff.com/e/2026-10-22-claude-apps-auto-mode-default/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-22-claude-apps-auto-mode-default","date":"2026-10-22","date_precision":"day","short_title":"Claude apps switch to auto mode by default","deck":null,"takeaway":"The same evening Anthropic and Google made \"Claude Models on Google Cloud (Anthropic managed)\" generally available.","category":"product","category_label":"Products","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Claude on X: auto mode by default in Claude apps (Oct 22, 2026)","url":"https://x.com/claudeai/status/2113360845409583307","type":"official","group":"primary","domain":"x.com"},{"n":2,"title":"Claude on X: Claude Models on Google Cloud (Anthropic managed) generally available","url":"https://x.com/claudeai/status/2113380122468454765","type":"official","group":"primary","domain":"x.com"},{"n":3,"title":"Google Cloud: Expanding Claude availability and deployment choice on Google Cloud","url":"https://cloud.google.com/blog/products/ai-machine-learning/expanding-claude-availability-on-google-cloud","type":"official","group":"primary","domain":"cloud.google.com"}],"official":3,"filed":"2026-10-23","updated":"2026-10-23","orgs":["Anthropic","Google"],"title":"Anthropic: Claude web, desktop and mobile apps will run in auto mode by default on Pro, Max and Team plans; Anthropic-managed Claude on Google Cloud goes GA","summary":"On Oct 22, 2026 Anthropic announced that, starting the following week, sessions in the Claude web, desktop and mobile apps will run in auto mode by default on Pro, Max and Team plans: instead of asking users to approve each step, an automated check blocks risky actions, and users can switch back to manual. Auto mode had been the default in Claude Code since Aug 14. The same evening Anthropic and Google made \"Claude Models on Google Cloud (Anthropic managed)\" generally available.","key_facts":["@claudeai (Oct 22, ~1.64M views): 'Starting next week, sessions across Claude web, desktop, and mobile apps will run in auto mode by default on Pro, Max, and Team plans. Rather than asking you to approve each step, an automated check blocks risky actions. Switch back to manual anytime.'","Precedent quoted in the post: auto mode became the default permission mode in Claude Code for Pro, Max and Team users on Aug 14; a separate classifier reviews shell commands and actions, and in Anthropic's testing it 'caught 89% of dangerous commands. Manual approval caught 14%'","Google Cloud (Oct 23 blog): 'Claude Models on Google Cloud (Anthropic managed)' is GA: Anthropic operates the stack as data processor under its Commercial Terms on Google Cloud infrastructure, with Google Cloud IAM, Cloud Audit Logging, Google Cloud billing and commitment drawdown, and day-zero access to Claude Platform features (Managed Agents beta, skills, code execution); models listed: Claude Fable 5.1, Opus 5.5, Sonnet 5.5, Haiku 5.5. The Google-managed option keeps VPC Service Controls, CMEK and data residency","Reach: the Google Cloud GA post on @claudeai had ~468k views"],"key_numbers":[],"tags":["claude","agents","permissions","classifiers","auto-mode","google-cloud","enterprise"],"science":null,"body_md":"## What happened\n\nAnthropic is moving its consumer and team apps, where Claude increasingly runs agentic sessions, to the same classifier-gated permission\nmodel it made the default in Claude Code in August. Users stop approving each step; a separate model blocks actions it judges risky.\n\n## Why it matters\n\nDefault settings decide what most people actually run. The change hands routine oversight of agent actions in Claude's apps from people\nto an automated check, a trade-off Anthropic justifies with its own figures (the classifier caught far more dangerous commands than\nfatigued humans did). It comes in a week when rogue-agent behaviour (banks, OpenAI's monitoring) dominated the news.","disputed":[],"related":[{"id":"2026-10-21-anthropic-claude-duet","url":"https://postcutoff.com/e/2026-10-21-anthropic-claude-duet/","date":"2026-10-21","date_precision":"day","short_title":"Anthropic launches Claude Duet, a proactive background agent app on iOS, Android and the web (research preview)","deck":null,"takeaway":"With Meta's Muse (10M+ users by Oct 21) and OpenAI's Dots already out, all three big consumer labs now ship background agents that act across email, payments and documents.","category":"agents","category_label":"Agents","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":3,"filed":"2026-10-22","updated":"2026-10-22","orgs":["Anthropic"]},{"id":"2026-10-21-openai-models-google-cloud","url":"https://postcutoff.com/e/2026-10-21-openai-models-google-cloud/","date":"2026-10-21","date_precision":"day","short_title":"OpenAI models come to Google Cloud's Model Garden (GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna), making Google the only hyperscaler with all three leading closed model families","deck":null,"takeaway":"Google says it is now the only hyperscale cloud offering all three leading closed LLM families (Gemini, Claude, GPT).","category":"business","category_label":"Business","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":3,"filed":"2026-10-22","updated":"2026-10-22","orgs":["OpenAI","Google"]},{"id":"2026-03-25-claude-code-auto-mode","url":"https://postcutoff.com/e/2026-03-25-claude-code-auto-mode/","date":"2026-03-25","date_precision":"day","short_title":"Claude Code auto mode","deck":"Model-based classifiers approve tool calls instead of the user","takeaway":"Auto mode made classifier-gated autonomy the default way many developers ran coding agents in 2026, and its published false-negative rate is a baseline for later incidents where agents acted beyond their instructions.","category":"product","category_label":"Products","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":2,"filed":"2026-10-10","updated":"2026-10-11","orgs":["Anthropic"]}],"people":[],"posts":[{"id":"x-claudeai-2113360845409583307","title":"“Starting next week, sessions across Claude web, desktop, and mobile apps will run in auto…”","url":"https://postcutoff.com/p/x-claudeai-2113360845409583307/"},{"id":"x-claudeai-2113380122468454765","title":"“Claude Models on Google Cloud (Anthropic managed) is now generally available. Get the…”","url":"https://postcutoff.com/p/x-claudeai-2113380122468454765/"}],"videos":[],"models":[],"changes":[{"date":"2026-10-23","type":"filed","text":"Created (Google Cloud blog)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-23","run":null,"sources_read":null,"updated":"2026-10-23","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":175,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":114,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":205,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":144,"in_training_data":false}],"short_url":null}