Anthropic adds 16 service integrations to Claude, including Uber, Instacart, and Audible
Anthropic has expanded Claude's connector system with 16 new service integrations, bringing the total to over 200 partners. The additions include Uber, Instacart, Audible, Booking.com, and Spotify, with the company emphasizing no paid placements or sponsored answers.
Anthropic adds 16 service integrations to Claude, including Uber, Instacart, and Audible
Anthropic expanded Claude's connector system with 16 new service integrations this week, bringing the total partner count to over 200. The new additions allow Claude users to interact directly with Uber, Instacart, Audible, and other consumer services without leaving the Claude interface.
The full list of newly integrated services includes:
- AllTrails
- Audible
- Booking.com
- Instacart
- Intuit Credit Karma
- Intuit TurboTax
- Resy
- Spotify
- StubHub
- Taskrabbit
- Thumbtack
- Tripadvisor
- Uber
- Uber Eats
- Viator
How Claude connectors work
According to Anthropic, these services surface in conversations based on relevance, with no paid placements or sponsored answers. "Claude is ad-free and will stay that way," the company stated. When multiple connectors could assist with a request, both appear ranked by usefulness to the user.
Anthropic first introduced the connector system in July 2025. The complete connector directory lists all available integrations, with Anthropic confirming more partnerships are in development.
Managed Agents gain memory capability
Separately, Anthropic updated its Managed Agents feature with built-in memory. Agents can now retain information across sessions using what Anthropic describes as an "intelligence-optimized memory layer." Because memories are stored as files, developers can export them, manage them via API, and maintain control over retained information.
Anthropic launched Managed Agents in early April 2026.
Claude Code adds one-time task scheduling
Claude Code, the company's developer-focused tool, now supports scheduling one-time tasks through the routines feature. Users can schedule tasks via CLI or the Routines UI using the "Schedule -> Once" trigger. Example use cases include scheduling feature flag cleanups or requesting launch reports at specific future times.
Anthropic redesigned the Claude Code experience earlier this month.
What this means
The connector expansion represents Anthropic's push to make Claude a central interface for everyday tasks, directly competing with OpenAI's GPT integrations and Google's extension ecosystem. The emphasis on ad-free operation and no paid placements differentiates Claude from potential competitor monetization strategies. With over 200 partners now integrated, Claude is positioning itself as a comprehensive assistant that can execute tasks across multiple services rather than just providing information.
Related Articles
Anthropic Cuts False Positives in Fable 5's Biology Filter by 85%, Keeps Virology and Toxicology Blocked
Anthropic has cut false positives in Fable 5's biology safety classifier by roughly 85%, letting users ask about lab results, symptoms, and medical questions without being rerouted to the weaker Opus 5 model. Dual-use topics like virology, toxicology, and molecular design remain restricted, with Anthropic citing the difficulty of containing biological threats once released.
Anthropic SDK v0.121.0 Adds Session Budgets, Mid-Conversation Tool Changes, and GitHub Skills Auto-Loading
Anthropic released version 0.121.0 of its Python SDK on August 7, 2026, introducing a new beta for mid-conversation tool changes, session budgets, an advisor tool, pinned inference location, and skills auto-loading from GitHub. The update also removes retired Claude Opus 4.1 models from the API.
Study: Humans Approve 1 in 3 Malicious AI Coding Agent Commands in Browser Game Test
A browser-based game simulating Claude Code-style permission requests found that human reviewers approved roughly one in three malicious commands across more than 40,000 game sessions. The findings, alongside Anthropic's own telemetry showing 93% approval rates for permission prompts, highlight growing concerns about approval fatigue in agentic AI coding workflows.
Anthropic Adds Cross-Session Messaging to Claude Code v2.1.224
Claude Code v2.1.224 introduces cross-session messaging, letting separate Claude Code instances on macOS and Linux send each other summaries to coordinate work. The feature does not support approving permissions or executing commands remotely.
Comments
Loading...