Claudeforce Arrives: Salesforce and Anthropic Expand Partnership, Claude Becomes Slack's Default Model

Claude is now Slack's default model — the window you open most at work just quietly got a new brain.

Ben Calloway · August 27, 2026

Salesforce and Anthropic jointly announced Claudeforce on August 26, 2026, the latest expansion of their partnership. This round goes well beyond letting Salesforce customers simply choose a Claude model — it embeds Claude directly into the core of Salesforce's workflow, and makes Claude the default model powering Slack.What the Partnership Actually DeliversThe first product under Claudeforce is Salesforce in Claude, a Plugin with 37 prebuilt sales skills that let sellers handle meeting...

practice

Claude Code's --worktree Now Accepts a GitLab Merge Request URL Directly, No Number Conversion Needed

One fewer step of "look up the number, then manually assemble the format"...

tools

Claude Code Remote Control Now Streams Live: Every Foreground Subagent Tool Call, Visible on Your Phone

Background subagents still only show status — that's not an oversight, it's...

tools

Claude Code Adds PreModelSwitch/PostModelSwitch Hooks: Switching Models Can Finally Be Intercepted and Logged

Automatic fallback and session resume never go through PreModelSwitch —...

Useful Resources

Claude API Status → Model Pricing → Prompt Playground → Token Counter → MCP Servers → LLM Benchmarks → Model Comparison →

Glossary

View All →

Agent Permission Scoping

The practice of deliberately granting an <a href="/en/glossary/core-concepts/ai-agent/">AI Agent</a> only the minimum set of permissions needed for its current task, rather than granting broad access far beyond actual need for convenience, so the potential impact of an error stays as contained as possible.

What is <a href="/en/glossary/agent-permissions/agent-permission-scoping/">Agent Permission Scoping</a>, and how does it differ from the intuition...

advanced

Least-Privilege Agent

Granting an agent only the minimum set of tools and data access strictly needed for its current task, rather than starting broad and narrowing later.

What does the principle of least privilege actually mean when applied to an agent? Least privilege isn't an AI-specific concept — it's a...

intermediate

Prompt Injection Defense

Designing a mechanism so an agent, while processing external data (like webpage content or user-uploaded documents), can distinguish original task instructions from malicious instructions potentially hidden within the data itself, avoiding being misled into performing unintended actions by content buried in that data.

What is prompt injection defense, and how does it differ from typical <a href="/en/glossary/prompt-techniques/jailbreaking/">jailbreaking</a>...

intermediate

Weekly Picks

practice

Claude Code's Auto Mode Became the Default on 8/14, and Its Rules Are Now Written as Plain Sentences

Making Auto Mode the default doesn't really change who clicks approve — it changes whether...

Derek Finch

tools

Claude Code's New Feature: It Drafts Its Own Feedback Report When Something Goes Wrong, and You Decide Whether to Send It

When something goes wrong, it writes the report and leaves it on the desk before anyone asks —...

Marcus Ide

mcp

What Actually Changed in the MCP 2026-07-28 Spec: From Stateless Core to Stronger OAuth

MCP moving from a persistent bidirectional connection to a request-response model sounds like an...

Hannah Scott

beginners

Claude Memory for Beginners: How Cross-Conversation Memory Works, and What About Sensitive Info?

Memory doesn't save your health, beliefs, or politics by default — that's not the system being...

Grace Patel