Claude Blog, read from an operations desk

Latest

Anthropic Pairs Claude Agents With NVIDIA's OpenShell

Anthropic worked with NVIDIA to add security layers to Claude's agent stack. Claude Managed Agents now holds credentials in a separate vault the agent never sees, while NVIDIA's open-source OpenShell blocks every agent action unless explicitly allowed. Together they let companies log, restrict and verify what deployed agents can reach.

What changes for operators — For a 10-200 person company running Claude agents against CRM, support tickets or finance systems, this closes a real gap: until now, giving an agent broad tool access meant trusting the model itself not to misuse credentials. With Managed Agents separating the agent loop from the sandbox and vaulting credentials, and OpenShell enforcing a default-deny policy on every file, network call and data access, an operations lead can start an agent on narrow permissions, review the audit log, and widen access only where the log shows it's needed — turning agent rollout from a one-time trust decision into an auditable, reversible control process.

Claude Tag lets Slack users bring their own connectors

For a sales or support team running Slack with Claude Tag, this closes a real gap: previously an admin had to attach a shared CRM or drive connector to a whole channel, which either over-exposed data or left reps unable to ask Claude about their own accounts. Now a rep can ask @Claude in a deal-review channel to check their own CRM pipeline or a support agent can pull their own ticket queue, without granting the entire channel access to that data. Combined with auto-post or manual review modes, this lets ops leads decide per-workflow whether Claude's answers post automatically or wait for a human check — useful for anything touching pricing, contracts, or customer-specific plans. The tradeoff: unattended or scheduled automations (on-call triage, nightly reports) still depend on connectors an admin explicitly attaches to the channel, so teams still need to plan which workflows are personal-and-supervised versus shared-and-automated.

Claude for Small Business adds 43 workflows and 27 integrations

For a company running sales and ops with 10-200 people, the workflows on offer map directly onto tasks that currently eat an owner's or ops lead's time: a Monday brief pulled from 37 possible connectors, after-hours lead qualification and CRM logging, proposal generation priced from past jobs, and a monthly close that reconciles across payroll, card spend and sales settlements. The governance model is the part worth checking before adopting any of it: every workflow defaults to approval mode, existing software permissions carry over unchanged, and Anthropic states it does not train on business data by default on Team and Enterprise plans. That's the detail an operations lead should verify against their own compliance requirements rather than assume from the marketing copy — the connector list, the approval gate, and who can see what once Claude is wired into finance and CRM systems.

Anthropic Ships Salesforce Plugin That Drafts CRM Updates From Inside Claude

For a sales team at a 10-200 person B2B company, this turns Claude into the layer that assembles call prep and drafts CRM hygiene work — stage changes, close dates, follow-up tasks, contact records — that reps currently do manually or skip. The catch is it needs an admin to connect Salesforce and Slack org-wide through AgentExchange and requires a paid Claude plan; it doesn't replace Salesforce as the system of record, and every write still needs a human approval click, so the actual time saved depends on how disciplined the sales org already is about logging activity.

Claude Tag Slack Agents Close Most Incident Tickets Unaided

None of these companies' constraints are healthcare-specific in structure: an ops team runs a Slack channel for alerts, another for an internal tool, another for a body of undocumented policy knowledge that lives in a few people's heads. Claude Tag's per-channel scoping (no PHI/PII connectors, DMs off, access bundles limited per channel) means a 10-200 person B2B company could run the same pattern today - one channel for support-ticket triage, one for a recruiting or CRM internal tool where the agent ships and deploys changes on request, one for policy or pricing questions that currently bottleneck on a single expert. The Team-tier credit ($2,500 for 10+ seats, expiring October 1, 2026) is sized for exactly this segment, not enterprise accounts.