Zevari Safety Center

What Safety Center Does

Safety Center is Zevari's control surface for LinkedIn sender health. It explains whether Zevari can run LinkedIn actions, whether the sender is still warming up, which guardrails are active, and why Zevari paused, blocked, or denied recent LinkedIn work.

What Zevari Checks

• Active LinkedIn sender

  Zevari checks the selected workspace and LinkedIn sender before LinkedIn actions run.

• Warm-up state

  Newly connected senders start below full capacity and ramp up gradually.

• Daily and weekly budgets

  Zevari tracks how much activity has already happened for the selected sender.

• Burst caps

  Short-window limits prevent rapid spikes of LinkedIn activity.

• Blocked-action history

  Recent errors, skips, denials, and pauses influence what Zevari allows next.

Warm-Up

Warm-up is the first ramp period after a LinkedIn sender is connected. Instead of operating at full tier capacity immediately, Zevari starts lower and gradually increases activity over time.

• Warm-Up Guide

Common States

• Active

  Zevari can run LinkedIn actions inside the current guardrails.

• Paused

  Zevari is holding LinkedIn activity until the user or safety system resumes it.

• Circuit broken

  Zevari detected repeated failures or unsafe activity and stopped LinkedIn actions temporarily.

• Blocked or denied

  A specific LinkedIn action was refused, skipped, or errored because a guardrail was hit.

Docs Links

• Help Center

  Human-facing guide to Zevari skills, workflows, agents, videos, safety, and support.

• Prompting Guide

  Copy-ready prompts that require AI assistants to read the MCP reference before acting.

• Workspaces and Sender Seats

  Human-facing setup guide for workspaces, members, billing, add-on LinkedIn sender seats, and teammate LinkedIn connections.

• Safety Center

  Human-facing guide to Zevari safety guardrails, warm-up, pauses, blocked actions, and recovery state.

• Warm-Up

  Human-facing guide to LinkedIn sender warm-up and gradual activity ramping.

• MCP Reference

  Agent-facing tool schemas, capability contracts, examples, gotchas, and recovery guidance.

• API Reference

  Public REST API reference powered by the Zevari OpenAPI document.

• MCP Reference JSON

  Machine-readable MCP tool reference.

• LLMs Full

  AI-readable Zevari documentation bundle.

• Support

  Send bug reports, support handoffs, and feature requests.