First-Run Checklist

Baseline checks

Run the first SophMate session with an administrator who can see settings, diagnostics, approvals, and Copilot. Confirm provider connection, budget controls, and safe-mode behavior before inviting the rest of the team. The installation docs cover plugin activation, and the provider setup tutorial covers the first successful provider request.

Low-risk prompt

Start with read-only questions about site context, product summaries, or documentation. Avoid product edits, coupon creation, Theme Assistant publishing, workflow execution, or support replies during the first run. The goal is to prove that the provider, permissions, and audit surfaces behave as expected.

Rollout decision

After the first session, document the owner for provider keys, approval rules, budgets, support evidence, and workflow access. Teams should review approval controls and roles and permissions before production users start relying on AI output.

Owner and cadence

• Primary owner: site administrator or agency implementation lead.
• Review cadence: during initial setup, after hosting changes, and before adding new SophMate users.
• Escalate when setup cannot be repeated, diagnostics are unclear, or the team cannot identify rollback and support owners.

Production checklist

• Run one read-only Copilot prompt, one diagnostics refresh, one provider test, and one low-risk approval review.
• Keep editors, support users, and marketers out of SophMate until the first administrator run is documented.
• Record the setup owner, production site URL, staging site URL, SophMate version, WordPress version, PHP version, and active theme before rollout.
• Confirm the team can reach diagnostics and support and knows where to pause high-risk activity.

Acceptance checks

• The first run proves provider, permissions, diagnostics, approvals, and budget surfaces are reachable.
• The rollout owner can name the next users to invite and the modules they should not receive yet.
• A trusted administrator can repeat the setup path without relying on private notes or one person's memory.
• The team has a documented rollback or support path before any write-capable workflow is enabled.

Common mistakes

• Inviting the wider team before provider, diagnostics, permissions, and rollback ownership have been verified.
• Treating a successful admin page load as proof that hosting, outbound HTTPS, backups, and support routing are ready.

Related operations

• Map access with Roles and Permissions.
• Set limits with Budget and Usage Controls.
• Use First-Run Checklist before inviting non-administrator users.
• Use Copilot Prompting and Context before team members rely on chat output.
• Use Environment and Hosting Checklist when provider or fetch tests depend on host behavior.
• Use Staging Test Data and Demo Hygiene before testing with production-like records.
• Use Operator Training and SOP Rollout before broad team adoption.