Turn it on first
Suds AI is off by default. An owner enables it under Settings then Suds AI and accepts a short responsibility attestation. Until then, none of the automatic AI features below run. You can also add custom instructions there to tune how the AI works for your business.What it does
Incoming message suggestions
Automatically reads every inbound text and email and suggests follow-ups, pipeline moves, and draft replies for you to approve.
Review request drafting
After a job completes or an invoice is paid, drafts a personalized review request for the customer.
Message rewriter
On-demand polish for a text or email draft before you send it, tuned to the channel.
MCP server
Connect your own Claude account to ShineCRM and operate your CRM in plain language.
How approvals work
Most AI output is a suggestion, not an action. Suggestions appear on the Suds AI page and on the relevant contact and conversation, where you can edit, dismiss, or send them. Pressing Send on a drafted message is the approval: it goes out through your normal scheduled messages queue, usually within a minute. Suds can also send without individual approval when an owner accepts the relevant terms and enables Estimate Follow-ups, Review Follow-ups, or Recurring Service Management. The master switch alone is not enough. Automatic sends have eligibility checks, outreach limits, and a supervisor review. Inactive Customer Finder produces drafts for you to send. Review-request rules under Settings then Reviews also offer hold or auto-send behavior. Review pending messages under Scheduled messages. Turning off a single automation may leave already queued messages; the master Suds AI switch is the immediate stop. See Suds AI controls and Review request drafting.What data the AI sees
To do the work above, the AI is given the relevant customer’s details and conversation history, scoped to your organization. It does not have access to:- Photos or file attachments
- Payment card details
- Any other organization’s data (every request is scoped to yours)
Privacy and AI providers
Your data is processed by two AI providers, each only for the length of a single request:- Anthropic powers the text features (suggestions, drafting, rewriting, summaries). Under Anthropic’s commercial API terms, your inputs and outputs are not used to train its models.
- OpenAI provides the speech-to-text model (Whisper) used to transcribe call and voicemail recordings, and only when you have call recording turned on. Under OpenAI’s API terms, API inputs are not used to train its models.