AI features: Cleo, reply suggestions and automation
Clientflow's AI module analyzes your customer communication and suggests replies, actions, and templates, saving you time while delivering consistent service. The AI learns from your choices and adapts to your company's style.
What does the AI do?
Clientflow's AI works in several layers:
- Cleo: the AI assistant that answers questions, shows you the way and runs actions when you approve
- Reply suggestions: generates draft replies to customer inquiries
- Action cards: suggests concrete actions (rescheduling, cancellation, etc.)
- Template learning: learns from your replies and builds a growing bank of reply templates
- Business rules: detects patterns and suggests rules that improve future replies
- Feedback analysis: analyzes your feedback to find opportunities for improvement
Important: The AI never automatically sends replies to customers. Every suggestion is reviewed and approved by a team member before it's sent.
Cleo, the AI assistant
Cleo is included in every plan. Click Cleo to start a conversation and write the way you talk:
- Ask: Cleo looks things up in your customers, orders, leads, offers, invoices and conversations. For example "What's on tomorrow?" or "Find a customer by address or phone number".
- Get shown the way: Cleo explains how Clientflow works and points at the button you need.
- Get actions done: Cleo can run more than 200 actions. Each action appears as a card showing what will change, and runs only when you press Run. Bigger changes get an extra preview and a Confirm. If an action can't be undone, the card says so.
Allowance: Starter and Professional have a monthly allowance for Cleo that resets on the 1st of the month. When it is used up, Cleo says so in the conversation. Enterprise uses the included AI credits instead. Cleo's allowance can't be spent on AI reply suggestions.
Cleo planning
Cleo can also help with planning. It is part of Enterprise only, and it uses AI credits. It is not included on Starter and Professional. If the company has switched AI off, Cleo planning is not shown at all.
The week's planning summary
Turn on the switch Show this week's planning summary under Settings → Planning. Every week Cleo then writes in the calendar which orders could not be planned or were split, and why. You can take each point further with Cleo.
The switch is off when you start. The summary costs nothing until the office turns it on.
Ask Cleo why an order turned out the way it did
Ask Cleo why a particular order was not planned, or why it was split. You get the explanation right away instead of searching the calendar. Administrators and office staff can ask this.
To read more about how the planner thinks, see Planning rules.
Activation
First time
The first time you enable AI features, a consent dialog appears:
- Confirm that you understand how the AI uses your data
- AI is enabled per company (tenant)
- You can disable AI again at any time
Tell AI about your business
In Settings → AI, in the Tell AI about your business block, you write two texts in your own words:
- Who are you?: What do you do? Who are your customers? What makes you different?
- How do you talk to customers?: Friendly or formal? Words you always use, or never?
The texts are saved when you save the page. Under How do you talk to customers? you can also upload a PDF style guide, and the text is read out of the file.
The more AI knows about who you are and how you talk to customers, the better its suggestions.
Can't see the AI page? Then AI is switched off for the company with the AI processing master switch under Settings → Company profile.
AI reply suggestions
Generation
On Starter and Professional you generate a suggestion yourself with Generate AI suggestion in the conversation. You get 3 AI reply suggestions per week.
On Enterprise AI reply suggestions have no weekly limit and can also be generated automatically when a customer sends a message:
- The AI analyzes the message automatically
- Within seconds, a reply suggestion appears below the compose field in the communications module
- The suggestion is adapted to the channel (email format, SMS format or generic)
What the AI analyzes
| Analysis | Result |
|---|---|
| Intent | What does the customer want? (E.g. rescheduling, complaint, inquiry, cancellation) |
| Sentiment | Positive, neutral or negative; indicates urgency |
| Customer history | Previous tasks, subscriptions, communication; provides context |
| Confidence | How sure the AI is about its suggestion (as a percentage) |
| Needs human | Whether the inquiry is too complex for an automated reply |
Actions on the suggestion
| Action | Description |
|---|---|
| Accept | Inserts the suggestion into the compose field. You can edit before sending |
| Dismiss | Hides the suggestion |
| Regenerate | Asks for an alternative suggestion |
| Save as template | Saves the suggestion as a reusable template for future use |
Internal notes
The AI often adds an internal note: a short explanation to you of why it suggested this particular reply. The note is only visible to team members and is never sent to the customer.
AI action cards
Beyond text replies, the AI can suggest concrete actions based on the customer's inquiry. Actions appear as interactive cards that can be expanded and edited.
Available actions
| Action | Description |
|---|---|
| Reschedule task | Move a task to a new date, with optional locking type and team-member assignment |
| Cancel task | Cancel a specific task |
| Update task constraints | Change time-window preferences for a task |
| Update subscription interval | Change the frequency of a subscription |
| Update subscription constraints | Change time constraints on a subscription |
| Update contact notes | Add or update notes on a contact |
| Update contact notifications | Change notification settings for a contact |
| Update lead status | Move a lead to a new column in the pipeline |
| Open complaint | Log a complaint based on the customer's message |
How to use action cards
- Review: the card shows a summary: "Current date → Suggested new date"
- Expand: click to see and edit every field
- Adjust: change details if the AI's suggestion isn't quite right
- Confirm: click to perform the action
- Completed: the card shows a green confirmation with a summary
Example: The customer writes "Can we move the window cleaning to next Tuesday?" → The AI shows an action card with:
- Current date: Wednesday April 8th
- Suggested date: Tuesday April 14th
- Team member: Ahmed (unchanged)
- Locking type: Day (suggested)
You verify, edit if needed, and confirm with one click.
Feedback and learning
Give feedback
The AI's suggestions get better over time, but only if you give feedback:
- Thumbs up / thumbs down: quick rating of the suggestion's quality
- Written feedback: elaborate on what was good or bad
- "Missing action": flag if the AI should have suggested an action it didn't
What happens to your feedback?
- Feedback is classified automatically into categories:
- Business rule: "We always issue a credit note on complaints older than 3 days"
- Missing action: "The AI should have suggested cancelling the task"
- Style: "The tone was too formal"
- Context gap: "The AI lacked information about the customer's history"
- Factual error: "Wrong date or price in the suggestion"
- Business rules with high confidence → created automatically as inactive rules (awaiting your approval)
- Missing actions → counted and prioritized in the action-gap overview
The AI page in Settings
Everything about how the AI learns is under Settings → AI. The page is split into blocks:
| Block | What you use it for |
|---|---|
| Learning | The switch Learn from your replies turns on and off whether the AI learns from how you answer customers |
| Tell AI about your business | The two texts Who are you? and How do you talk to customers? (see Activation above) |
| What AI has learned | Rules the AI suggests based on your feedback |
| Templates AI has put to work | Templates the AI has put into use |
| Template health | Status of the templates on your account |
| Suggestion signal | The last 30 days of figures on how AI suggestions are used |
If Learn from your replies is off, only the first block is shown. The others appear once you have turned learning on and saved.
What AI has learned: rules
When you give feedback on the AI's suggestions, it proposes new rules. You decide whether they are used:
- Activate: the AI uses the rule next time
- Not relevant: you dismiss the suggestion. Dismissed rules are listed under Show … dismissed, and you can bring one back with Restore
- Rephrase: edit the wording of the rule before you use it
- Show … rules in use: the rules the AI uses now. Here you can Deactivate a rule or Delete forever
Under Why? you can see the feedback the rule came from.
Template learning
Clientflow learns from your actual sent replies:
- Observation: Each outgoing reply is analyzed automatically (every 15 minutes)
- Synthesis: Every night the AI reviews the observations and:
- Creates new templates from recurring reply patterns
- Updates existing templates with better wording
- Demotes templates that are rarely used
- Priority: Three template sources:
- Seed (default): predefined templates, lowest priority
- Learned: automatically generated templates
- Manual (manually saved): templates you saved yourself, highest priority
AI settings
| Setting | Where | What it does |
|---|---|---|
| Learn from your replies | Settings → AI, the Learning block | Turns on or off whether the AI learns from your replies |
| Who are you? and How do you talk to customers? | Settings → AI, the Tell AI about your business block | Gives the AI context about you and your tone |
| Allow AI processing | Settings → Company profile, the Privacy and access block | The master switch. When it is off, no customer messages are sent to AI and the AI settings are hidden |
Turning Learn from your replies off does not stop the AI from reading your messages. Only the AI processing master switch does that.
Automated workflows
Beyond reply suggestions, you can create AI-powered workflows in Workflows:
- Define a schedule (e.g. "Every Monday at 07:00")
- Pick data sources (which tables the AI should read: tasks, subscriptions, contacts, etc.)
- Write a prompt: describe what the AI should generate
- Pick an output: which inbox the result is sent to
Examples:
- "Generate a weekly summary of every unfinished task and send it to the admin inbox"
- "Identify customers who haven't received service in 60+ days and generate a follow-up message"
- "Build an overview of this week's leads with recommended actions"
Event-based workflows
Event-based workflows trigger automatically when a message is received in an inbox. No AI credits are consumed.
Setup:
- Pick the inbox the workflow should watch
- Pick a message type: email, SMS or note
- Optionally add sender contacts to limit the trigger to specific senders
- Configure actions that run in order:
| Action | What it does |
|---|---|
| Extract fields | Pulls data out of the message content via regex (e.g. phone number) |
| Find or create contact | Looks up a contact based on extracted fields, or creates a new one |
| Write note | Writes an internal note on the contact's conversation |
| Close conversation | Automatically closes the sender's conversation after every action |
Example: A supplier sends an SMS in the format "New customer: Peter Hansen / 4512345678". The workflow extracts the name and phone via regex, finds or creates the contact and writes a note, all without manual intervention.