Scenarios are great for structured, repeatable flows. But real conversations don't always follow a script. AI actions let you add flexibility at the exact points where contacts go off-path, without rebuilding the whole flow.
This article shows patterns for combining AI with your existing scenarios. For the full detail on each AI action, see AI Smart Actions in Scenarios.
⚠️ AI actions need Pro and AI features, and each run uses AI credits. When your credits run out, the actions are skipped and the flow continues.
Pattern 1: branch where keywords can't
Keyword conditions handle simple yes/no choices. They break down when contacts express the same intent in a dozen different ways.
After an open-ended question, add an AI-detected condition with a plain-language rule like "the contact is interested in buying" or "the contact is asking about the free plan." It reads the full conversation, not only the last message, so it can judge intent even when the reply was short or phrased oddly. Route the true branch to a conversion step and the false branch to more nurturing.
Pattern 2: hand off at the right moment
The most common AI pattern is "structured start, open handoff." Your scenario handles the predictable part (the first reply, qualifying the contact, collecting details), then hands the open conversation to the AI Agent.
Use Hand over to AI Agent as the last action in your flow, with a short, factual instruction.
Keep the instruction to a sentence or two: "Contact confirmed interest in 1-on-1 coaching. Goal is to book a discovery call." That's more useful than a paragraph.
Pattern 3: add one personalised AI reply
Not every message needs to be fixed text. Some moments call for a reply that responds to what the contact said in the previous step.
After a step where the contact says something variable, add an AI Agent message action with a clear instruction like "Acknowledge their answer and move to the next step." Unlike a full handover, the scenario keeps running and the agent handles only that one message.
Pattern 4: filter before the flow even starts
If your scenarios trigger from public content like comments or open DMs, filter at the entry point so spam and off-topic messages don't consume your runs.
Use the AI-detected intent trigger filter to fire the scenario only on messages that match a specific intent, and keep exclude hateful and negative comments on for comment triggers. That keeps junk out before any step runs. See Using AI to Filter Scenario Triggers.
When to use AI versus rule-based logic
AI and rule-based logic solve different problems. Knowing which to reach for saves debugging later.
Use AI actions when:
Replies are too varied for keyword matching.
You need to judge tone or intent, not only the exact content.
The conversation has enough context for AI to work with.
Stick with rule-based logic (see Flow Control) when:
The condition is simple and binary, like "are they in folder X?"
The stakes are high, like payments, bookings, and confirmations.
You need guaranteed, predictable behaviour.
🐾 Netsuke's Tips
AI conditions aren't instant. In high-volume flows, add a short Time delay before an AI condition so it has time to evaluate.
Test AI conditions against real conversations from your inbox before going live. The preview shows whether a given message evaluates true or false.
If an AI Agent message runs too long or too short, change the message-length setting on the action rather than adding length instructions to the prompt.
Keep handover instructions short and factual. State the situation and the goal in one or two sentences.
What's next?
For the full reference on every AI action and when to use each, read AI Smart Actions in Scenarios. To control which messages start your scenario in the first place, read Using AI to Filter Scenario Triggers.