> ## Documentation Index > Fetch the complete documentation index at: https://developers.autoplay.ai/llms.txt > Use this file to discover all available pages before exploring further. # Step 2 — Define proactive triggers > Proactively message users in Botpress based on what they're doing in your product — coming soon. **Coming soon.** This step is currently in progress. Check back shortly. Once you've connected real-time events in [Step 1](./step-1-connect-real-time-events), the next layer is proactive triggers — letting your Botpress bot reach out to users **before** they ask, based on what they're doing in your product. ## What this step will cover * Defining trigger conditions on top of live activity pulled from the Autoplay connector (e.g. user stuck on the same workflow step, first visit to a key feature, repeated failure signals) * Routing a firing trigger to Botpress as an outbound message or quick-reply prompt * Gating triggers with the Autoplay FSM (`can_show_proactive_with_reason`) to avoid noise and respect cooldowns * Using the Botpress Conversations API to initiate a conversation when no active thread exists ## Why proactive triggers matter here With only Step 1, your Botpress agent is context-aware but still **reactive** — it waits for the user to open chat. Proactive triggers let the bot send the first message at exactly the right moment: when the user is visibly stuck, exploring a new feature for the first time, or resuming an incomplete workflow. *** **Back to overview:** [Botpress tutorial](./)