IA AP3K

Configuration de AP3K AI

AP3K AI est disponible sur Pro et Business et peut être activé indépendamment pour les commentaires et les messages directs.

Dans cet article

Étape par étape

  1. Ouvrez AP3K AI et ajoutez des notes de connaissance ciblées et précises.
  2. Définissez le rôle, la voix de marque, le ton, les garde-corps et les choix de protection des commentaires.
  3. Testez les réponses dans Playground, puis sauvegardez explicitement les faits d'affaires utiles à la connaissance.
  4. Activer les réponses d'IA ou les commentaires d'IA au niveau de l'espace de travail et séparément dans chaque automatisation.
  5. Les réponses d'AI comptent pour l'indemnité mensuelle d'IA du régime.

Tap any screenshot to enlarge it. Screens show an example account; your activity and available plan details may differ.

Review readiness in Overview

Read Your AI readiness to see what remains to prepare. Open knowledge takes you to business facts; Open behavior takes you to voice and response rules. AI Replies controls DM replies and AI Comments controls comment replies at workspace level.

These are master switches. Each automation must also opt into AI, so switching on a skill does not automatically convert every saved flow. Use Save changes after editing the configuration.

Overview separates business knowledge, voice and behavior, and the AI Replies and AI Comments master switches.

Add reliable business knowledge

In Knowledge, give each note a clear Topic and fill in Facts AI may use. Choose Add knowledge, check that the note appears under Saved knowledge, and save your changes. Keep separate notes for services, prices, delivery, policies, and frequently asked questions so updates stay simple.

Use exact, current facts and say what the assistant should do when information is unknown. The empty state in the screenshot means no knowledge has been added yet. Do not add passwords, payment details, or private customer information.

Add a Topic and Facts AI may use. Saved notes appear in the panel beside the form.

Choose voice and response boundaries

In Behavior, describe the AI role and your brand voice. Choose Fun, Friendly, or Professional as the default tone. In Guardrails & escalation, explain when to avoid guessing and when to offer human help. Keep these instructions consistent with your saved business facts.

Review Comment protection deliberately. Skip reply and Delete are different actions: deleting affects the Instagram comment. The screenshot shows a Delete selection for insults and hate speech as an example, not a required setting. Choose what suits your moderation policy, then save.

Behavior contains the AI role, brand voice, tone, guardrails, and comment-protection settings.

Test in Playground before going live

Add at least one knowledge note, save the setup, then ask a realistic customer question in Playground. Try a follow-up and a question your notes do not answer. Check accuracy, tone, and whether the assistant respects your boundaries. Update Knowledge or Behavior and test again if needed.

Playground conversations are saved, but they do not become live business knowledge automatically. Save useful facts explicitly as knowledge. Tests use your monthly AI allowance. When the results are ready, enable the appropriate master switch and AI option in the intended automation, save, and test the live flow.

Playground asks for at least one knowledge note before a meaningful test. Tests count toward the monthly AI limit.