FAQ: Wavo / Fast-Smart-Expert modes / voice / mobile push / credits / actions / privacy / image-video gen / multilingual / memory.

FAQ — AI features

Common questions about Wevion's AI capabilities — Wavo assistant, Creative Hub generation, AI-powered rules. For deep-dive: see PRD-20 (Wavo) + PRD-18 (Creative Hub).

What's Wavo?

Wavo is Wevion's in-app AI assistant. Access at /chat. Answers questions about your data, takes actions (with approval), generates creatives via Creative Hub tools.

See ai-101 meet Wavo.

Which AI mode can I use?

You pick a mode, not a specific model — Wevion manages which model powers each mode and hides model names from the picker:

Switch mode per session from the mode picker in the chat composer; modes above your plan render locked.

Can Wavo speak back via voice (TTS)?

No. Voice input via Whisper transcription only (25 MB max). Wavo doesn't generate audio output.

For voice-over generation (audio output for ads): use Creative Hub TTS — see ch-116.

Is there a mobile app for Wavo?

No native mobile app. Use:

• Mobile browser (responsive UI)
• PWA push notifications via VAPID
• Telegram bot for real-time alerts (ntf-104)

How much do AI credits cost?

1 credit = $0.001 with MARKUP 1.1× applied on top of base provider costs.

Per-message cost varies by model + tokens. View per-message breakdown in /settings/team/billing.

See ai-109 credits + limits.

Can Wavo take actions on my account?

Yes — with explicit approval for HIGH / MEDIUM risk actions:

Every tool in TOOL_RISK_MAP runs in approval mode — even LOW-risk drafts show an approval card and do not run immediately. Only creative generation runs without approval. Approval card expires after 30 minutes if not confirmed.

See ai-105 actions.

Can I prevent Wavo from taking certain actions?

Yes — via role-based access control (RBAC). Viewers can't trigger write tools. Specific tools have role requirements.

Workspace-level overrides (which tools available per role): advanced configuration — contact admin.

Does Wavo see my data?

Yes — your team's data only (strictly team-isolated). Wavo cannot see other teams' data.

See ai-104 data grounded.

Are AI conversations private?

Yes — team-scoped. Sent to model providers per their enterprise terms. Most providers do NOT train on customer data (verify your enterprise agreement).

See ai-110 privacy + data usage.

Can Wavo generate images / videos?

Yes — via Creative Hub tools that Wavo can invoke:

• Images: 6 providers (seedream_4, seedream_4_5, nano_banana_pro, nano_banana, flux_2_pro, gpt_image_1_5)
• Videos: 6 providers (luma_ray3, runway_gen4, kling_2_6, kling_3_0, veo_3_1, seedance_pro)
• Avatars: 3 providers (heygen, kling_avatar, veed)
• TTS: 3 providers (elevenlabs, openai_tts, heygen)
• Compositing: Creatomate (assemble video + audio + text + transitions)

See ch-111 AI generation overview.

What languages does AI support?

• Wavo: auto-detects user language; responds in same. Configurable via preferred_language in user_ai_preferences.
• Whisper transcription: optional BCP-47 hint (en, it, es, fr, de, etc.); if omitted, Whisper auto-detects the spoken language.
• Creative AI: multilingual TTS (ElevenLabs) + image / video generation (provider-specific).

Does Wavo remember things across sessions?

Yes — via project memory facts:

• Per-project: max 20 facts (MAX_PROJECT_MEMORY_FACTS)
• Stored in project_memory_fact table
• Opt-out: /settings → AI preferences → Memory toggle

See ai-106 projects + sessions.

Does Wavo hallucinate?

Wavo's system prompt forbids fabricating metrics. It cites the tool that produced each number.

If you suspect hallucination:

• Ask "cite your source" — Wavo should reference the tool
• Switch to a stronger mode (Smart or Expert)
• Give thumbs-down feedback to help improve

See ai-104 data grounded.

How fast is Wavo?

Depends on model + complexity:

• Quick queries (no tools): 2-5 sec
• Single tool call: 5-15 sec
• Multi-tool chain (up to MAX_TOOL_ROUNDS=15, cap 30 calls/session): 30-90 sec
• Creative generation (async): minutes (job polling pattern)

Fast mode is noticeably quicker for short queries; Expert mode is slower but stronger on complex reasoning.

What if I want to disable AI features entirely?

Workspace-level: admin can disable AI features for the workspace (advanced config — contact support).

Per-user: opt out of memory + don't use chat. AI generation tools (Creative Hub) can be limited per role.

Can I integrate my own AI model?

No — Wevion manages the underlying models behind the Fast / Smart / Expert modes; custom model integration is not exposed.

For specific use cases (private models, custom fine-tuning): enterprise tier may include options. Contact sales.

Can Wavo connect to external knowledge (web, my docs)?

• Web search: yes (web_search tool)
• Your uploaded docs: yes (per-session file upload + project files — see ai-106)
• Other knowledge bases: limited (no external KB integration beyond Wevion docs)

Does Wavo learn from feedback?

Yes — feedback aggregated for prompt + model tuning. Per-message thumbs up/down via PATCH /api/v1/chat/messages/:messageId/feedback. See ai-111 feedback + improve.

Can I see my AI usage history?

Yes:

• Per session: messages persisted in chat_session
• Total usage: /settings/team/billing → Recent transactions (credit charges)
• Specific message details: chat_message includes token usage + cost

What's the AI Action Audit Trail?

Every approval-mode action by Wavo logs to ai_action_log:

• Status (PENDING / CONFIRMED / SUCCESS / FAILURE / EXPIRED / REJECTED / BLOCKED_KILLSWITCH)
• Payload hash (SHA-256)
• Idempotency key
• Confirmed by + at
• Executed at

Visible via GET /api/v1/ai-action-log (owner / admin / super_admin, and manager where the team's action_log_visible flag is on).

FAQ

What is Wavo in Wevion?

Wavo is Wevion's in-app AI assistant, accessed at /chat. It answers questions about your data, takes actions with your approval, and generates creatives by invoking Creative Hub tools. Wavo sees only your team's data, strictly team-isolated, and its system prompt forbids fabricating metrics — it cites the tool that produced each number.

Which AI mode can I use in Wevion?

You pick a mode, not a model: Fast (default, everyone including Free), Smart (Plus and up), or Expert (Pro and up). Wevion manages which model powers each mode and hides the model names from the picker. Switch mode per session from the mode picker in the chat composer; modes above your plan render locked.

How much do AI credits cost in Wevion?

In Wevion, 1 credit equals $0.001, with a 1.1× markup applied on top of base provider costs. Per-message cost varies by the model and token count, and you can view the per-message breakdown in /settings/team/billing. Credits fund AI usage across Wavo and Creative Hub generation, separate from your subscription.

Can Wavo take actions on my account?

Yes, but every write/action tool requires your explicit approval — HIGH (e.g. update_entity_budget), MEDIUM (e.g. create_automation_rule), and even LOW-risk tools like create_campaign_draft and create_support_ticket all show an approval card and do not run immediately. Only creative generation runs without approval. The approval card expires after 30 minutes if unconfirmed. You can also restrict actions via RBAC, since viewers cannot trigger write tools in Wevion.

Can Wavo generate images and videos?

Yes — Wavo invokes Wevion's Creative Hub tools to generate media: images via six providers (seedream_4, seedream_4_5, nano_banana_pro, nano_banana, flux_2_pro, gpt_image_1_5), videos via six (luma_ray3, runway_gen4, kling_2_6, kling_3_0, veo_3_1, seedance_pro), avatars via three (heygen, kling_avatar, veed), TTS via three (elevenlabs, openai_tts, heygen), and compositing via Creatomate. Generation runs asynchronously, so it can take minutes using a job-polling pattern.

Related articles

• Meet Wavo — your AI assistant in Wevion
• Wavo credits and limits
• AI Generation overview — what you can create