Meet Cove AI

The AI agent that answers your merchants, grounded in your own docs.

Cove AI reads your help center, website, files, and Q&A, then answers customer questions directly, in their language, with citations. It never invents an answer: when it isn't sure, it hands off to your team with the full context. Not a generic chatbot, an agent that deflects tickets without putting your name on a wrong answer.

Grounded in your knowledge · Escalates when unsure · $0.20 per resolved conversation

Cove AI answering a customer question in chat with a source citation
Answered · 94% confident · cited 2 sources
Grounded in your docs Safe escalation Plan-aware answers Suggest → Auto Reads screenshots Replies in any language

It answers from your knowledge, and only your knowledge.

Cove AI is trained on your own help-center articles, a crawled docs or help site, uploaded files, and hand-written Q&A. Every reply is grounded in what it retrieved, hybrid search plus a reranker pick the right passages, and Cove AI cites them back to the customer. If the answer isn't in your sources, it won't guess a price, a policy, or a step. No hallucinated answers under your brand.

  • Four sources: help center, website crawl, uploaded files (TXT/MD/CSV), Q&A
  • Hybrid retrieval (semantic + keyword) with a cross-encoder reranker
  • One-click "Train AI", embeds your existing articles automatically
  • Source citations shown to the customer; never invents facts or prices
  • Follow-up aware, resolves "what about mine?" into a full question before it answers
Cove AI answering with cited sources from the knowledge base

Start in Suggest. Graduate to Auto when it's earned your trust.

Cove AI starts safe: it drafts replies your agents approve. As your team accepts those drafts, the analytics show the acceptance rate climbing, and tell you when Cove AI is ready to reply on its own. Flip it to Auto, or Auto-only-when-offline so Cove AI covers nights and weekends while your team owns the day. Hybrid does both automatically.

  • Five modes: Off · Suggest · Auto-when-offline · Auto · Hybrid
  • Suggest mode drafts replies; agents accept, edit, or reject in one click
  • Trust funnel surfaces acceptance rate and a "ready for Auto" signal
  • Off-hours coverage tied to your live availability + business hours
  • Handles greetings and small talk itself, never pages a human for "thanks"
The agent setup with reply modes and the Suggest-mode trust funnel

Cove AI knows which merchants pay for your app.

Connect your Shopify Partner account and Cove AI answers with each customer's billing reality in mind, whether they're on a free install or paying, their MRR, and whether they're Shopify Plus. So when a free-install merchant asks about a paid feature, Cove AI is honest that it's paid instead of pretending it doesn't exist, and can nudge an upgrade when you want it to. It only ever cites prices and links that appear in your own sources.

  • Uses real billing facts: paying vs free install, MRR, Shopify Plus
  • Honest about paid features, never a blank "not available"
  • Neutral or nudge-to-upgrade, your call, per app
  • Describe your tiers once; Cove AI answers plan questions precisely
Cove AI giving a plan-aware answer about a paid feature

Built to know its limits, and hand off cleanly.

A confidence threshold decides when Cove AI answers versus escalates. Set topics it must always send to a human, billing disputes, cancellations, legal, and Cove AI never touches them. When it does hand off, it writes a warm, context-specific line so the customer gets a real transfer, not a cold dead end. Customer messages are treated as untrusted, so prompt-injection attempts get politely declined.

  • Tunable confidence threshold: answer more, or only when very sure
  • Scope fence: topics Cove AI always routes to a human
  • Max replies before handoff, and a clear AI disclosure label
  • Warm, context-aware handoff line on every escalation
  • Prompt-injection resistant, customer input is never trusted as instructions
Guardrail settings: confidence threshold and never-answer topics

See exactly what Cove AI deflects, and what it's missing.

A live dashboard shows deflection rate, conversations handled, CSAT, and cost over time, answered versus escalated, day by day. And Knowledge Gaps clusters the recurring questions Cove AI couldn't answer, so you know precisely which Q&A or article to add next to deflect more. You're never guessing, and at $0.20 per resolved conversation, the cost is always clear.

  • Deflection rate, handled count, CSAT, and cost, by date range
  • Answered-vs-escalated trend with deflection % overlaid
  • Knowledge Gaps: recurring unanswered questions, clustered and counted
  • Haiku by default for low cost; Sonnet when you want higher quality
Cove AI analytics: deflection, cost, and knowledge gaps
Why Cove AI is different

Most AI chatbots will confidently make something up. Cove AI won't.

Generic support bots optimize for always having an answer. For a Shopify app, a wrong answer about billing or a setting is worse than no answer, it creates a ticket and a bad review. Cove AI is built the other way: grounded in your docs, honest about your plans, and quick to hand off when it isn't sure. It deflects the easy questions so your team spends its time on the merchants who actually need a human.

Per resolved conversation $0.20 Usage-based. You only pay when Cove AI actually resolves a conversation, not per seat.
Reply modes 5 From draft-only to fully autonomous, graduate at the pace your team trusts.
Knowledge sources 4 Help center, website crawl, uploaded files, and hand-written Q&A.

Put Cove AI on your front line. Free to start.

Train it on your docs in one click, run it in Suggest mode, and only pay $0.20 when it resolves a conversation.