Meihaku

Pre-launch readiness for AI support

Know exactly what your AI support agent is cleared to answer

Meihaku reads your help center, macros, policies, SOPs, and ticket notes, then matches them to the questions customers actually ask. It drafts cited answers, and nothing reaches your AI agent until you greenlight it.

Launch readiness

Support launch pack

25 blockers

Approved

42

ready for the agent

Conflict

7

policy mismatch

Gap

18

missing evidence

Launch blockers

Ranked by customer risk

1

Refund rules disagree across macros and policy docs

2

Subscription cancellation intent has no approved source

3

Billing escalation answer needs manager review

Approved answer feed

Topic, intent, answer, scope, citations, and approval timestamp exported for downstream support agents.

Readiness, not chat

The first screen is a launch blocker map.

Point Meihaku at your sources

Connect the support sources your team already uses. Meihaku reads help articles, macros, policies, SOPs, and ticket notes.

Meihaku surfaces the questions customers actually ask

It matches customer questions to your source evidence, drafts cited answers, and flags gaps or conflicts.

You approve what ships

Review each draft with sources attached. Approved intents become the boundary your AI agent operates inside.

Built for the support manager carrying launch risk

Ship AI support without shipping the wrong answer.

Coverage you can defend

See which intents have approved answers, which are blocked, and which need a human before launch.

Every answer cites a source

Review the exact policy line, macro, or article behind each draft before approving it.

No rewrite project required

Meihaku does the reading and first pass from the materials you already have. Your team only greenlights what is safe to ship.

Gaps stay out of the agent

Unsupported or conflicting intents stay blocked until your team has source evidence or a handoff path.

Frequently asked

Questions support and compliance teams ask before they buy.

How is Meihaku different from AI support agents like Intercom Fin or Decagon?

Meihaku is the readiness layer that runs before and alongside AI support agents, not a replacement. Tools like Intercom Fin, Decagon, Sierra, and Maven generate answers at runtime. Meihaku audits whether your knowledge base actually supports those answers in the first place, surfacing conflicts, gaps, and ungrounded intents before they reach a customer. Most teams use Meihaku to pre-flight an AI agent rollout, then keep it running as a governance layer.

What sources can Meihaku read?

Help center articles (Intercom, Zendesk, HelpScout, Notion, Confluence), saved replies and macros (Zendesk macros, Front rules, Gorgias auto-responders), policy and SOP documents (Google Docs, Notion, Confluence), and historical ticket notes. Meihaku connects read-only and never writes back to the source.

Does Meihaku replace my AI support agent?

No. Meihaku is complementary. Your AI agent (Fin, Decagon, Sierra, custom) still answers customers. Meihaku decides which intents are cleared for that agent to handle, with cited evidence, and exports the approved answer set. Unsupported or conflicting intents stay blocked until your team has source evidence or a handoff path.

Can my team approve answers before customers see them?

Yes — that's the core workflow. Meihaku drafts cited answers from your sources, your team reviews each one with the source line attached, and only approved intents become the boundary your AI agent operates inside. Nothing reaches production until you greenlight it.

How do you detect conflicts between policies and macros?

When the same intent (for example, the refund window for international orders) resolves to different answers across your help center, macros, and policy docs, Meihaku flags it as a conflict and shows both source lines side-by-side. Your team picks the canonical answer, which becomes the approved version exported to your AI agent.

Is my support data used to train AI models?

No. Customer data is processed in your isolated workspace. We don't train foundation models on your content, and we don't share data across customers. Source content is processed transiently and not retained beyond what's needed for citations.

Launch with approved knowledge, not hopeful retrieval.

Connect your sources. Meihaku reads, matches, and drafts cited answers, so your team can approve what ships.

See your readiness map