wiki.co

mx

inbound-smtp.us-east-1.amazonaws.com

ns

ns36.domaincontrol.com

ns35.domaincontrol.com

caa

txt

yandex-verification: 047847552ace239f

google-site-verification=0Lyrv6PDsLabOhpmrO1tEoPhYUtBwAKznUGYgSk45K4

dmarc

v=DMARC1; p=quarantine; pct=100; rua=mailto:hello@wiki.co; adkim=r; aspf=r

User-Agent: *
Allow: /
Disallow: /design-system
Disallow: /app
Disallow: /onboarding
Disallow: /invite
Disallow: /auth
Disallow: /admin
Disallow: /sites

User-Agent: GPTBot
Allow: /

User-Agent: ChatGPT-User
Allow: /

User-Agent: ClaudeBot
Allow: /

User-Agent: anthropic-ai
Allow: /

User-Agent: PerplexityBot
Allow: /

User-Agent: Google-Extended
Allow: /

User-Agent: Applebot-Extended
Allow: /

User-Agent: CCBot
Allow: /

User-Agent: Amazonbot
Allow: /

User-Agent: meta-externalagent
Allow: /

Sitemap: https://wiki.co/sitemap.xml

# Wiki

> Wiki Management for AI Applications. Manage the verified knowledge, permissions, and proof behind every AI answer.

Wiki is the management layer for verified knowledge, permissions, and proof behind AI applications. It helps teams verify sources, control what each AI may use, test answers, and publish documentation from the same governed source.

## What Wiki is for

Wiki is for teams that need AI answers grounded in reviewed sources, not whatever a model happens to retrieve.

- Verified sources: documents go through review before they are allowed for AI use.
- Public-safe vs internal knowledge: customer-facing apps stay scoped to approved public collections. Internal copilots stay scoped to employee-only collections.
- Permission-aware retrieval: each AI Application gets a policy for which collections it may use.
- Answer Playground: test questions and inspect citations before customers see the answers.
- Wiki Connect: an HTTP API for policy-constrained, citation-backed answers from your own bot.

Wiki is not a traditional knowledge base or a RAG retrieval wrapper. It governs which documents are reviewed, allowed, citation-ready, and safe for each AI application.

## Product

- [Home](https://wiki.co/): Overview of Wiki Management for AI Applications
- [Features](https://wiki.co/product): Product capabilities across knowledge, verification, permissions, answers, docs, and health
- [Pricing](https://wiki.co/pricing): Plans start at $29/mo with a 14-day free trial
- [Demo](https://wiki.co/demo): Interactive product demo
- [Docs](https://wiki.co/docs): Product documentation and getting started guides
- [Wiki Connect](https://wiki.co/product/wiki-connect): HTTP API for policy-constrained, citation-backed answers
- [Wiki Connect docs](https://wiki.co/docs/answers/wiki-connect): Create a key and call POST /api/v1/answers
- [About](https://wiki.co/about): Who builds Wiki
- [Changelog](https://wiki.co/changelog): User-facing product updates
- [Security](https://wiki.co/security): Security practices and trust center
- [Affiliates](https://wiki.co/affiliates): Partner program
- [Contact](https://wiki.co/contact): Sales and support

## Feature areas

- [Knowledge](https://wiki.co/product/knowledge): Collections, ownership, lifecycle status, source links, version history, imports, search, relationships, and archive controls give your team one place to prepare knowledge for AI use.
- [Verification](https://wiki.co/product/verification): Review queues, manual source checks, approval workflows, and AI-ready states keep draft and unreviewed content out of production AI so every answer starts from knowledge someone signed off on.
- [Permissions](https://wiki.co/product/permissions): Define AI applications, audiences, policies, and access rules so each assistant uses the right collections and documents.
- [Answers](https://wiki.co/product/answers): Use the answer playground, citations, source coverage, refusals, test cases, evaluation runs, correction tickets, and knowledge gaps to improve answer behavior with evidence.
- [Docs](https://wiki.co/product/docs): Docs sites, custom domains, search, publishing rules, access controls, feedback, analytics, and Docs Assistant keep public docs aligned with governed knowledge.
- [Health](https://wiki.co/product/health): Knowledge Health, review queues, stale sources, conflicts, health flags, governance settings, docs publishing health, and policy health show what needs attention before AI relies on it.

## Common questions

- What is Wiki Management for AI Applications?
- Is Wiki a knowledge base?
- Is Wiki a RAG tool?
- Does Wiki replace my existing documentation?
- Can Wiki help reduce AI hallucinations?
- Can Wiki control what my chatbot knows?

## Resources

- [Blog](https://wiki.co/blog): Essays on AI knowledge, verification, and documentation
- [What Is Wiki Management for AI Applications?](https://wiki.co/blog/what-is-wiki-management-for-ai-applications): Wiki Management for AI Applications governs what AI can use, who can see it, whether it is current, and whether an answer can be trusted.
- [How to Build an AI Knowledge Base for Production](https://wiki.co/blog/how-to-build-an-ai-knowledge-base-for-production): A production AI knowledge base is governed, verified, permissioned, and test-covered. This guide walks through the six gates and a 30-day rollout.
- [Glossary](https://wiki.co/glossary): Definitions for AI knowledge management terms
- [AI Knowledge Management](https://wiki.co/glossary/ai-knowledge-management): The work of deciding what your AI can rely on, who owns it, when it needs review, and what happens when it changes.
- [AI Knowledge Base](https://wiki.co/glossary/ai-knowledge-base): A structured collection of verified documents and sources that AI applications are allowed to retrieve, cite, and answer from.
- [AI Knowledge Governance](https://wiki.co/glossary/ai-knowledge-governance): The policies, ownership, and review systems that control what knowledge AI may use and how it stays trustworthy over time.
- [AI Source of Truth](https://wiki.co/glossary/ai-source-of-truth): The approved, current set of documents and claims that an AI application is authorized to treat as authoritative.
- [RAG](https://wiki.co/glossary/rag): Retrieval-Augmented Generation: a pattern where AI retrieves relevant documents before generating an answer.
- [Retrieval-Augmented Generation](https://wiki.co/glossary/retrieval-augmented-generation): An AI architecture that searches a knowledge store for relevant context, then uses that context to generate a response.
- [RAG Governance](https://wiki.co/glossary/rag-governance): The controls around retrieval that decide which sources are eligible, current, permissioned, and cite-worthy for each AI app.
- [AI Source Monitoring](https://wiki.co/glossary/ai-source-monitoring): Tracking upstream sources for changes that could affect AI answers.
- [Tools](https://wiki.co/tools): Free tools for auditing AI knowledge bases
- [Guides](https://wiki.co/guides): Audits, agent context, and documentation conflicts
- [Checklist](https://wiki.co/checklist): Checks for sources, permissions, and citations
- [Compare](https://wiki.co/compare): How Wiki compares to knowledge bases, RAG tools, and docs platforms

## Use cases

- [Use cases](https://wiki.co/use-cases): AI knowledge use cases for support chatbots, copilots, help centers, docs, and sales assistants
- [A support chatbot should only say what you approved.](https://wiki.co/use-cases/support-chatbot): Keep support chatbot knowledge scoped to verified public-safe collections. Refuse when there is no source, and cite answers through Wiki Connect or the Answer Playground.
- [Employee copilots should not see everything.](https://wiki.co/use-cases/internal-copilot): Scope employee copilots to internal collections with permission-aware retrieval. Keep public-safe knowledge and internal notes in separate collections.
- [One verified source for the help center and the chatbot.](https://wiki.co/use-cases/help-center): Publish public docs from the same verified sources your support chatbot may use. One review workflow, two surfaces, no invented help-center answers.
- [Your docs assistant should quote the published page.](https://wiki.co/use-cases/docs-assistant): Power a docs assistant from verified public-safe documentation. Cite sources, refuse when docs are missing, and keep drafts out of the assistant.
- [Sales AI should only repeat approved claims.](https://wiki.co/use-cases/sales-assistant): Keep sales AI on verified pricing, packaging, and competitive claims. Prohibit inventing discounts or roadmap promises.

## Solutions

- [Solutions](https://wiki.co/solutions): Chatbot hallucinations, refund answers, RAG governance, stale docs, and helpdesk knowledge
- [Stop the chatbot from making things up.](https://wiki.co/solutions/chatbot-hallucinations): Wiki cannot guarantee no hallucinations. It requires source-backed answers, refuses when nothing is approved, and keeps unverified and internal content out of public bots.
- [Do not let the chatbot invent a refund.](https://wiki.co/solutions/refund-policy-answers): Stop a chatbot invented refund. Import the policy URL, verify it, put it in a public-safe collection, attach an AI Application policy, test in the Playground, then serve a cited Wiki Connect answer or refuse.
- [Retrieval is not an AI source of truth.](https://wiki.co/solutions/ai-source-of-truth): An AI source of truth is verified, permissioned knowledge with a policy per application. Wiki Management for AI Applications is that layer, not a second copy of your docs.
- [If it cannot cite a source, it should not answer.](https://wiki.co/solutions/citation-backed-ai-answers): Require AI answers to cite approved sources or refuse. Wiki tests citation behavior in the Answer Playground and serves it through Wiki Connect.
- [RAG needs a governance layer.](https://wiki.co/solutions/rag-governance): RAG retrieves. Wiki governs whether retrieved documents are verified, allowed, and safe to cite for each AI application.
- [Stale docs are an AI outage waiting to happen.](https://wiki.co/solutions/stale-docs-ai-risk): Stale docs become wrong AI answers at scale. Wiki tracks review cadence, source changes, and knowledge health before AI reuses a page.
- [Helpdesk AI needs governed knowledge behind it.](https://wiki.co/solutions/intercom-zendesk-ai-knowledge): Ground Intercom and Zendesk bots in verified Wiki knowledge via Connect adapters and private apps. Cite or refuse instead of inventing refunds.

## Optional

- [Full llms.txt](https://wiki.co/llms-full.txt): Extended page index for crawlers
- [ai.txt](https://wiki.co/ai.txt): Crawl and citation guidance for AI systems
- [Sitemap](https://wiki.co/sitemap.xml)