Skip to main content
Clarifeye captures the knowledge a project runs on, consolidates it into structured artifacts, and exposes it to your team and your AI tools. Once you know these concepts, the rest of the docs read quickly.

​
Organization and knowledge store

Clarifeye has two layers. Organization is your company’s top-level account. Billing, plan, org-wide settings (SSO, security), shared organization context, Clara skills, and knowledge store templates live here, so finance and admin only manage one contract. See Organization settings. Knowledge store is the working unit inside an organization: one self-contained body of expertise, typically one per project, team, or use case. An organization can hold several. Permissions are scoped to a knowledge store rather than the organization, so the same person can be a contributor in one store and a user in another, while billing rolls up to a single invoice.

​
Inside a knowledge store

Every knowledge store is organized the same way: its sidebar follows the lifecycle of the knowledge inside it. See How this maps to Clarifeye for what each sidebar item is for.

​
Clara

Clara is Clarifeye’s AI consultant. She scopes the project with you and proposes the artifacts and plan, reads your sources and flags gaps and contradictions, drafts and runs interviews, and consolidates what comes in. She is proactive: on every new interview, signal or source she proposes the next step, who to interview, which gap to close, which artifact to update. Clara does the analysis and the mechanical edits, you stay in control of every change.

​
Artifacts

Artifacts are the consolidated, trusted output of a knowledge store, the documents your teams work from and AI clients draw on. Each one has a purpose (what it is for) and a format (how it is stored). Clara proposes a starting set when you scope the project, grouped by purpose:
  • Project management: the brief (mission and context) and the project plan (what remains to be done, and who does what).
  • Knowledge capture: the mental map (the domain’s ontology: glossary, domains, classes and relations) and general knowledge (the conventions and exceptions an expert just knows).
  • AI orchestration: playbooks (how an expert approaches a kind of task, step by step) and design templates (the output formats the store produces).
  • Data and documents: the library description (what source material the store draws on and how to navigate it).
  • Custom: anything your methodology needs, such as a process blueprint or a business rules table.
Formats range from a plain document to a concept map, a playbook list, a BPMN process diagram or a table. Artifacts are versioned and keep the evidence they were built from. Where two contributors disagree, both versions are kept and flagged. See Artifacts.

​
Sources

Sources are the context the store draws on, alongside interviews. They can be uploaded documents (PDF, docs, slides, spreadsheets), connected sources pulled from Google Drive, SharePoint, and other connectors, or external MCPs that give Clara access to tools and systems such as Confluence, Granola, or your IT systems. See Sources and External MCPs.

​
Interviews

Interviews are how Clara captures what nobody wrote down. She spots the gaps worth exploring and drafts the interviews; you assign each one to the person who holds that knowledge. Clara conducts it asynchronously, in the contributor’s own language, with every question informed by what is already known. See Interviews.

​
Signals

A signal is anything that should update the knowledge store: a correction, a gap, a piece of drift, or new context. Signals can come from anywhere people use the knowledge (an AI client, a chat or a task, Slack or Teams, or a manual note) and are centralized in one place so nothing is lost. Clara helps turn them into concrete updates, sometimes triggering a new interview. See Signals.

​
The Clarifeye skill and how AI consumes a store

Your team installs the Clarifeye skill in their AI client. The skill teaches the client how to work with Clarifeye, then uses the Model Context Protocol (MCP) to discover knowledge stores, inspect their artifacts, run retrieval, and raise signals. The same knowledge feeds every client you already use (Claude, ChatGPT, Copilot, or your own), and your process logic is stored separately from the model that reads it, so you can change model without rebuilding. See Connect to AI clients.

​
Chat and Task

Chat and Task apply a knowledge store to real work at a point in time, inside Clarifeye: Chat for short exchanges and questions, Task for long-running jobs that produce an output. Where Work with Clara changes the knowledge, Chat and Task use it as it stands today. Which surface you reach for, and whether you use the store directly or plug it into your own AI client, depends on the use case. See Use.