Skip to main content
Put knowledge to work is where you use a store as it stands today, without changing it. Two surfaces live there:
  • Chat is for short exchanges: ask a question, check how the store would answer it, see which artifacts and sources the answer rests on.
  • Task is for long-running jobs: hand Clara a concrete piece of work and come back to the result. If your store captures how you answer RFPs, a task is filling one; if it captures how you review contracts, a task is reviewing one.
Either way, rather than applying the playbooks yourself, you hand the work to Clara: she follows your artifacts, draws on your sources, and shows how each answer was produced and which sources it rests on so you can trust it.

​
Two ways to use a store

Which surface fits depends on the use case:
  • The store is the tool. For answering questions on a policy, producing a recurring deliverable, or checking a decision against your rules, use the store directly. Three surfaces sit at the same level: Chat and Task inside Clarifeye, where you inspect each output and its sources in one place, and MCP through the Clarifeye skill, which brings the same knowledge into the AI client your team already works in.
  • The store is the deliverable. On a project like an ERP migration or an AI deployment, the knowledge is what you hand over: the integrator, the consultants or the team building an agent take it as the specification of how you actually work. They read it in Clarifeye or pull it into their own tools with the Clarifeye skill, so the target system or agent follows your processes, rules and vocabulary.
It’s the same underlying knowledge either way. If a chat or a task shows the knowledge is wrong or thin, that’s a signal: take it into Work with Clara, then try again.