Scattered versions
The current contract template sits next to three old versions in different folders, and nobody knows which one applies.
Memory for Legal
Templates, clauses, policies and opinions become a reviewed knowledge base. The company asks and gets the current guidance with its source document, and Legal decides what AI may publish.
The problem
And still runs the risk of someone using the wrong version.
The current contract template sits next to three old versions in different folders, and nobody knows which one applies.
Questions that already have a written answer arrive by email and message, and take the time that should go to what is new.
Anyone using a generic AI gets a generic answer, without the company's policy and without saying where it came from.
Before and after
From a manager's question to reviewed guidance.
| Without the company's memory | With Kluco |
|---|---|
| Without the company's memoryEach department keeps its own copy of the template | With KlucoThe current template is in the knowledge base, with an owner and the date of its last verification |
| Without the company's memoryOld guidance keeps circulating | With KlucoWhen the review deadline passes, the article is flagged as overdue |
| Without the company's memoryAI writes and nobody reviews | With KlucoWhat AI writes or updates can wait for Legal's approval |
| Without the company's memoryThe same question arrives by email every week | With KlucoThe company asks the knowledge base and gets the guidance with its source document |
| Without the company's memoryAny agent reads any document | With KlucoEach agent queries only the documents Legal chooses |
What goes into memory
Documents come in from Google Drive, OneDrive, SharePoint, file upload, API or webhook, and every article keeps its version history.
Use cases
The most common use cases in Legal, with the part of the platform that does each one.
Templates, clauses and guidance sit in the knowledge base with an owner and a review deadline. AI uses the current version and shows where it came from.
BrainWhen AI writes or updates an article, the change can wait for the approval of whoever owns the topic.
BrainEach agent queries only the documents you choose, and the access profile sets who can use each agent.
AgentsPeople ask in Slack, Teams or Google Chat and get the answer with the source article.
AgentsWhen the company turns it on, the agent masks personal data in its logs and answers.
AgentsChatGPT, Claude, Gemini and other MCP-compatible tools query the same knowledge base, each person with their own access.
BrainBrain · the memory
The Brain turns Legal's documents into articles with an owner, a review deadline and a version history. Every answer shows the passage and its verification date.
Agents · AI agents
Create one agent for contract questions and another for internal policies, each limited to the documents Legal selects.
LLM Management and Chat
The team uses the models the company allows, in the Chat, which draws on the memory, with an audit log of the configuration and the conversations.
Control
The company sets up each control below in the console.
Related
FAQ
Only if the company wants it to. Human approval is an option: when it is on, everything AI writes or updates waits for a person's approval before it enters the knowledge base.
The current template sits in the knowledge base with an owner and a review deadline. When the deadline passes, the article is flagged as overdue, and every answer shows the passage used and its verification date.
Yes. Each agent can query only the documents you choose, and the access profile sets who can use each agent.
No. It organises what Legal has already decided and delivers that guidance to whoever asks. New matters, non-standard contracts and decisions stay with Legal.
Next step
In the demo, we show the knowledge base, approval of what AI writes and an agent limited to chosen documents.