Pricing rules in someone's head
The price list is in a spreadsheet, the exception in an email and the old campaign is still going around. Every proposal goes out with a different discount.
Memory for Sales
Playbook, talking points, pricing rules and approved proposals become a reviewed knowledge base, with an owner and a review deadline. Sellers ask and get the current rule with its source, in the Chat or in the AI they already use.
The problem
And what works stays with whoever closed the deal.
The price list is in a spreadsheet, the exception in an email and the old campaign is still going around. Every proposal goes out with a different discount.
The best answer to an objection stayed in one seller's meeting. New hires learn by asking the person next to them and take a long time to sell on their own.
Everyone uses their own AI account, which knows neither the playbook nor the pricing policy, and writes proposals with made-up information.
Before and after
From a question in the middle of a negotiation to a reviewed rule.
| Without the company's memory | With Kluco |
|---|---|
| Without the company's memoryThe discount policy sits in an old spreadsheet | With KlucoThe current policy is in the knowledge base, with an owner and the date of its last verification |
| Without the company's memoryEach seller builds the proposal their own way | With KlucoA skill stores the structure of the proposal, and people and agents use the same one |
| Without the company's memoryWhat is learned in a meeting stays with whoever was there | With KlucoThe recorded meeting becomes a document with the minutes, without personal data, and goes through review |
| Without the company's memoryAn unanswered question becomes a message to the manager | With KlucoAn unanswered question goes into a queue and becomes an article |
| Without the company's memoryEveryone uses their own AI account | With KlucoOne company chat, and the same knowledge base in ChatGPT, Claude or Gemini over MCP |
What goes into memory
Documents come in from Google Drive, OneDrive, SharePoint, file upload, API or webhook, and meetings recorded in Fathom, Gemini in Meet, Fireflies, Zoom, Read AI and Granola become documents with the minutes, without personal data and with review before publishing.
Use cases
The most common use cases in Sales, with the part of the platform that does each one.
The steps of a process, the criteria of an analysis or the tone of an answer are kept as a skill, with versions. Agents and people use the same skills.
BrainEach recorded meeting becomes a document with the minutes, without participants and personal data, and goes through review before it enters the base.
BrainTemplates, 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.
BrainWhat the knowledge base could not answer goes into a queue. Someone answers it once, and the answer becomes an article for everyone.
BrainChatGPT, Claude, Gemini and other MCP-compatible tools query the same knowledge base, each person with their own access.
BrainGPT, Claude, Gemini and other models, all in the Chat, with the access the company sets and an audit log.
LLM Management and ChatBrain · the memory
The Brain turns the playbook, pricing rules and proposals into articles with an owner and a review deadline. Skills store the company's way of qualifying, building a proposal and replying to a customer.
Agents · AI agents
Create an assistant that answers pricing and product questions, or one that drafts a first version of a proposal with the company's skill. You decide what each one queries and what it may do.
LLM Management and Chat
The team uses the models the company allows, in the Chat, which draws on the memory and shows the source. A good answer can be saved to the Brain, with review before publishing.
Control
The company sets up each control below in the console.
Related
FAQ
The current policy 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.
If you turn that source on. Each meeting recorded in Fathom, Gemini in Meet, Fireflies, Zoom, Read AI or Granola becomes a document with the minutes, without participants, emails, phone numbers or tax IDs, and goes through review before it is published.
Yes. The Brain has an MCP server, and compatible tools such as ChatGPT, Claude and Gemini query the same base. Each person signs in with their own access and reaches only their company's base.
It is the company's way of doing a task, stored and versioned: how to qualify an opportunity, the structure of a proposal, the tone of a reply. People use it from the "/" menu in the Chat, and agents use the same skills.
Next step
In the demo, we show the sales knowledge base, skills in the Chat and a recorded meeting becoming knowledge.