Memory for Customer Service

Every agent, human or AI, answering from the same knowledge base.

Kluco brings the service team's policies, procedures and answers into a reviewed knowledge base, with an owner and a review deadline. AI agents serve customers from it, and the team checks the same source.

Product screen, with sample data

The problem

Every channel answers differently.

When the answer depends on who picks up, the customer notices.

Different answers to the same question

The policy is in a PDF, the exception in an email and the new rule in the supervisor's head. Each agent answers with whatever they found.

Training takes weeks

New joiners take a long time to answer on their own, and experienced people stop what they are doing to help.

AI without a source

A bot that answers without the company's knowledge base invents deadlines, promises what it cannot, and nobody knows where the answer came from.

Before and after

What changes in customer service.

From the first contact to the day's summary.

Without the company's memoryThe right policy is somewhere in the driveWith KlucoThe current policy is in the knowledge base, with an owner and the date of its last verification
Without the company's memoryThe bot answers without saying where it got itWith KlucoThe agent answers from the knowledge base, and the passages consulted are recorded
Without the company's memoryA new question gets lost in the chatWith KlucoAn unanswered question goes into a queue and becomes an article
Without the company's memoryNew joiners learn by asking a colleagueWith KlucoNew joiners ask the knowledge base and get the same answer as the team
Without the company's memoryThe leadership builds the day's summary by handWith KlucoAn agent delivers the day's summary with topics, open items and conversations at risk

What goes into memory

What customer service knows, in one place.

Documents come in from Google Drive, OneDrive, SharePoint, file upload, API or webhook, and resolved customer service conversations also teach the knowledge base, with personal data masked and review before publishing.

  • Exchange, return and refund policies
  • Ticket opening procedures
  • Approved answers to frequent questions
  • Plan and product conditions
  • Delivery deadlines and rules
  • Escalation paths
  • Collection and negotiation rules
  • Announcements and policy changes

Use cases

Where customer service starts.

The most common use cases in customer service, with the part of the platform that does each one.

  • A service agent that answers from the knowledge base

    The agent serves customers on WhatsApp and the other channels with what is in the reviewed knowledge base, and hands over to a person what it does not know.

    Agents
  • An unanswered question becomes an article

    What the knowledge base could not answer goes into a queue. Someone answers it once, and the answer becomes an article for everyone.

    Brain
  • Daily service summary

    At the end of the day, an agent puts together the summary for the leadership: volume, topics, open items and conversations at risk.

    Agents
  • Approved templates and guidance

    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.

    Brain
  • Personal data masked

    When the company turns it on, the agent masks personal data in its logs and answers.

    Agents
  • The same memory for any AI

    ChatGPT, Claude, Gemini and other MCP-compatible tools query the same knowledge base, each person with their own access.

    Brain

Agents · AI agents

Agents that serve customers from the knowledge base, under clear rules.

The service agent answers customers with what is in the knowledge base. You set what it can do, who approves and how much it can spend.

  • WhatsApp, Telegram, Slack, Microsoft Teams and Google Chat
  • Human approval for sensitive actions
  • A monthly budget with an automatic stop and the history of every run
See the Agents
Product screen, with sample data

Brain · the memory

The knowledge base everyone checks, always reviewed.

The Brain turns the service team's documents into articles with an owner and a review deadline. When the deadline passes, the article is flagged.

  • A queue of unanswered questions
  • AI proposes updates, with human approval if you want it
  • Contradictions and duplicates become review suggestions
See the Brain
Product screen, with sample data

LLM Management and Chat

AI for the service team, with costs you can see.

The team uses the best models in the Chat, which draws on the company's memory and saves to the Brain what is worth keeping, after review. In LLM Management, you track limits and cost.

  • A limit per person and a budget per team
  • Cost in Brazilian reais, with the month's forecast
  • Use-case and adoption reports
See LLM Management
Product screen, with sample data

Control

What customer service controls.

The company sets up each control below in the console.

See security and LGPD
  • An owner and a review deadline on every article, with a record of who verified it and when
  • The audience of each article: all agents or internal assistants only
  • Per-tool rules and human approval for the agent's sensitive actions
  • Personal data masking in logs and answers, when turned on
  • A step-by-step history of every run, with its cost

FAQ

What customer service teams ask.

Can the agent answer customers directly on WhatsApp?

Yes. WhatsApp is one of the agents' channels, along with Telegram, Slack, Microsoft Teams and Google Chat. The agent answers with what is in the knowledge base, and you set the rules and approvals.

What happens when the knowledge base does not know the answer?

The question goes into the unanswered questions queue. When someone answers it, the answer can become an article and applies to the team and to the agents from then on.

How does the knowledge base stay up to date?

Every article can have an owner and a review deadline. When the deadline passes, the article is flagged for review. AI also reads the connected sources and proposes updates, which can wait for a person's approval.

Can the team check the knowledge base too?

Yes. The team asks the knowledge base in the console or in the Chat and gets the answer with its source passages, from the same knowledge base the agents use.

How does it handle the LGPD in customer service?

With access profiles, data isolated per company, an audit log and the option to mask personal data in the logs and answers of each agent. The Security page covers each control.

Next step

See a service agent answering from your knowledge base.

In the demo, we show the knowledge base, the agent and the unanswered questions queue with customer service examples.