Memory for Banks and Fintechs

When the rule changes, the answer changes with it.

Products, fees, rules and procedures become a reviewed knowledge base, with an owner and a review deadline. Customer service, back office and AI agents answer customers from the current version.

Product screen, with sample data

The problem

The product changes, the rule changes, and customer service falls behind.

Banks and fintechs deal with many rules, internal and from regulators, that change often.

Outdated procedures

The new fee has come into force, but the service script still shows the old one, and each channel answers differently.

A back office that turns into a help desk

Service agents ask product and operations teams about what is already written in some manual, and the queue of questions grows.

AI close to customer data

An agent that serves customers handles CPF, card and phone numbers, and nobody knows what was logged or who approved each action.

Before and after

What changes at the bank or fintech.

From the published procedure to the answer a customer gets.

Without the company's memoryThe new procedure arrives by email and the old one stays in the scriptWith KlucoThe current procedure is in the knowledge base, with an owner and the date of its last verification
Without the company's memoryTwo rules say different things and nobody noticesWith KlucoAutomatic review points out contradictions, duplicates and overdue articles
Without the company's memoryEach channel answers customers differentlyWith KlucoAI agents and staff answer from the same reviewed knowledge base
Without the company's memoryPersonal data shows up in AI logsWith KlucoEmail, CPF, CNPJ, phone and card numbers can be masked for each agent
Without the company's memoryNobody knows who approved an agent's actionWith KlucoThe audit log records who approved or rejected each action, with the step-by-step view of the run

What goes into memory

What a bank or fintech keeps in memory.

Documents come in from Google Drive, OneDrive, SharePoint, file upload, API or webhook, and become articles that AI keeps up to date.

  • Product conditions, fees and limits
  • Account opening and closing procedures
  • Service scripts per channel
  • Dispute and chargeback procedures
  • Credit policy and approval limits
  • Internal rules and fraud prevention policies
  • Collection and renegotiation procedures
  • Internal system and back-office manuals

Use cases

Where banks and fintechs start.

The most common use cases in banks and fintechs, with the part of the platform that does each one.

  • Procedures and rules in memory

    Internal rules and procedures live in one knowledge base, with an owner, a review deadline and a version history.

    Brain
  • 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
  • Automatic review of the base

    The automatic review points out contradictions, duplicates and expired articles, and the proposals wait in the queue with the before and after.

    Brain
  • Audit trail

    Configuration changes and Chat use are recorded, with CSV export, and every agent run keeps its step by step.

    LLM Management and Chat
  • Personal data masked

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

    Agents
  • AI proposes, a person approves

    When AI writes or updates an article, the change can wait for the approval of whoever owns the topic.

    Brain

Brain · the memory

The current version of every product and procedure.

The Brain turns products, rules and procedures into articles with an owner, a review deadline and a version history. Every answer shows the passage and its verification date.

  • Human approval before publishing what AI writes
  • Automatic review: contradictions, duplicates and overdue articles
  • Audience per article: all agents or internal assistants only
See the Brain
Product screen, with sample data

Agents · AI agents

Agents that serve customers from the knowledge base.

Service agents answer on WhatsApp and the other channels with what is in the reviewed knowledge base, and hand over to a person what they do not know. Each one queries only the documents chosen for it.

  • Rules per tool: allow, ask for approval or block
  • Masking of email, CPF, CNPJ, phone and card numbers, per agent
  • The history of every run, step by step
See the Agents
Product screen, with sample data

LLM Management and Chat

AI for every team, with defined access.

Customer service, operations, product and risk use the models their profile allows, in the Chat, which draws on the company's memory.

  • Access profiles by model, agent, skill and memory
  • A limit per person and a budget per team
  • Audit of configuration and of the Chat, with CSV export
See LLM Management
Product screen, with sample data

Control

What the bank or fintech controls.

The company sets up each control below in the console.

See security and LGPD
  • An owner and a review deadline on every procedure, with a record of who verified it and when
  • A person's approval before publishing what AI writes
  • The audience of each article: agents that talk to customers do not read internal articles
  • Personal data masking in logs and answers, when turned on
  • A record of who approved or rejected each agent action

FAQ

What banks and fintechs ask.

How do I make sure customer service uses the current procedure?

The current procedure sits in one knowledge base, with an owner and a review deadline. When it changes, everyone queries the new version, and every answer shows the document and its verification date. When the deadline passes, the article shows as overdue.

Can the service agent answer anything?

No. It answers with what is in the reviewed knowledge base and hands over to a person what it does not know. Each article defines whether agents that talk to customers can read it, and sensitive actions can require a person's approval.

Does Kluco make the company compliant with regulators?

No. It organises the rules the company has already set, delivers the current version to whoever asks and records how AI is used. Interpreting the rules and making decisions stay with the company's teams.

How does Kluco handle personal data?

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 the current procedure reaching every channel.

In the demo, we show the procedure knowledge base, automatic review and a service agent with personal data masking.