A different version in each unit
The new guideline arrives by official letter, the old one is still printed at the counter, and citizens hear different answers each time.
Memory for the Public Sector
Rules, procedures and service guidelines become a reviewed knowledge base, with an owner and a review deadline. Departments, service units and AI agents answer citizens from the same version.
The problem
And every staff change starts the learning over.
The new guideline arrives by official letter, the old one is still printed at the counter, and citizens hear different answers each time.
When a public servant moves to another department or retires, the way of doing things goes too, and newcomers learn by asking colleagues.
Public servants try AI tools on their own, without knowing what leaves the organisation, what it costs or what information it answers from.
Before and after
From the published procedure to the answer a citizen gets.
| Without the company's memory | With Kluco |
|---|---|
| Without the company's memoryThe new guideline arrives by official letter and each unit keeps its own copy | With KlucoThe current procedure is in the knowledge base, with an owner and the date of its last verification |
| Without the company's memoryThe old version is still used in service | With KlucoWhen the review deadline passes, the article is flagged as overdue |
| Without the company's memoryNew public servants learn by asking colleagues | With KlucoNewcomers ask the knowledge base and get the answer with its source document |
| Without the company's memoryEach channel answers citizens differently | With KlucoAI agents and staff answer from the same knowledge base, and the agent hands over to a person what it does not know |
| Without the company's memoryThere is no record of who changed what | With KlucoAudit log for configuration and chat, with CSV export |
What goes into memory
Documents come in from Google Drive, OneDrive, SharePoint, file upload, API or webhook, and become articles that AI keeps up to date.
Use cases
The most common use cases in government bodies, agencies and state-owned companies, with the part of the platform that does each one.
Internal rules and procedures live in one knowledge base, with an owner, a review deadline and a version history.
BrainBranches, units and teams query the same version of each rule. When it changes, everyone answers from the new one.
BrainThe 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.
AgentsConfiguration changes and Chat use are recorded, with CSV export, and every agent run keeps its step by step.
LLM Management and ChatWhen the company turns it on, the agent masks personal data in its logs and answers.
AgentsPeople who just joined ask the knowledge base instead of interrupting the team, and learn the company's way of working through skills.
BrainBrain · the memory
The Brain turns rules, procedures and service guidelines into articles with an owner, a review deadline and a version history. When a procedure changes, AI proposes the update and the responsible department approves it.
Agents · AI agents
Service agents answer on WhatsApp and the other channels with what is in the knowledge base, and hand over to a person what they do not know. Internal agents answer public servants' questions in Teams, Slack or Google Chat.
LLM Management and Chat
Public servants use the models their profile allows in the Chat, with the public body's memory. Every change to access, limits and keys goes into the audit log.
Control
The public body sets up each control below in the console.
Related
FAQ
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.
Yes. Service agents answer on WhatsApp and other channels with what is in the knowledge base, and hand over to a person what they do not know. Agents that talk to the public do not read articles marked as internal.
It stays in the knowledge base, with an owner and a version history. Newcomers ask the knowledge base instead of interrupting colleagues, and learn how the public body works through skills.
With access profiles, data isolated per customer, an audit log and the option to mask personal data, such as CPF, in the logs and answers of each agent. The product was designed around the principles of the LGPD, and the Security page covers each control.
Next step
In the demo, we show the procedure base, approval of what AI writes and a citizen service agent.