Skip to main content

AI assistant

The KNX Clarity AI assistant is a chat interface backed by a large language model hosted on AWS Bedrock in eu-central-1. It is available from two places:

  • Per-project chat — the "AI assistant" tab on every project detail. Messages here have access to the project's rooms, devices, group addresses, and recent service cases as context.
  • Global chat — an org-wide floating button that opens a chat without any project context. Useful for KNX reference questions that don't belong to a specific building.
Project AI assistant tab showing a chat thread with a user question 'How many dimmers do I have in this project?' and an assistant response listing the dimmers grouped by room.

What it can do well​

  • Explain KNX concepts — "What does DPT_9.001 mean?", "How does a main/middle/sub group address work?".
  • Summarise your project — "How many devices are in the kitchen?", "Which rooms have no dimmers?".
  • Surface recent activity — "What changed in the last week?", "Which service cases are still open?".
  • Draft technical copy — commissioning notes, handover documents, customer-facing explanations.

What it is not good at​

  • Writing ETS XML — it will happily produce XML that looks right but won't round-trip through ETS. Don't paste its output into your ETS project.
  • Live device state — the assistant has no connection to the KNX bus. It can tell you a device exists in the parsed export; it cannot tell you whether the device is currently on.
  • Guaranteed facts — like any LLM, it can hallucinate. Verify anything that would cost you a truck roll.

Privacy​

  • Messages and responses are stored in the aiChatMessages table and are visible only to the author (owner-based auth). Nobody else in your org, including admins, can read your chat history.
  • The message content is sent to AWS Bedrock in the eu-central-1 region. It is not sent to OpenAI or any US-hosted service.
  • The model we use for the beta is Amazon Nova Lite while we wait for Claude access in eu-central-1; messages are not used to retrain the model.
  • Clearing your chat history permanently deletes the messages from Aurora. Use ⋮ → Clear conversation in the chat header.

See the Privacy page inside the web app (app.knx-clarity.com/privacy) for the full data-processing statement.

Rate limits​

During the public beta we apply a soft per-user rate limit:

  • 50 messages per hour per user
  • 500 messages per day per org
  • Maximum context window of 32k tokens per conversation

If you hit the hourly limit you'll see a friendly "Too many messages" banner with a countdown. The daily limit resets at 00:00 UTC.

Providing project context​

The per-project chat automatically injects a compact summary of the project (name, customer, device count, room list, recent activity) into the system prompt at the start of every conversation. You don't need to copy-paste this yourself.

If you want the assistant to focus on a specific subset, just tell it in the first message:

"Only answer questions about the dimmers in this project. Ignore every other device."

The assistant respects that for the rest of the conversation.

Providing feedback​

Below every assistant response you'll see a 👍 / 👎 pair. These are anonymous — we log the message id and the thumbs direction, but not the content — and they feed our beta-period model tuning work. Please use them liberally: they're the single highest signal on what's working and what isn't.