Chat

Kasimir's multi-LLM chat: write with several language models in a GDPR-compliant way, analyse files, search the web, and bring in company knowledge and tools.

Chat is the heart of Kasimir: a conversation window where you work with several AI language models – write and rephrase text, summarise documents, search the web, query databases, generate charts, and much more. Everything runs in a GDPR-compliant way; the default model is operated on Kasimir's own servers inside the EU. This article explains every feature exactly as it behaves in the product.

What chat can do

• Talk to several LLMs and switch models at any time

• Attach files (PDF, Word, Excel, PowerPoint, images and more) – the text is extracted and read automatically

• Search the web and have individual pages read

• Bring in company knowledge (uploaded documents), databases, and integrations (Microsoft 365, Google Workspace …)

• Generate charts and simple interactive 3D scenes right inside the chat

• Dictate (microphone) instead of typing

• Address and combine assistants (predefined personas)

• Have answers read aloud, copy, share, and rate them

Starting a chat

1. Open Chat from the sidebar. You land on the start screen with a personal greeting and example prompts.

2. Type your question into the input field – or click one of the example cards (Summarize the key points…, Draft a reply email…, etc.) to load it as a draft.

3. Press Enter or the orange send button. The first message automatically creates a conversation and derives a title from it.

The input field (composer)

Below the text field you'll find a compact toolbar:

The "+" menu

The + icon gives you three actions:

• Upload file – attaches a document or image to this message.

• Workflows – starts a predefined, multi-step workflow.

• Prompt library – inserts a saved template into the input field.

The "Tools" menu

Use Tools (sliders icon) to enable extra capabilities per chat. Active tools then appear as removable chips above the input field; a checkmark marks the current state.

The "@" context picker

Type @ in the input field to open a picker. Results are grouped by category:

• Integrations – activates a connected source for this chat.

• Folders – selects all documents in a document folder as knowledge.

• Assistants – inserts a persona as a coloured pill mid-sentence; that one message is then answered by that assistant.

• Files – inserts the file name as an @filename text reference.

Dictating instead of typing

The microphone icon starts voice recording. While recording, a live waveform replaces the toolbar; clicking again stops it, the speech is transcribed and inserted at the cursor position. This requires your browser's microphone permission.

Choosing the model

On the right of the toolbar sits the model picker. When opened, it shows a list with a data-residency badge per model:

• EU (green) – processed inside the EU.

• Non-EU (amber) – data leaves the EU; only available if your organisation has explicitly allowed it.

Hovering a model opens (on desktop) a detail card with Context size, Vision support (yes/no), and the exact data processing:

• Processed on Kasimir's own servers in the EU (the sovereign default model)

• Processed in the EU via Azure AI Foundry (Microsoft)

• Processed outside the EU – data leaves the EU

Attaching files

You can add files via + → Upload file, the paperclip icon, or drag & drop straight onto the input field. The attachment dialog also offers the tabs In chat, In project, Upload, Microsoft 365, and Google Workspace.

• Maximum size: 25 MB per file.

• Supported formats: PDF, Word (DOC/DOCX), Excel (XLS/XLSX), PowerPoint (PPT/PPTX), OpenDocument (ODT/ODS/ODP), RTF, TXT, Markdown, CSV, HTML, XML, JSON, and images (PNG, JPEG, WEBP, HEIC).

Kasimir extracts the text automatically and makes it available to the model – across multiple follow-up messages too. Very large attachments are not sent in full but searched intelligently (RAG) so the context window doesn't overflow.

Sending, cancelling, and the safety dialogs

Before the message actually goes out, two dialogs may appear:

1. Web search suggested – if web search is off but the question looks like it needs current information (prices, products, facts, sources), Kasimir asks: enable & ask again, Send anyway, or cancel.

2. Context window almost full – if the message would exceed the model's limit, you can choose: Compress & send (summarise older history), Send anyway, or cancel.

While the answer streams, the send button becomes a Stop button – one click aborts the running response. You can already type your next message while streaming continues.

During the answer

The answer appears word by word. Depending on the task you may also see:

• Reasoning – for "thinking" models, an expandable section (Show reasoning).

• Tool steps – a live timeline, e.g. "Searching the web…", "Reading …", "Chart created".

• Charts and 3D scenes embedded directly by the model.

• Indexing progress when a large knowledge library is first prepared for search.

• Texts (artifacts) that appear as a card and open in the side editor.

Below answers that rely on documents, a Sources panel appears with the cited passages, plus a strategy badge where applicable (Full context, Retrieval, or Hybrid).

Actions on a message

Hovering over an answer reveals an action bar:

• Copy – copies the answer text.

• Read aloud – reads the answer via text-to-speech (click again to stop).

• Share – via your device's native share sheet (where available).

• Helpful / Not helpful (👍/👎) – with an optional detail dialog (category + comment). Feedback stays within your company.

• Regenerate response – re-runs the preceding question.

Your own messages are editable: via the pencil icon you change the text and re-send with Save & regenerate – the original answer (and everything after it) is replaced.

The context meter

Next to the model picker (on desktop), a small bar shows how full the context window is. Clicking it opens a breakdown by History, Documents, System, Tools, Answer, Draft, and Free. There you can also compress older history manually via Summarize now – your attachments and the most recent messages are always kept.

Managing chats

Each conversation can be organised via the action menu in the list:

• Rename (also by clicking the title at the top)

• Pin / Unpin

• Move to project / Remove from project

• Share – creates a read-only public link with a snapshot of the chat

• Delete

Use the search field (Search chats…) to find earlier conversations.

Project chats

When you move a chat into a project, it becomes visible to project members. You then additionally get:

• Presence – small avatars show who else currently has the chat open.

• Live sync – new messages from teammates appear automatically.

• Project instructions – the project's instructions flow into every answer, as do project-specific terms from the glossary.

Assistants in chat

You can attach assistants (personas) to a chat. They appear as badges in the header and can be removed there. Using @, you address a single message specifically to an assistant, which then answers with its own system prompt, model, knowledge, and tools.

Budget & limits

• Monthly budget: if your organisation has set a cap, a warning appears at 90 %; sending is blocked once it's reached.

• Rate limit: at most 30 sent messages per minute per person.

• Message length: up to 50,000 characters per message.

Deliberate limitations (as of v1)

• Per message, the last assistant mention wins when several are present.

• Web search is only available when a search provider is configured.

• PDF "seeing" works only with vision-capable models (first page).

• The context meter is shown on desktop only.

• Models under Coming soon are a preview only and not usable.