Chat & Conversations
The Conversation mode is the core of Kognar Platform. It's a full-featured AI chat interface supporting multi-turn dialogue, file attachments, rich content rendering, and real-time tool use.
Sending messages
Type your message in the input bar at the bottom of the screen and press Enter to send. Use Shift+Enter to add a new line without sending.
While the assistant is generating a response, the Send button turns into a Stop button (red). Click it to cancel the response at any time.
Streaming responses
Responses appear in real time as the model generates them — character by character. You'll see a blinking cursor at the end of the current output while the model is still writing.
Message actions
On the last assistant message, two action buttons appear:
- Retry — Regenerates the response using the same message
- Export — Downloads the response as a
.md(Markdown) file
Context window meter
The header shows a context meter — a progress bar indicating how much of the model's context window is currently in use. As conversations grow, this meter fills up.
When the context is nearly full, Kognar will warn you before sending. You can choose to compress the conversation (reduces size while preserving meaning) or cancel.
Starting a new conversation
Use the New Chat row at the top of the sidebar or press Ctrl/Cmd+N. Conversations are automatically titled with a timestamp and can be renamed at any time. To start a conversation inside a specific project, right-click the project and choose New chat in this project.
Picking a model from the input
The AI model is selected from the bar directly below the message text, next to the Send button — not from the chat header. Open the model selector there to browse providers and models. Once you send the first message in a conversation, the model is locked (start a new conversation to pick a different one).
The selector popover opens above the rest of the conversation, so it isn't clipped by the message input.
Power Tools
The Kognar Power Tools button (slider icon) sits in the action bar below the message text, alongside the attach and microphone buttons. It opens agents, MCP servers and rules without leaving the conversation.
Private (incognito) window
On the desktop app, the shortcut to open a private window is a floating button in the top-right corner of the main area — visible whether or not the sidebar is open, and across work modes. The keyboard shortcut ⇧⌘I (macOS) still works.
Personalized greeting
When you open a new conversation (one with no messages yet), the welcome title is generated for you — using your name, the time of day, and, when you have history, optionally suggesting that you continue something from recent conversations. The greeting is fetched once per app session; if it can't be generated, the default welcome text is shown.
Quick start suggestions
Below the message input, a row of suggestion chips appears whenever the conversation is empty. Each chip has an icon and a short label, and tapping one pre-fills the input with a ready-made request:
| Chip | Pre-filled request |
|---|---|
| Write code | Help me write code |
| Summarize text | Summarize this text |
| Analyze data | Analyze this data |
| Generate ideas | Brainstorm ideas |
| Create content | Draft a piece of content |
Response metadata
Below each assistant message, Kognar shows:
- P: — Prompt tokens used
- C: — Completion tokens generated
- Latency — Response time in milliseconds
Markdown rendering
Assistant responses render full GitHub-flavored Markdown:
- Headings, bold, italic, strikethrough
- Ordered and unordered lists
- Code blocks with syntax highlighting
- Tables with borders and alternating rows
- Blockquotes
- Inline links (open in a new browser tab)
Tool execution
When an agent uses a tool (like web search or code analysis), a tool card appears in the response thread. It shows:
- The tool name and status (running / complete)
- The result returned by the tool
- Which agent invoked the tool
Tool cards are collapsible to save space.
Voice input
Click the microphone icon in the chat input bar to dictate your message instead of typing:
- Click the mic icon — recording starts immediately
- Speak your message
- Stop recording — the text is transcribed and placed in the input field
- Review and press Enter to send
See Audio Transcription for details on on-device vs. cloud transcription modes.
Web search sources
When the Web Search agent is active and returns results, a sources accordion appears below the response:
- The header shows how many sources were consulted (e.g. "4 sources")
- Click the header to expand and see the full list
- Each source shows the page title and URL
- Long URLs are truncated on screen — hover to see the full address
- Click a source to open it in your browser
If no sources were found, the accordion does not appear.
Conversation context menu
Right-click any conversation in the sidebar to access:
| Option | Description |
|---|---|
| Edit | Rename the conversation |
| Delete | Remove the conversation permanently |
| More information | View creation date, last update, model used, and estimated token usage |
In-app product help
When you ask the assistant how to use Kognar — features, settings, shortcuts, or work modes — it can pull snippets from the official documentation at docs.kognar.com to ground its answers. The guide ships bundled inside the app so it opens quickly; updates are checked at most once a day in the background. This works whether personal memory is on or off, and in private windows too.
Sound notifications
Kognar can play a sound when the assistant finishes responding. Enable or disable this in Settings > General > Preferences > Play sounds.