Chats
A chat is one piece of work. Everything in it shares context: the system you described, the assumptions you corrected, the files you attached, the results that came back. That is why the second question in a chat is cheap to ask and a new chat has to be told everything again.
One chat per task, not per day
Start a new chat when the subject changes. A chat that has been a beam, then a slab, then a question about credits carries all of it into every later answer, which costs tokens and gives the model three subjects to confuse.
Example: you finished a purlin check and now want to look at the bracing. New chat. You want the same purlin in S355 instead of S235? Same chat, one sentence.
How much context goes into the next answer
CALC selects conversation context automatically. There is no fixed user setting such as "10 turns". The latest completed messages go first. If the content becomes too large for the selected model's context window, the oldest messages are left out of that request. The latest exchange is retained.
This trimming applies only to the individual model request. It does not delete messages from the chat. You can still read and search older content or add it to a report.
Example: early in a long chat, you explained a load assumption. Many large tool results later, that explanation no longer fits in the next model request. Repeat the decisive assumption in a new message if it must still govern the next check.
Finding one again
The sidebar lists your chats newest first, grouped by date, and the search above the list matches titles and message text. Chats are titled automatically from the first exchange, so the list stays readable without you naming anything.
A separate short background call creates the title. CALC prefers the cheapest configured model with low latency. The current order is GLM-4.7-Flash, GPT-5.6 Luna, DeepSeek V4 Flash and Claude Haiku 4.5. This choice does not change the model that answers your actual question. If the call fails, a shortened first line of your message is used as the title.
Rename a chat that you will come back to. Search finds text, but a list of eight chats called "Steel beam check" is a list you have to open one by one.
How long they are kept
Retention is part of the plan, and it is the one limit that removes work rather than blocking it:
| Plan | Chat history kept |
|---|---|
| Free | 30 days |
| Starter | 90 days |
| Professional and Enterprise | kept |
On Free and Starter a chat older than the window is deleted, not archived. Export anything you need to keep as a report before it ages out.
What a chat can see
The conversation, the files you attached to it, and whatever the tools looked up during it. Not your other chats, not a colleague's chats, and nothing on your machine that you did not attach or expose through the Dlubal-Connector.
This is worth knowing when an answer seems to have forgotten something: if it happened in a different chat, it did not happen as far as this one is concerned.
Sharing
A chat can be shared as a read-only link from its menu in the sidebar. The reader sees the conversation and its results without an account of their own.
A share link is a link: whoever holds it can open it. Treat it like sending the PDF, not like granting access to your project.
Where to go next
- Projects to group chats and fill the report cover page.
- Reports to turn a chat into a document.
- Plans and credits for the retention and limit table.