Chat
Conversational interface for talking to agents and running workflows from natural language.
Chat is Bifrost’s conversational entry point. Users send a message, the assistant picks the right tools (the workflows you’ve exposed) and produces a response, and the entire turn is captured as a run you can audit and tune later.
Each conversation belongs to one user, and its full history is preserved across turns. A conversation can be driven by a specific agent — the same agent that powers an autonomous run — or be agentless, where the assistant draws on every tool you’ve made available. The sidebar lists recent conversations; selecting one reopens its complete transcript.
Tool calls render inline as the assistant makes them, so you can see exactly which workflow ran, with what arguments, and what it returned. Platform admins also see per-conversation token counts and an estimated cost in the header.
Governed model choices
Section titled “Governed model choices”Chat exposes administrator-defined choices such as Fast, Balanced, and Pro instead of provider model IDs. Platform admins decide which model backs each tier in Settings → AI Configuration, can rename the labels, and can hide optional tiers by leaving their model blank. Users get a meaningful choice without needing to understand the provider catalog.
File attachments
Section titled “File attachments”Attach up to five images, PDFs, CSVs, JSON/YAML documents, Markdown files, or other text files to a message. Each file can be up to 25 MB, and a conversation can hold up to 500 MB. You can also paste or drag files into the composer.
Bifrost sends images and PDFs to models that support binary input. Text files are extracted into bounded text context; CSV previews include the first rows so a large export does not consume the entire context window. Attachments stay bound to their conversation and can be previewed or downloaded from the message.
Private memory
Section titled “Private memory”When an administrator enables memory and a user opts in, Bifrost-connected assistants can retrieve durable context saved for that user. Memories are private to the account and remain reviewable and removable under User Settings → Preferences. See Manage AI memory and instructions for the controls and instruction order.