Skip to main content
Not every expert has every capability. Use this page as a high-level checklist.

Common Platform Integrations

PlatformTypical Actions
Google DocsCreate, read, update documents
Google SheetsRead/analyze/update spreadsheet data
Google DriveSearch files, read docs, organize content
Google CalendarRead schedule, create events
GmailDraft/search emails
Google ChatRespond in DM and group Spaces
NotionRead/update pages and databases
Custom APIs (MCP)Call external/internal services through custom connectors

Input and Output Types

TypeSupported
InputGoogle Docs/Sheets, PDFs, text files, common images, selected attachments
OutputText responses, structured summaries, links to created docs/sheets, tool-driven actions

Conversation and Collaboration

CapabilityNotes
Streaming responsesReplies appear progressively in chat
Multi-turn contextRecent context is used for follow-up questions
Group Space routing@BrainTrust routes to best-fit expert in that group Space
Multi-expert supportMultiple experts can coexist in one group Space

Automation

CapabilityNotes
Cron triggersRun tasks on schedules
Calendar triggersRun tasks based on calendar events
DM/Space deliveryTrigger output can be delivered to DM or group Space

Practical Limits

  • Tool access depends on configured credentials.
  • Behavior quality depends heavily on prompt quality.
  • Large/complex requests may take longer to complete.
  • Some capabilities are expert-specific, not global defaults.

Code Execution (Sandbox)

Experts can execute Python code in an isolated sandbox environment.
AspectDetails
LanguagePython
IsolationFully sandboxed — no access to host system
Use casesData processing, calculations, chart generation, file transformation
File handlingSandbox outputs files back to the agent filesystem; files can be exported as downloadable links
Input filesSandbox has access to input_files passed from the agent workspace
The sandbox is ideal for tasks that need computation beyond what the LLM can do inline — number crunching, data visualization, or transforming file formats.

Memory and Context

TypeHow It Works
Conversation historyRecent turns are included in context automatically. The number of turns is bounded by the session history setting.
Long-term memoryExperts use Mem0 to remember user preferences, past decisions, and context across sessions. Memory is per-user.
Knowledge base (RAG)If a Google Drive folder or knowledge base is configured, relevant documents are retrieved via semantic search and injected into context.
Long-term memory allows experts to personalize over time — remembering your preferred report format, your team’s naming conventions, or decisions from past conversations.

Next Steps

Connecting Tools and Integrations

Configure credentials and integration access.

Expert Fields Reference

See which fields influence capability behavior.

Troubleshooting

Resolve common capability and response issues.

Glossary

Learn key terms used in this page.