Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.bland.ai/llms.txt

Use this file to discover all available pages before exploring further.

An interactive AI-powered development REPL for building phone agents. Powered by Claude. Streams responses, executes tools, edits pathways, and pushes to production without leaving your terminal. 
bland dev

​
Options

bland dev                      # Launch the dev terminal
  -m, --model <model>          #   Claude model (default: claude-opus-4-6)
  -t, --max-tokens <n>         #   Max output tokens per response
  -k, --key <key>              #   Claude API key
  --no-banner                  #   Skip ASCII banner

​
Slash Commands

CommandDescription
/helpShow available commands
/statusShow session status
/modelList models or switch (/model claude-sonnet-4-6)
/tokensView or set max output tokens (/tokens 64000 or /tokens max)
/keyUpdate Claude API key
/clearClear conversation history
/exitExit

​
Available Models

ModelMax OutputContext
claude-opus-4-6128k1M
claude-sonnet-4-664k1M
claude-haiku-4-5-2025100164k200k
claude-opus-4-2025051432k200k
claude-sonnet-4-2025051464k200k

​
Capabilities

The dev terminal has access to all MCP tools plus local pathway operations (read, write, diff, push, pull). Type / then Tab to autocomplete commands, or just type naturally. The terminal includes the built-in guide system, so the AI understands how to write good phone prompts, structure pathways, configure tools, and test effectively.

​
Built-in Guides

The CLI ships with guides designed to give LLMs the context they need to build good pathways, not just call the API, but actually understand how phone conversations work. 
bland guide                  # List all guides
bland guide phone-tone       # Writing natural phone prompts
bland guide pathways         # Node/edge architecture and execution model
bland guide tools            # Webhook and custom tools on nodes
bland guide testing          # Chat, simulate, node tests
bland guide variables        # Extracting and using caller data
GuideWhat it teaches
phone-toneHow to write prompts that sound like a real person on the phone, not a chatbot. Covers back-channeling, brevity, empathy, and topic transitions.
pathwaysHow the conversation graph works: nodes, edges, global nodes, variables, the global prompt, and the execution model.
toolsAttaching webhook and custom tools to nodes for real-time data. Covers speech, behavior, and response_data.
testingThe full testing workflow: pathway chat for interactive testing, simulate for end-to-end AI personas, node-test for stress-testing individual nodes.
variablesExtracting structured data from natural conversation with extract_variables, using {{curly_braces}} in prompts, and spelling_precision for names/emails.