A guided, step-by-step setup. Advanced sections are collapsed — expand only what you need.
This guided setup will walk you through configuring your Cortex agent step by step.
Give your agent a name and describe what it does.
Choose the language model that will power your agent's reasoning.
ANTHROPIC_API_KEY). Do not paste the key itself.us-east-1).llm_provider:. Use this to mix cheap/fast models with the default.Connect external tools via the Model Context Protocol. Optional — you can add these later.
Define the kinds of tasks your agent can handle. Optional — the agent can auto-discover tasks from its tools.
Where the agent keeps its state — session data, uploaded files, session history, and disk quotas.
database is locked errors under load.0600.{prefix}:…. Lets multiple agents share a Redis instance without colliding.Features that let the agent discover capabilities, improve over time, and guard its own output quality.
storage.base_path.validation_notes before they reach the user. Low-scoring waves are either flagged or rejected depending on the thresholds below.llm_access.providers used to run validation scoring. Leave as default unless you want a cheaper/faster model to judge — a typical setup is a small Haiku or Gemini Flash judging a bigger main model.Operational limits, boot-time behavior, and the surfaces that deliver the agent to end users (chat UI, code sandbox, per-user overrides).
cortex publish ui: a clean chat interface with streaming responses,
file attachments, and per-user session history. History is stored via the history
backend configured in the Storage step. File uploads are validated against the
File input MIME and size settings there.
cortex publish ui will serve the UI on the host/port below.0.0.0.0 to accept connections from any interface, 127.0.0.1 to restrict to the local machine.none assigns each browser an anonymous id so history persists per-device. token / basic gate the whole UI behind a shared credential.Authorization: Bearer <token>. Only used when auth mode is token.basic.[REDACTED] before the text leaves the process. Leave blank to use the sensible default set.storage.base_path.capability_hint: code_exec to run generated Python inside a sandboxed subprocess. Off disables all code execution regardless of task config.cortex ants hatch or the framework API.llm_access). Use default to inherit the parent's default provider.Choose how you want to deploy and run your agent.
Review your generated configuration, then save and publish.