Skip to main content
Smith is Guild’s built-in support agent. It replaces the legacy dashboard as the default landing experience when you open a workspace, putting chat front and center so you can start working immediately.

​
What Smith does

Smith is always available in every workspace. You can ask it to:
  • Answer questions about Guild features, agents, and configuration
  • Help you build, debug, and publish agents
  • Walk you through setting up integrations and triggers
  • Troubleshoot errors in your sessions or agent code
  • Inspect and manage your inference provider credentials and model policies

​
Starting a conversation

When you open a workspace, Smith’s chat interface is the first thing you see. Type a message and press Enter to begin. You can also open Smith at any time from the left sidebar by clicking Smith at the top of the left nav.

​
Switching agents

Smith is the default agent, but it is not the only one. Use @mention to route a message to a different agent without leaving the chat interface. See Agent mentions.

​
Workspace context

Smith has read access to your workspace configuration — installed agents, triggers, integrations, and recent sessions — so it can give context-aware answers without you having to copy-paste configuration details.

​
Software Factory commissioning

Smith can commission a Software Factory for you, so you do not have to wire up its repository, runtimes, labels, agents, contexts, and triggers by hand. Ask Smith to build one and it runs the blueprint_software_factory skill, which drives the setup end to end. See Software Factory commissioning for how Smith does this, including its workspace variable contract, two-phase approval flow, and bounded runtime repair loop.

​
Inference provider credentials and model policies

Smith can inspect and configure the inference provider credentials and model policies on your account. It can:
  • List the credentials available to the account, along with the model publishers each one unlocks, and the account’s model policies.
  • Create, update, delete, and reorder model policies.
A model policy points a credential access — one publisher on one credential — optionally narrowed to specific models, at a target. A target is an account, a workspace, an agent, or a workspace-agent. Account, workspace, and workspace-agent targets must belong to the same account as the credential. Agent targets are catalog-level, so they can point at a visible agent owned by another account while still using the chosen account’s credential.
Smith asks before it writes. For any policy change it first reports the current state, then presents the exact change it intends to make — target, credential access, and resulting model list — and waits for your approval. Read-only questions are answered directly.
A general question such as “what is a model policy?” is answered from the documentation. A question about your own credentials or policies, or a request to change them, is answered from live account state instead.

​
Safety limits

Smith includes internal protections that stop a single conversation from looping or running up cost:
  • Unsupported integration stop. When you ask Smith to set up credentials for a service it cannot resolve to a supported integration, it stops after one discovery pass, names the unsupported service as the blocker, and does not retry.
These limits apply on top of the platform-wide execution limits.