Powered by the Smith runtime

Describe it.
Smith forges it.

Describe what you want. Smith generates the multi-agent graph, agents, tools, and routing, then deploys it live with tracing.

No SDK to learn  ·  no infrastructure to manage  ·  deploy in one click

SR Build a support copilot that triages tickets and issues refunds
SMITH live
START ORCHESTRATOR Supervisor opus 4.8 TOOL Knowledge Base SPECIALIST Billing sonnet 4.6 SPECIALIST Technical sonnet 4.6 SPECIALIST Refunds haiku 4.5 RESOLVED
smith.run/support-copilot · 1.4s p50

One conversation. The whole system designed, deployed, and traced.

THE FORGE LOOP

Five steps from a sentence to a live system

You describe the outcome. Smith handles topology, prompts, routing, and hosting, and you stay in control of every node.

01

Commission

Describe the system you want in plain language.

02

Forge

Smith generates the agent graph node by node, with routing welded in.

03

Inspect

Tune any agent's model, temperature, tools, and system prompt.

04

Deploy

One action compiles the graph and publishes a versioned live endpoint.

05

Observe

Watch real traffic flow through the graph with live traces and metrics.

THE STUDIO

Everything the build needs, in one surface

Generation, graph, inspector, deploy, and traces, all in one place. No notebook, framework, and dashboard to juggle.

Conversational generation

Describe the outcome. Smith turns it into a structured spec, picks a topology, drafts prompts, and assigns tools.

A research agent that searches the web and writes a cited report
Forging a planner, synthesizer, critic loop with web + vector tools.

Visual graph

Every system is a legible directed graph of agents, tools, and routing. Not a black box.

Node inspector

Smith suggests a model per role. Change it, plus temperature, tools, and prompt, on any node.

modelclaude-opus-4.8
temp0.2
toolsstripe, kb

One-click deploy

Compile and publish to a versioned, regional endpoint in seconds.

draft forged live
POSTsmith.run/support-copilot

Live traces

Runs, p50 latency, and success rate, streamed as traffic arrives.

run_a4f1c21.3sok
run_9bd0e71.5sok

Generated, not black-boxed

Every system is a structured spec you can read, edit, and export. Stay in the studio or take the graph with you.

{
  "system": "support-copilot",
  "nodes": [
    { "id":"supervisor", "role":"orchestrator", "model":"claude-opus-4.8" },
    { "id":"billing", "role":"specialist", "tools":["stripe","kb"] }
  ],
  "edges": [ { "from":"supervisor", "to":"billing", "type":"conditional" } ],
  "deploy": { "region":"iad1", "endpoint":"smith.run/support-copilot" }
}
ORCHESTRATION

Real topologies, not a smarter chatbot

Most tools stop at a single agent. Smith generates the orchestration: supervisors, specialists, parallel work, and feedback loops.

Supervisor + specialists

A router delegates each task to the right specialist and decides when the job is done.

Sequential pipeline

Each step hands its output to the next, in a fixed order, start to finish.

Parallel fan-out

Run independent agents at once, then aggregate their results into one answer.

Reflective loop

An agent acts, a critic checks, and the work loops until it meets the bar.

EXAMPLES

A sentence in, a system out

Real descriptions, and the multi-agent systems Smith forged from each.

WHY SMITH

LangGraph Studio, inverted

The graph is an output of a conversation, not something you assemble by hand. That makes the generated system legible, editable, runnable, and observable, all in one place.

Legible

The whole system is a graph you can see and understand, never a hidden chain.

Editable

Every agent, tool, and edge is inspectable and tunable before and after deploy.

Runnable

One action takes a draft to a live, versioned endpoint on the Smith runtime.

Observable

Live traces and metrics are built in, right where you built the system.

FAQ

Questions, answered

How is this different from LangGraph Studio or a visual builder?

Visual builders give you a blank canvas to wire agents by hand; code-first tools like LangGraph have you write the graph in code. Smith generates the multi-agent graph from your description, then lets you tune any node and deploy with tracing, in one place. The graph is an output, not a chore.

Do I need to know LangGraph or an agent framework?

No. You describe the system in plain language and Smith generates the graph. The framework details are handled for you, though developers can read and edit the underlying spec.

What actually runs the agents?

The Smith runtime compiles each generated graph into an executable agent system, hosts a versioned endpoint, and streams traces. The studio is the design surface on top of it.

Can I edit what Smith generates?

Yes. Select any agent to change its model, temperature, tools, and system prompt. The generated graph is a starting point you stay in control of.

Which models does it use?

Smith auto-assigns and suggests a model per role: stronger ones (Claude Opus) for reasoning and security, faster ones (Sonnet, Haiku) for mechanical steps. It's a suggestion, change the model on any node to fit your preference, budget, or latency.

Is it production-ready today?

Smith Studio is in early access. You can explore the full build-to-deploy loop in the live prototype now; real generation and runtime are rolling out in phases.

Stop wiring agents by hand

Describe the system you want, and watch Smith forge it into a deployable multi-agent graph.