Agent Config

Forward typed configuration from your UI into the agent's reasoning loop.

Agent Config Object

Waking up the demo

You have a working agent and want the user to be able to tune how it behaves: tone, expertise level, response length, language, persona. By the end of this guide, your UI will own a typed config object that the agent reads on every run and rebuilds its system prompt from.

When to use this

Reach for agent config whenever the agent's behaviour depends on user-controllable settings that don't fit naturally as chat input:

  • Tone, voice, persona: "playful", "formal", "casual"
  • Expertise level: "beginner", "intermediate", "expert"
  • Response shape: short / medium / long, structured / prose, language
  • Domain switches: which knowledge base to consult, which tool subset to enable

If the values are a channel the user occasionally tunes (a settings panel, a toolbar of selects), agent config is the right shape. If the values are content the agent should write back to (notes, a document, a plan), use Shared State instead.

How agent config flows from the UI into the agent's reasoning loop depends on your runtime architecture. Most agents read the config from the context that the UI publishes with useAgentContext. The Built-in Agent reads it from input.forwardedProps, which the UI sets with the properties prop on <CopilotKit>.

How it works

Make runtime configuration explicit

The Claude Agent SDK demo reads configuration from shared state and folds it into the system prompt. This keeps the agent behavior visible to the UI and lets users tune model behavior without rebuilding the backend.

agent-config-prompt.ts
export type Tone = "professional" | "casual" | "enthusiastic";
export type Expertise = "beginner" | "intermediate" | "expert";
export type ResponseLength = "concise" | "detailed";

const DEFAULT_TONE: Tone = "professional";
const DEFAULT_EXPERTISE: Expertise = "intermediate";
const DEFAULT_RESPONSE_LENGTH: ResponseLength = "concise";

const VALID_TONES: ReadonlySet<string> = new Set<Tone>([
  "professional",
  "casual",
  "enthusiastic",
]);
const VALID_EXPERTISE: ReadonlySet<string> = new Set<Expertise>([
  "beginner",
  "intermediate",
  "expert",
]);
const VALID_RESPONSE_LENGTHS: ReadonlySet<string> = new Set<ResponseLength>([
  "concise",
  "detailed",
]);

const TONE_RULES: Record<Tone, string> = {
  professional: "Use neutral, precise language. No emoji. Short sentences.",
  casual:
    "Use friendly, conversational language. Contractions OK. Light humor welcome.",
  enthusiastic:
    "Use upbeat, energetic language. Exclamation points OK. Emoji OK.",
};

const EXPERTISE_RULES: Record<Expertise, string> = {
  beginner: "Assume no prior knowledge. Define jargon. Use analogies.",
  intermediate:
    "Assume common terms are understood; explain specialized terms.",
  expert: "Assume technical fluency. Use precise terminology. Skip basics.",
};

const LENGTH_RULES: Record<ResponseLength, string> = {
  concise: "Respond in 1-3 sentences.",
  detailed: "Respond in multiple paragraphs with examples where relevant.",
};

function readString(value: unknown): string | undefined {
  return typeof value === "string" ? value : undefined;
}

export function buildAgentConfigSystemPrompt(
  forwardedProps: Record<string, unknown>,
): string {
  const rawTone = readString(forwardedProps.tone) ?? DEFAULT_TONE;
  const rawExpertise =
    readString(forwardedProps.expertise) ?? DEFAULT_EXPERTISE;
  const rawLength =
    readString(forwardedProps.responseLength) ?? DEFAULT_RESPONSE_LENGTH;

  const tone = (VALID_TONES.has(rawTone) ? rawTone : DEFAULT_TONE) as Tone;
  const expertise = (
    VALID_EXPERTISE.has(rawExpertise) ? rawExpertise : DEFAULT_EXPERTISE
  ) as Expertise;
  const responseLength = (
    VALID_RESPONSE_LENGTHS.has(rawLength) ? rawLength : DEFAULT_RESPONSE_LENGTH
  ) as ResponseLength;

  return [
    "You are a helpful assistant.",
    "",
    `Tone: ${TONE_RULES[tone]}`,
    `Expertise level: ${EXPERTISE_RULES[expertise]}`,
    `Response length: ${LENGTH_RULES[responseLength]}`,
  ].join("\n");
}

export const AGENT_CONFIG_DEFAULT_SYSTEM_PROMPT = buildAgentConfigSystemPrompt(
  {},
);

Agent config is a typed object the frontend owns and publishes to the agent as runtime context. The backend reads that context entry and turns it into a system prompt.

The framework setup above shows the exact backend bridge for the selected agent. In every framework, the flow is the same: read the latest valid context from the current run and use it to build the system prompt for that turn.

Backend flow
config = latestValidConfig(currentRun.context)
systemPrompt = buildSystemPrompt(config)
model.invoke(systemPrompt, currentUserRequest)

At the start of every turn, the agent reads the latest config. Then it rebuilds the system prompt and runs the turn.

Change the tone in your UI and send a message. The next reply uses the new tone.

How is this guide?