--- title: Human-in-the-loop patterns description: Implement human-in-the-loop functionality using Cloudflare Agents for workflow approvals and MCP elicitation image: https://developers.cloudflare.com/dev-products-preview.png --- > Documentation Index > Fetch the complete documentation index at: https://developers.cloudflare.com/agents/llms.txt > Use this file to discover all available pages before exploring further. [Skip to content](#%5Ftop) # Human-in-the-loop patterns Human-in-the-loop (HITL) patterns allow agents to pause execution and wait for human approval, confirmation, or input before proceeding. This is essential for compliance, safety, and oversight in agentic systems. ## Why human-in-the-loop? * **Compliance**: Regulatory requirements may mandate human approval for certain actions * **Safety**: High-stakes operations (payments, deletions, external communications) need oversight * **Quality**: Human review catches errors AI might miss * **Trust**: Users feel more confident when they can approve critical actions ### Common use cases | Use Case | Example | | ------------------- | ------------------------------------ | | Financial approvals | Expense reports, payment processing | | Content moderation | Publishing, email sending | | Data operations | Bulk deletions, exports | | AI tool execution | Confirming tool calls before running | | Access control | Granting permissions, role changes | ## Choosing a pattern Cloudflare provides two main patterns for human-in-the-loop: | Pattern | Best for | Key API | | --------------------- | -------------------------------------------- | ----------------- | | **Workflow approval** | Multi-step processes, durable approval gates | waitForApproval() | | **MCP elicitation** | MCP servers requesting structured user input | elicitInput() | Decision guide: * Use **Workflow approval** when you need durable, multi-step processes with approval gates that can wait hours, days, or weeks * Use **MCP elicitation** when building MCP servers that need to request additional structured input from users during tool execution ## Workflow-based approval For durable, multi-step processes, use [Cloudflare Workflows](https://developers.cloudflare.com/workflows/) with the `waitForApproval()` method. The workflow pauses until a human approves or rejects. ### Basic pattern * [ JavaScript ](#tab-panel-5573) * [ TypeScript ](#tab-panel-5574) JavaScript ``` import { Agent } from "agents";import { AgentWorkflow } from "agents/workflows"; export class ExpenseWorkflow extends AgentWorkflow { async run(event, step) { const expense = event.payload; // Step 1: Validate the expense const validated = await step.do("validate", async () => { if (expense.amount <= 0) { throw new Error("Invalid expense amount"); } return { ...expense, validatedAt: Date.now() }; }); // Step 2: Report that we are waiting for approval await this.reportProgress({ step: "approval", status: "pending", message: `Awaiting approval for $${expense.amount}`, }); // Step 3: Wait for human approval (pauses the workflow) const approval = await this.waitForApproval(step, { timeout: "7 days", }); console.log(`Approved by: ${approval?.approvedBy}`); // Step 4: Process the approved expense const result = await step.do("process", async () => { return { expenseId: crypto.randomUUID(), ...validated }; }); await step.reportComplete(result); return result; }} ``` TypeScript ``` import { Agent } from "agents";import { AgentWorkflow } from "agents/workflows";import type { AgentWorkflowEvent, AgentWorkflowStep } from "agents/workflows"; type ExpenseParams = { amount: number; description: string; requestedBy: string;}; export class ExpenseWorkflow extends AgentWorkflow< ExpenseAgent, ExpenseParams> { async run(event: AgentWorkflowEvent, step: AgentWorkflowStep) { const expense = event.payload; // Step 1: Validate the expense const validated = await step.do("validate", async () => { if (expense.amount <= 0) { throw new Error("Invalid expense amount"); } return { ...expense, validatedAt: Date.now() }; }); // Step 2: Report that we are waiting for approval await this.reportProgress({ step: "approval", status: "pending", message: `Awaiting approval for $${expense.amount}`, }); // Step 3: Wait for human approval (pauses the workflow) const approval = await this.waitForApproval<{ approvedBy: string }>(step, { timeout: "7 days", }); console.log(`Approved by: ${approval?.approvedBy}`); // Step 4: Process the approved expense const result = await step.do("process", async () => { return { expenseId: crypto.randomUUID(), ...validated }; }); await step.reportComplete(result); return result; }} ``` ### Agent methods for approval The agent provides methods to approve or reject waiting workflows: * [ JavaScript ](#tab-panel-5577) * [ TypeScript ](#tab-panel-5578) JavaScript ``` import { Agent, callable } from "agents"; export class ExpenseAgent extends Agent { initialState = { pendingApprovals: [], }; // Approve a waiting workflow @callable() async approve(workflowId, approvedBy) { await this.approveWorkflow(workflowId, { reason: "Expense approved", metadata: { approvedBy, approvedAt: Date.now() }, }); // Update state to reflect approval this.setState({ ...this.state, pendingApprovals: this.state.pendingApprovals.filter( (p) => p.workflowId !== workflowId, ), }); } // Reject a waiting workflow @callable() async reject(workflowId, reason) { await this.rejectWorkflow(workflowId, { reason }); this.setState({ ...this.state, pendingApprovals: this.state.pendingApprovals.filter( (p) => p.workflowId !== workflowId, ), }); } // Track workflow progress to update pending approvals async onWorkflowProgress(workflowName, workflowId, progress) { const p = progress; if (p.step === "approval" && p.status === "pending") { // Add to pending approvals list for UI display this.setState({ ...this.state, pendingApprovals: [ ...this.state.pendingApprovals, { workflowId, amount: 0, // Would come from workflow params description: p.message || "", requestedBy: "user", requestedAt: Date.now(), }, ], }); } }} ``` TypeScript ``` import { Agent, callable } from "agents"; type PendingApproval = { workflowId: string; amount: number; description: string; requestedBy: string; requestedAt: number;}; type ExpenseState = { pendingApprovals: PendingApproval[];}; export class ExpenseAgent extends Agent { initialState: ExpenseState = { pendingApprovals: [], }; // Approve a waiting workflow @callable() async approve(workflowId: string, approvedBy: string): Promise { await this.approveWorkflow(workflowId, { reason: "Expense approved", metadata: { approvedBy, approvedAt: Date.now() }, }); // Update state to reflect approval this.setState({ ...this.state, pendingApprovals: this.state.pendingApprovals.filter( (p) => p.workflowId !== workflowId, ), }); } // Reject a waiting workflow @callable() async reject(workflowId: string, reason: string): Promise { await this.rejectWorkflow(workflowId, { reason }); this.setState({ ...this.state, pendingApprovals: this.state.pendingApprovals.filter( (p) => p.workflowId !== workflowId, ), }); } // Track workflow progress to update pending approvals async onWorkflowProgress( workflowName: string, workflowId: string, progress: unknown, ): Promise { const p = progress as { step: string; status: string; message?: string }; if (p.step === "approval" && p.status === "pending") { // Add to pending approvals list for UI display this.setState({ ...this.state, pendingApprovals: [ ...this.state.pendingApprovals, { workflowId, amount: 0, // Would come from workflow params description: p.message || "", requestedBy: "user", requestedAt: Date.now(), }, ], }); } }} ``` ### Timeout handling Set timeouts to prevent workflows from waiting indefinitely: * [ JavaScript ](#tab-panel-5567) * [ TypeScript ](#tab-panel-5568) JavaScript ``` const approval = await this.waitForApproval(step, { timeout: "7 days", // Also supports: "1 hour", "30 minutes", etc.}); if (!approval) { // Timeout expired - escalate or auto-reject await step.reportError("Approval timeout - escalating to manager"); throw new Error("Approval timeout");} ``` TypeScript ``` const approval = await this.waitForApproval<{ approvedBy: string }>(step, { timeout: "7 days", // Also supports: "1 hour", "30 minutes", etc.}); if (!approval) { // Timeout expired - escalate or auto-reject await step.reportError("Approval timeout - escalating to manager"); throw new Error("Approval timeout");} ``` ### Escalation with scheduling Use `schedule()` to set up escalation reminders: * [ JavaScript ](#tab-panel-5569) * [ TypeScript ](#tab-panel-5570) JavaScript ``` import { Agent, callable } from "agents"; class ExpenseAgent extends Agent { @callable() async submitForApproval(expense) { // Start the approval workflow const workflowId = await this.runWorkflow("EXPENSE_WORKFLOW", expense); // Schedule reminder after 4 hours await this.schedule(Date.now() + 4 * 60 * 60 * 1000, "sendReminder", { workflowId, }); // Schedule escalation after 24 hours await this.schedule(Date.now() + 24 * 60 * 60 * 1000, "escalateApproval", { workflowId, }); return workflowId; } async sendReminder(payload) { const workflow = this.getWorkflow(payload.workflowId); if (workflow?.status === "waiting") { // Send reminder notification console.log("Reminder: approval still pending"); } } async escalateApproval(payload) { const workflow = this.getWorkflow(payload.workflowId); if (workflow?.status === "waiting") { // Escalate to manager console.log("Escalating to manager"); } }} ``` TypeScript ``` import { Agent, callable } from "agents"; class ExpenseAgent extends Agent { @callable() async submitForApproval(expense: ExpenseParams): Promise { // Start the approval workflow const workflowId = await this.runWorkflow("EXPENSE_WORKFLOW", expense); // Schedule reminder after 4 hours await this.schedule(Date.now() + 4 * 60 * 60 * 1000, "sendReminder", { workflowId, }); // Schedule escalation after 24 hours await this.schedule(Date.now() + 24 * 60 * 60 * 1000, "escalateApproval", { workflowId, }); return workflowId; } async sendReminder(payload: { workflowId: string }) { const workflow = this.getWorkflow(payload.workflowId); if (workflow?.status === "waiting") { // Send reminder notification console.log("Reminder: approval still pending"); } } async escalateApproval(payload: { workflowId: string }) { const workflow = this.getWorkflow(payload.workflowId); if (workflow?.status === "waiting") { // Escalate to manager console.log("Escalating to manager"); } }} ``` ### Audit trail with SQL Use `this.sql` to maintain an immutable audit trail: * [ JavaScript ](#tab-panel-5571) * [ TypeScript ](#tab-panel-5572) JavaScript ``` import { Agent, callable } from "agents"; class ExpenseAgent extends Agent { async onStart() { // Create audit table this.sql` CREATE TABLE IF NOT EXISTS approval_audit ( id INTEGER PRIMARY KEY AUTOINCREMENT, workflow_id TEXT NOT NULL, decision TEXT NOT NULL CHECK(decision IN ('approved', 'rejected')), decided_by TEXT NOT NULL, decided_at INTEGER NOT NULL, reason TEXT ) `; } @callable() async approve(workflowId, userId, reason) { // Record the decision in SQL (immutable audit log) this.sql` INSERT INTO approval_audit (workflow_id, decision, decided_by, decided_at, reason) VALUES (${workflowId}, 'approved', ${userId}, ${Date.now()}, ${reason || null}) `; // Process the approval await this.approveWorkflow(workflowId, { reason: reason || "Approved", metadata: { approvedBy: userId }, }); }} ``` TypeScript ``` import { Agent, callable } from "agents"; class ExpenseAgent extends Agent { async onStart() { // Create audit table this.sql` CREATE TABLE IF NOT EXISTS approval_audit ( id INTEGER PRIMARY KEY AUTOINCREMENT, workflow_id TEXT NOT NULL, decision TEXT NOT NULL CHECK(decision IN ('approved', 'rejected')), decided_by TEXT NOT NULL, decided_at INTEGER NOT NULL, reason TEXT ) `; } @callable() async approve( workflowId: string, userId: string, reason?: string, ): Promise { // Record the decision in SQL (immutable audit log) this.sql` INSERT INTO approval_audit (workflow_id, decision, decided_by, decided_at, reason) VALUES (${workflowId}, 'approved', ${userId}, ${Date.now()}, ${reason || null}) `; // Process the approval await this.approveWorkflow(workflowId, { reason: reason || "Approved", metadata: { approvedBy: userId }, }); }} ``` ### Configuration * [ wrangler.jsonc ](#tab-panel-5565) * [ wrangler.toml ](#tab-panel-5566) JSONC ``` { "name": "expense-approval", "main": "src/index.ts", // Set this to today's date "compatibility_date": "2026-06-30", "compatibility_flags": ["nodejs_compat"], "durable_objects": { "bindings": [{ "name": "EXPENSE_AGENT", "class_name": "ExpenseAgent" }], }, "workflows": [ { "name": "expense-workflow", "binding": "EXPENSE_WORKFLOW", "class_name": "ExpenseWorkflow", }, ], "migrations": [{ "tag": "v1", "new_sqlite_classes": ["ExpenseAgent"] }],} ``` TOML ``` name = "expense-approval"main = "src/index.ts"# Set this to today's datecompatibility_date = "2026-06-30"compatibility_flags = [ "nodejs_compat" ] [[durable_objects.bindings]]name = "EXPENSE_AGENT"class_name = "ExpenseAgent" [[workflows]]name = "expense-workflow"binding = "EXPENSE_WORKFLOW"class_name = "ExpenseWorkflow" [[migrations]]tag = "v1"new_sqlite_classes = [ "ExpenseAgent" ] ``` ## MCP elicitation When building MCP servers with `McpAgent`, you can request additional user input during tool execution using **elicitation**. The MCP client renders a form based on your JSON Schema and returns the user's response. ### Basic pattern * [ JavaScript ](#tab-panel-5579) * [ TypeScript ](#tab-panel-5580) JavaScript ``` import { McpAgent } from "agents/mcp";import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";import { z } from "zod"; export class CounterMCP extends McpAgent { server = new McpServer({ name: "counter-server", version: "1.0.0", }); initialState = { counter: 0 }; async init() { this.server.tool( "increase-counter", "Increase the counter by a user-specified amount", { confirm: z.boolean().describe("Do you want to increase the counter?") }, async ({ confirm }, extra) => { if (!confirm) { return { content: [{ type: "text", text: "Cancelled." }] }; } // Request additional input from the user const userInput = await this.server.server.elicitInput( { message: "By how much do you want to increase the counter?", requestedSchema: { type: "object", properties: { amount: { type: "number", title: "Amount", description: "The amount to increase the counter by", }, }, required: ["amount"], }, }, { relatedRequestId: extra.requestId }, ); // Check if user accepted or cancelled if (userInput.action !== "accept" || !userInput.content) { return { content: [{ type: "text", text: "Cancelled." }] }; } // Use the input const amount = Number(userInput.content.amount); this.setState({ ...this.state, counter: this.state.counter + amount, }); return { content: [ { type: "text", text: `Counter increased by ${amount}, now at ${this.state.counter}`, }, ], }; }, ); }} ``` TypeScript ``` import { McpAgent } from "agents/mcp";import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";import { z } from "zod"; type State = { counter: number }; export class CounterMCP extends McpAgent { server = new McpServer({ name: "counter-server", version: "1.0.0", }); initialState: State = { counter: 0 }; async init() { this.server.tool( "increase-counter", "Increase the counter by a user-specified amount", { confirm: z.boolean().describe("Do you want to increase the counter?") }, async ({ confirm }, extra) => { if (!confirm) { return { content: [{ type: "text", text: "Cancelled." }] }; } // Request additional input from the user const userInput = await this.server.server.elicitInput( { message: "By how much do you want to increase the counter?", requestedSchema: { type: "object", properties: { amount: { type: "number", title: "Amount", description: "The amount to increase the counter by", }, }, required: ["amount"], }, }, { relatedRequestId: extra.requestId }, ); // Check if user accepted or cancelled if (userInput.action !== "accept" || !userInput.content) { return { content: [{ type: "text", text: "Cancelled." }] }; } // Use the input const amount = Number(userInput.content.amount); this.setState({ ...this.state, counter: this.state.counter + amount, }); return { content: [ { type: "text", text: `Counter increased by ${amount}, now at ${this.state.counter}`, }, ], }; }, ); }} ``` ## Elicitation vs workflow approval | Aspect | MCP Elicitation | Workflow Approval | | ------------ | ----------------------------- | ----------------------------- | | **Context** | MCP server tool execution | Multi-step workflow processes | | **Duration** | Immediate (within tool call) | Can wait hours/days/weeks | | **UI** | JSON Schema-based form | Custom UI via agent state | | **State** | MCP session state | Durable workflow state | | **Use case** | Interactive input during tool | Approval gates in pipelines | ## Building approval UIs ### Pending approvals list Use the agent's state to display pending approvals in your UI: ``` import { useAgent } from "agents/react"; function PendingApprovals() { const { state, agent } = useAgent({ agent: "expense-agent", name: "main", }); if (!state?.pendingApprovals?.length) { return

No pending approvals

; } return (
{state.pendingApprovals.map((item) => (

${item.amount}

{item.description}

Requested by {item.requestedBy}

))}
);} ``` ## Multi-approver patterns For sensitive operations requiring multiple approvers: * [ JavaScript ](#tab-panel-5575) * [ TypeScript ](#tab-panel-5576) JavaScript ``` import { Agent, callable } from "agents"; class MultiApprovalAgent extends Agent { @callable() async approveMulti(workflowId, userId) { const approval = this.state.pendingMultiApprovals.find( (p) => p.workflowId === workflowId, ); if (!approval) throw new Error("Approval not found"); // Check if user already approved if (approval.currentApprovals.some((a) => a.userId === userId)) { throw new Error("Already approved by this user"); } // Add this user's approval approval.currentApprovals.push({ userId, approvedAt: Date.now() }); // Check if we have enough approvals if (approval.currentApprovals.length >= approval.requiredApprovals) { // Execute the approved action await this.approveWorkflow(workflowId, { metadata: { approvers: approval.currentApprovals }, }); return true; } this.setState({ ...this.state }); return false; // Still waiting for more approvals }} ``` TypeScript ``` import { Agent, callable } from "agents"; type MultiApproval = { workflowId: string; requiredApprovals: number; currentApprovals: Array<{ userId: string; approvedAt: number }>; rejections: Array<{ userId: string; rejectedAt: number; reason: string }>;}; type State = { pendingMultiApprovals: MultiApproval[];}; class MultiApprovalAgent extends Agent { @callable() async approveMulti(workflowId: string, userId: string): Promise { const approval = this.state.pendingMultiApprovals.find( (p) => p.workflowId === workflowId, ); if (!approval) throw new Error("Approval not found"); // Check if user already approved if (approval.currentApprovals.some((a) => a.userId === userId)) { throw new Error("Already approved by this user"); } // Add this user's approval approval.currentApprovals.push({ userId, approvedAt: Date.now() }); // Check if we have enough approvals if (approval.currentApprovals.length >= approval.requiredApprovals) { // Execute the approved action await this.approveWorkflow(workflowId, { metadata: { approvers: approval.currentApprovals }, }); return true; } this.setState({ ...this.state }); return false; // Still waiting for more approvals }} ``` ## Best practices 1. **Define clear approval criteria** — Only require confirmation for actions with meaningful consequences (payments, emails, data changes) 2. **Provide detailed context** — Show users exactly what the action will do, including all arguments 3. **Implement timeouts** — Use `schedule()` to escalate or auto-reject after reasonable periods 4. **Maintain audit trails** — Use `this.sql` to record all approval decisions for compliance 5. **Handle connection drops** — Store pending approvals in agent state so they survive disconnections 6. **Graceful degradation** — Provide fallback behavior if approvals are rejected ## Next steps [ Run Workflows ](https://developers.cloudflare.com/agents/runtime/execution/run-workflows/) Complete waitForApproval() API reference. [ MCP servers ](https://developers.cloudflare.com/agents/model-context-protocol/apis/agent-api/) Build MCP agents with elicitation. [ Email notifications ](https://developers.cloudflare.com/email-service/api/send-emails/workers-api/) Send notifications for pending approvals. [ Schedule tasks ](https://developers.cloudflare.com/agents/runtime/execution/schedule-tasks/) Implement approval timeouts with schedules. ```json {"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/agents/concepts/agentic-patterns/human-in-the-loop/#page","headline":"Human-in-the-loop patterns · Cloudflare Agents docs","description":"Implement human-in-the-loop functionality using Cloudflare Agents for workflow approvals and MCP elicitation","url":"https://developers.cloudflare.com/agents/concepts/agentic-patterns/human-in-the-loop/","inLanguage":"en","image":"https://developers.cloudflare.com/dev-products-preview.png","dateModified":"2026-06-09","publisher":{"@type":"Organization","name":"Cloudflare","url":"https://www.cloudflare.com/"},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"item":{"@id":"/directory/","name":"Directory"}},{"@type":"ListItem","position":2,"item":{"@id":"/agents/","name":"Agents"}},{"@type":"ListItem","position":3,"item":{"@id":"/agents/concepts/","name":"Concepts"}},{"@type":"ListItem","position":4,"item":{"@id":"/agents/concepts/agentic-patterns/","name":"Agentic patterns"}},{"@type":"ListItem","position":5,"item":{"@id":"/agents/concepts/agentic-patterns/human-in-the-loop/","name":"Human-in-the-loop patterns"}}]} ```