Has any one ever used Strands – the AI Agent SDK by AWS

AWS has released Strands, an open-source AI agent SDK for building production agents, available via pip and npm. The SDK includes tools, hooks, and MCP server integrations for coding agents like Claude and Cursor. Strands supports Python and JavaScript, with features such as tool cancellation and source citation enforcement.

The open source toolkit for buildingproduction agents. pip install strands-agents npm install @strands-agents/sdk python from strands import Agent, tool from strands.hooks import BeforeToolCallEvent from pathlib import Path @tool def save report title: str, content: str - str: """Save a research report to disk.""" path = f"reports/{title}.md" Path path .write text content return f"Saved {path}" def require sources event: BeforeToolCallEvent : name = event.tool use "name" inp = str event.tool use "input" if name == "save report" and " source " not in inp: event.cancel tool = "Add source citations." agent = Agent tools= save report , hooks= require sources , agent "Research AI agent frameworks" python from strands import Agent, tool from strands.hooks import BeforeToolCallEvent from pathlib import Path @tool def save report title: str, content: str - str: """Save a research report to disk.""" path = f"reports/{title}.md" Path path .write text content return f"Saved {path}" def require sources event: BeforeToolCallEvent : name = event.tool use "name" inp = str event.tool use "input" if name == "save report" and " source " not in inp: event.cancel tool = "Add source citations." agent = Agent tools= save report , hooks= require sources , agent "Research AI agent frameworks" js import { Agent, tool, BeforeToolCallEvent } from '@strands-agents/sdk' import z from 'zod' import { writeFileSync } from 'fs' const saveReport = tool { name: 'save report', description: 'Save a research report.', inputSchema: z.object { title: z.string , content: z.string , } , callback: { title, content } = { writeFileSync reports/${title}.md , content return Saved ${title}.md }, } const agent = new Agent { tools: saveReport } agent.addHook BeforeToolCallEvent, event = { const inp = String event.toolUse.input if event.toolUse.name === 'save report' { if inp.includes ' source ' { event.cancel = 'Add source citations.' } } } await agent.invoke 'Research AI agent frameworks' js import { Agent, tool, BeforeToolCallEvent } from '@strands-agents/sdk' import z from 'zod' import { writeFileSync } from 'fs' const saveReport = tool { name: 'save report', description: 'Save a research report.', inputSchema: z.object { title: z.string , content: z.string , } , callback: { title, content } = { writeFileSync reports/${title}.md , content return Saved ${title}.md }, } const agent = new Agent { tools: saveReport } agent.addHook BeforeToolCallEvent, event = { const inp = String event.toolUse.input if event.toolUse.name === 'save report' { if inp.includes ' source ' { event.cancel = 'Add source citations.' } } } await agent.invoke 'Research AI agent frameworks' Set up with your coding agent Run in your terminal: claude mcp add strands uvx strands-agents-mcp-server claude mcp add strands uvx strands-agents-mcp-server Add to ~/.cursor/mcp.json: { "mcpServers": { "strands-agents": { "command": "uvx", "args": "strands-agents-mcp-server" } } } { "mcpServers": { "strands-agents": { "command": "uvx", "args": "strands-agents-mcp-server" } } } Add to ~/.kiro/settings/mcp.json: { "mcpServers": { "strands-agents": { "command": "uvx", "args": "strands-agents-mcp-server" , "disabled": false, "autoApprove": "search docs", "fetch doc" } } } { "mcpServers": { "strands-agents": { "command": "uvx", "args": "strands-agents-mcp-server" , "disabled": false, "autoApprove": "search docs", "fetch doc" } } } Add to your mcp.json: { "servers": { "strands-agents": { "command": "uvx", "args": "strands-agents-mcp-server" } } } { "servers": { "strands-agents": { "command": "uvx", "args": "strands-agents-mcp-server" } } } Or paste this prompt: Build your way Any model, any cloud. You get context management, execution limits, and observability before you write a line of config. Swap backends when you scale. Your code stays the same. python from strands import Agent, tool @tool def search logs query: str, hours: int = 24 - list: """Search application logs by keyword.""" return log api.search query, hours agent = Agent tools= search logs , agent "Find all timeout errors from the last 6 hours" python from strands import Agent, tool @tool def search logs query: str, hours: int = 24 - list: """Search application logs by keyword.""" return log api.search query, hours agent = Agent tools= search logs , agent "Find all timeout errors from the last 6 hours" python import { Agent, tool } from '@strands-agents/sdk' import z from 'zod' const searchLogs = tool { name: 'search logs', description: 'Search logs by keyword.', inputSchema: z.object { query: z.string , hours: z.number .default 24 , } , callback: { query, hours } = logApi.search query, hours , } const agent = new Agent { tools: searchLogs } await agent.invoke 'Find all timeout errors from the last 6 hours' python import { Agent, tool } from '@strands-agents/sdk' import z from 'zod' const searchLogs = tool { name: 'search logs', description: 'Search logs by keyword.', inputSchema: z.object { query: z.string , hours: z.number .default 24 , } , callback: { query, hours } = logApi.search query, hours , } const agent = new Agent { tools: searchLogs } await agent.invoke 'Find all timeout errors from the last 6 hours' Progressive complexity. Zero lock-in. python from strands.agent import SummarizingConversationManager Same agent, now with summarization. agent = Agent tools= search logs , conversation manager=SummarizingConversationManager , python from strands.agent import SummarizingConversationManager Same agent, now with summarization. agent = Agent tools= search logs , conversation manager=SummarizingConversationManager , js import { SummarizingConversationManager, } from '@strands-agents/sdk' // Same agent, now with summarization. const agent = new Agent { tools: searchLogs , conversationManager: new SummarizingConversationManager , } js import { SummarizingConversationManager, } from '@strands-agents/sdk' // Same agent, now with summarization. const agent = new Agent { tools: searchLogs , conversationManager: new SummarizingConversationManager , } Stay in control Monitor, modify, and debug with hooks. The agent loop traces every decision by default. Hooks let you intercept any step to log it, validate it, or redirect it. python from strands import Agent from strands.hooks import AfterToolCallEvent def log tool calls event: AfterToolCallEvent : """Log every tool call.""" print f"Tool: {event.tool use 'name' }" print f"Result: {event.result 'status' }" agent = Agent tools= search logs, query database , hooks= log tool calls , trace attributes={ "service": "ops-agent", "env": "production", }, python from strands import Agent from strands.hooks import AfterToolCallEvent def log tool calls event: AfterToolCallEvent : """Log every tool call.""" print f"Tool: {event.tool use 'name' }" print f"Result: {event.result 'status' }" agent = Agent tools= search logs, query database , hooks= log tool calls , trace attributes={ "service": "ops-agent", "env": "production", }, js import { Agent, AfterToolCallEvent, } from '@strands-agents/sdk' const agent = new Agent { tools: searchLogs, queryDatabase , traceAttributes: { service: 'ops-agent', env: 'production', }, } agent.addHook AfterToolCallEvent, event = { console.log Tool: ${event.toolUse.name} console.log Status: ${event.result.status} } js import { Agent, AfterToolCallEvent, } from '@strands-agents/sdk' const agent = new Agent { tools: searchLogs, queryDatabase , traceAttributes: { service: 'ops-agent', env: 'production', }, } agent.addHook AfterToolCallEvent, event = { console.log Tool: ${event.toolUse.name} console.log Status: ${event.result.status} } Built-in observability. Deliver outcomes that work Guardrails catch mistakes before they run. python from strands import Agent from strands.hooks import BeforeToolCallEvent WRITE OPS = "INSERT", "UPDATE", "DELETE", "DROP" def read only guard event: BeforeToolCallEvent : """Block writes. This agent is read-only.""" if event.tool use "name" == "query database": sql = event.tool use "input" .get "query", "" if any kw in sql.upper for kw in WRITE OPS : event.cancel tool = "Read-only access." agent = Agent tools= query database , hooks= read only guard , python from strands import Agent from strands.hooks import BeforeToolCallEvent WRITE OPS = "INSERT", "UPDATE", "DELETE", "DROP" def read only guard event: BeforeToolCallEvent : """Block writes. This agent is read-only.""" if event.tool use "name" == "query database": sql = event.tool use "input" .get "query", "" if any kw in sql.upper for kw in WRITE OPS : event.cancel tool = "Read-only access." agent = Agent tools= query database , hooks= read only guard , Then the harness gives specific feedback: "add a WHERE clause," "check permissions first." The agent corrects itself. You get reliable outcomes without micromanaging every step. from strands.vended plugins.steering import SteeringHandler, Guide, Proceed, class QueryQualityPolicy SteeringHandler : async def steer before tool self, , agent, tool use, kwargs : sql = tool use "input" .get "query", "" .upper if "SELECT" in sql and "WHERE" not in sql: return Guide reason="Add a WHERE clause and LIMIT." if sql.upper .count "JOIN" 3: return Guide reason="4+ joins. Break into smaller queries." return Proceed reason="Query looks good." agent = Agent tools= query database , plugins= QueryQualityPolicy , from strands.vended plugins.steering import SteeringHandler, Guide, Proceed, class QueryQualityPolicy SteeringHandler : async def steer before tool self, , agent, tool use, kwargs : sql = tool use "input" .get "query", "" .upper if "SELECT" in sql and "WHERE" not in sql: return Guide reason="Add a WHERE clause and LIMIT." if sql.upper .count "JOIN" 3: return Guide reason="4+ joins. Break into smaller queries." return Proceed reason="Query looks good." agent = Agent tools= query database , plugins= QueryQualityPolicy , 82.5% . Hard-coded workflows scored 80.8% . Agents with Strands steering handlers recovered from every mistake. See the benchmark → /blog/steering-accuracy-beats-prompts-workflows/ At Smartsheet, we chose Strands for our next generation of AI capabilities because it provided the perfect balance of enterprise-ready features and development efficiency. Its robust conversation memory and dynamic tool registration systems were crucial for creating a responsive, context-aware intelligent AI assistant. With Strands, we were able to quickly implement a secure and scalable solution, giving us a production-ready foundation to deliver a secure, high-performance, and enterprise-grade AI experience. Transform traditional error alerts into intelligent incident responses using Amazon Bedrock, RAG with Amazon OpenSearch, Multi-Agent Orchestration with Strands SDK, and Kiro AI IDE - reducing MTTR by 60% without manual coding. Strands’ SDK and great integration with AWS native services streamlined Landchecker’s development of agents. With easier integration of AgentCore Runtime, Bedrock Guardrails, and built-in support for OpenTelemetry, we could focus on what we do best – developing property information tools and data integrations. At Swisscom, we need an agentic AI backbone that is both enterprise-ready and future-proof. Strands Agents gives us the best of both worlds: a native fit with our cloud environment, yet fully open source and flexible. That combination allowed us to build proof-of-concepts within just a few weeks and now sets us on the path to scale multi-agent systems with confidence, while keeping our focus on delivering real value to customers and the business. The advisor is where things get interesting. We use the Strands Agents SDK to define an agent with a tool, a function the model can call during its reasoning loop. We chose Strands because it’s AWS-native, intuitive, and made agent development accessible across our engineering team. Its abstraction layer and built-in multi-agent patterns like Agent-as-Tool and Swarm let us focus on remediation logic instead of infrastructure work. We’ve already built multiple agents, and wiring them together has been seamless. On top of that, we layered our Agentic Remediation™ capability to automate vulnerability fixes and configuration validation/fault correction workflows, coordinating cross-agent remediation with precision Scaling our global trading platform required reimagining our support capabilities, and Strands Agents was the key to making it happen at enterprise scale. What would traditionally take months of development, Strands allowed us to achieve in just 10 days - delivering a secure, robust, production-ready agentic solution. The results speak for themselves: investigation time dropped on average from 30 minutes to 45 seconds, investigation quality improved by 94%, and we saved $5M in operational costs. Strands didn’t just accelerate our development - it gave us the confidence to explore other agentic AI use cases across our entire business, including launching our Agentic Security Operations Center Adding bidirectional voice to my existing Strands agent was surprisingly straightforward. BidiAgent handles the WebSocket complexity and interruption logic, my @tool functions carried over unchanged, and the same code deploys to AgentCore without modification. Strands made real-time voice feel like a natural extension, not a separate project. We see Strands as a great fit to power TeamForm’s next evolution of Agentic AI. Our customers need enterprise-grade security and scalability, which is exactly what Strands delivers. Its seamless integration with AWS and simplicity enables us to focus on innovating our AI capabilities and delivering value to our customers. For Jit’s infrastructure drift detection agent, we leverage Strands Agents, an open-source framework developed by AWS for building production-ready AI agents. Strands Agents provides several advantages including simplified development, native AWS integration, and built-in security. As someone who builds agents with LangGraph daily at work, Strands was a genuine surprise. The model-driven approach cut my setup from 40 lines to 3 — and for the 80% case, it just works without sacrificing flexibility. Strands Agents on Bedrock turns autonomous agents into an enterprise product: governed, observable, and safe by design. Together with Claude models, we analyze live webpages and generate code responsibly - helping customers reduce risk while accelerating delivery. Safety is non-negotiable in offensive security. On Amazon Bedrock, Strands Agents plus Claude let us scale autonomous pen-testing with Bedrock Guardrails - increasing coverage without increasing risk. The combination of the Strands Agents SDK and Tavily represents a significant advancement in enterprise-grade research agent development. This integration can help organizations build sophisticated, secure, and scalable AI agents while maintaining the highest standards of security and performance. Learn more in this blog . Strands was used to build a growing set of agents that run a company to do actual tasks. At Smartsheet, we chose Strands for our next generation of AI capabilities because it provided the perfect balance of enterprise-ready features and development efficiency. Its robust conversation memory and dynamic tool registration systems were crucial for creating a responsive, context-aware intelligent AI assistant. With Strands, we were able to quickly implement a secure and scalable solution, giving us a production-ready foundation to deliver a secure, high-performance, and enterprise-grade AI experience. Transform traditional error alerts into intelligent incident responses using Amazon Bedrock, RAG with Amazon OpenSearch, Multi-Agent Orchestration with Strands SDK, and Kiro AI IDE - reducing MTTR by 60% without manual coding. Strands’ SDK and great integration with AWS native services streamlined Landchecker’s development of agents. With easier integration of AgentCore Runtime, Bedrock Guardrails, and built-in support for OpenTelemetry, we could focus on what we do best – developing property information tools and data integrations. At Swisscom, we need an agentic AI backbone that is both enterprise-ready and future-proof. Strands Agents gives us the best of both worlds: a native fit with our cloud environment, yet fully open source and flexible. That combination allowed us to build proof-of-concepts within just a few weeks and now sets us on the path to scale multi-agent systems with confidence, while keeping our focus on delivering real value to customers and the business. The advisor is where things get interesting. We use the Strands Agents SDK to define an agent with a tool, a function the model can call during its reasoning loop. We chose Strands because it’s AWS-native, intuitive, and made agent development accessible across our engineering team. Its abstraction layer and built-in multi-agent patterns like Agent-as-Tool and Swarm let us focus on remediation logic instead of infrastructure work. We’ve already built multiple agents, and wiring them together has been seamless. On top of that, we layered our Agentic Remediation™ capability to automate vulnerability fixes and configuration validation/fault correction workflows, coordinating cross-agent remediation with precision Scaling our global trading platform required reimagining our support capabilities, and Strands Agents was the key to making it happen at enterprise scale. What would traditionally take months of development, Strands allowed us to achieve in just 10 days - delivering a secure, robust, production-ready agentic solution. The results speak for themselves: investigation time dropped on average from 30 minutes to 45 seconds, investigation quality improved by 94%, and we saved $5M in operational costs. Strands didn’t just accelerate our development - it gave us the confidence to explore other agentic AI use cases across our entire business, including launching our Agentic Security Operations Center Adding bidirectional voice to my existing Strands agent was surprisingly straightforward. BidiAgent handles the WebSocket complexity and interruption logic, my @tool functions carried over unchanged, and the same code deploys to AgentCore without modification. Strands made real-time voice feel like a natural extension, not a separate project. We see Strands as a great fit to power TeamForm’s next evolution of Agentic AI. Our customers need enterprise-grade security and scalability, which is exactly what Strands delivers. Its seamless integration with AWS and simplicity enables us to focus on innovating our AI capabilities and delivering value to our customers. For Jit’s infrastructure drift detection agent, we leverage Strands Agents, an open-source framework developed by AWS for building production-ready AI agents. Strands Agents provides several advantages including simplified development, native AWS integration, and built-in security. As someone who builds agents with LangGraph daily at work, Strands was a genuine surprise. The model-driven approach cut my setup from 40 lines to 3 — and for the 80% case, it just works without sacrificing flexibility. Strands Agents on Bedrock turns autonomous agents into an enterprise product: governed, observable, and safe by design. Together with Claude models, we analyze live webpages and generate code responsibly - helping customers reduce risk while accelerating delivery. Safety is non-negotiable in offensive security. On Amazon Bedrock, Strands Agents plus Claude let us scale autonomous pen-testing with Bedrock Guardrails - increasing coverage without increasing risk. The combination of the Strands Agents SDK and Tavily represents a significant advancement in enterprise-grade research agent development. This integration can help organizations build sophisticated, secure, and scalable AI agents while maintaining the highest standards of security and performance. Learn more in this blog . Strands was used to build a growing set of agents that run a company to do actual tasks. Automate workflows Classify, score, and route. One agent, one job. Replace brittle scripts with tools that adapt when your process changes. python from strands import Agent, tool @tool def classify lead email: str, company: str - dict: """Score and classify an inbound lead.""" firmographics = crm.lookup company return { "score": compute icp score firmographics , "segment": firmographics "industry" , } @tool def route to rep lead id: str, region: str - str: """Assign a lead to the right sales rep.""" rep = crm.get rep for region region crm.assign lead id, rep return f"Assigned to {rep}" agent = Agent tools= classify lead, route to rep , agent "New lead: jane@acme.com, Acme Corp, US-West" python from strands import Agent, tool @tool def classify lead email: str, company: str - dict: """Score and classify an inbound lead.""" firmographics = crm.lookup company return { "score": compute icp score firmographics , "segment": firmographics "industry" , } @tool def route to rep lead id: str, region: str - str: """Assign a lead to the right sales rep.""" rep = crm.get rep for region region crm.assign lead id, rep return f"Assigned to {rep}" agent = Agent tools= classify lead, route to rep , agent "New lead: jane@acme.com, Acme Corp, US-West" python import { Agent, tool } from '@strands-agents/sdk' import z from 'zod' const classifyLead = tool { name: 'classify lead', description: 'Score and classify a lead.', inputSchema: z.object { email: z.string , company: z.string , } , callback: { email, company } = { const data = crm.lookup company return { score: computeIcpScore data , segment: data.industry, } }, } const routeToRep = tool { name: 'route to rep', description: 'Assign a lead to a rep.', inputSchema: z.object { leadId: z.string , region: z.string , } , callback: { leadId, region } = { const rep = crm.getRepForRegion region crm.assign leadId, rep return Assigned to ${rep} }, } const agent = new Agent { tools: classifyLead, routeToRep , } await agent.invoke 'New lead: jane@acme.com, Acme Corp, US-West' python import { Agent, tool } from '@strands-agents/sdk' import z from 'zod' const classifyLead = tool { name: 'classify lead', description: 'Score and classify a lead.', inputSchema: z.object { email: z.string , company: z.string , } , callback: { email, company } = { const data = crm.lookup company return { score: computeIcpScore data , segment: data.industry, } }, } const routeToRep = tool { name: 'route to rep', description: 'Assign a lead to a rep.', inputSchema: z.object { leadId: z.string , region: z.string , } , callback: { leadId, region } = { const rep = crm.getRepForRegion region crm.assign leadId, rep return Assigned to ${rep} }, } const agent = new Agent { tools: classifyLead, routeToRep , } await agent.invoke 'New lead: jane@acme.com, Acme Corp, US-West' Build AI assistants Ground agents in your knowledge base via MCP. Context management keeps long conversations in bounds. Interrupts pause for human approval before sensitive actions. python from strands import Agent, tool from strands.tools.mcp import MCPClient from strands.hooks import BeforeToolCallEvent from strands.agent import SlidingWindowConversationManager from mcp import stdio client, StdioServerParameters kb = MCPClient lambda: stdio client StdioServerParameters command="uvx", args= "kb-server" @tool def issue refund order id: str, amount: float - str: """Process a customer refund.""" return payments.refund order id, amount def approve refunds event: BeforeToolCallEvent : """Pause for human approval before processing refunds.""" if event.tool use "name" == "issue refund": response = event.interrupt "refund approval", reason=event.tool use "input" if response = "APPROVE": event.cancel tool = "Refund not approved." agent = Agent system prompt="Support assistant. Use the KB. " "Refunds require approval.", tools= kb, issue refund , hooks= approve refunds , conversation manager=SlidingWindowConversationManager window size=20 , python from strands import Agent, tool from strands.tools.mcp import MCPClient from strands.hooks import BeforeToolCallEvent from strands.agent import SlidingWindowConversationManager from mcp import stdio client, StdioServerParameters kb = MCPClient lambda: stdio client StdioServerParameters command="uvx", args= "kb-server" @tool def issue refund order id: str, amount: float - str: """Process a customer refund.""" return payments.refund order id, amount def approve refunds event: BeforeToolCallEvent : """Pause for human approval before processing refunds.""" if event.tool use "name" == "issue refund": response = event.interrupt "refund approval", reason=event.tool use "input" if response = "APPROVE": event.cancel tool = "Refund not approved." agent = Agent system prompt="Support assistant. Use the KB. " "Refunds require approval.", tools= kb, issue refund , hooks= approve refunds , conversation manager=SlidingWindowConversationManager window size=20 , js import { Agent, tool, McpClient, BeforeToolCallEvent, SlidingWindowConversationManager, } from '@strands-agents/sdk' import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js' import z from 'zod' const kb = new McpClient { transport: new StdioClientTransport { command: 'npx', args: 'kb-server' , } , } const issueRefund = tool { name: 'issue refund', description: 'Process a refund.', inputSchema: z.object { orderId: z.string , amount: z.number , } , callback: { orderId, amount } = payments.refund orderId, amount , } const agent = new Agent { systemPrompt: 'Support assistant. ' + 'Use KB. Refunds require approval.', tools: kb, issueRefund , conversationManager: new SlidingWindowConversationManager { windowSize: 20, } , } // Cancel refunds interrupt coming soon to TS agent.addHook BeforeToolCallEvent, event = { if event.toolUse.name === 'issue refund' { event.cancel = 'Refund approval required.' } } js import { Agent, tool, McpClient, BeforeToolCallEvent, SlidingWindowConversationManager, } from '@strands-agents/sdk' import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js' import z from 'zod' const kb = new McpClient { transport: new StdioClientTransport { command: 'npx', args: 'kb-server' , } , } const issueRefund = tool { name: 'issue refund', description: 'Process a refund.', inputSchema: z.object { orderId: z.string , amount: z.number , } , callback: { orderId, amount } = payments.refund orderId, amount , } const agent = new Agent { systemPrompt: 'Support assistant. ' + 'Use KB. Refunds require approval.', tools: kb, issueRefund , conversationManager: new SlidingWindowConversationManager { windowSize: 20, } , } // Cancel refunds interrupt coming soon to TS agent.addHook BeforeToolCallEvent, event = { if event.toolUse.name === 'issue refund' { event.cancel = 'Refund approval required.' } } Build research agents Wake up to a briefing instead of a to-do list. Structured output keeps results typed and predictable. python from pydantic import BaseModel, Field from strands import Agent from strands tools import http request from pathlib import Path class Briefing BaseModel : headline: str = Field description="One-line summary" developments: list str = Field description="Key developments" sources: list str = Field description="URLs consulted" agent = Agent system prompt="Research assistant. Search the web, " "find developments from the last 24 hours, " "and produce a briefing with citations.", tools= http request , result = agent "What happened in AI agent frameworks yesterday?", structured output model=Briefing, briefing = result.structured output Path "briefings/daily.md" .write text f" {briefing.headline}\n\n" + "\n".join f"- {d}" for d in briefing.developments python from pydantic import BaseModel, Field from strands import Agent from strands tools import http request from pathlib import Path class Briefing BaseModel : headline: str = Field description="One-line summary" developments: list str = Field description="Key developments" sources: list str = Field description="URLs consulted" agent = Agent system prompt="Research assistant. Search the web, " "find developments from the last 24 hours, " "and produce a briefing with citations.", tools= http request , result = agent "What happened in AI agent frameworks yesterday?", structured output model=Briefing, briefing = result.structured output Path "briefings/daily.md" .write text f" {briefing.headline}\n\n" + "\n".join f"- {d}" for d in briefing.developments js import { Agent } from '@strands-agents/sdk' import { httpRequest } from '@strands-agents/tools' import z from 'zod' import { writeFileSync } from 'fs' const BriefingSchema = z.object { headline: z.string .describe 'Summary' , developments: z.array z.string .describe 'Key developments' , sources: z.array z.string .describe 'URLs consulted' , } const agent = new Agent { systemPrompt: 'Research assistant. ' + 'Search the web. Cite sources.', tools: httpRequest , } const result = await agent.invoke 'AI agent frameworks: what happened yesterday?', { structuredOutputSchema: BriefingSchema }, const briefing = result.structuredOutput writeFileSync 'briefings/daily.md', ${briefing.headline}\n\n + briefing.developments .map d: string = - ${d} .join '\n' js import { Agent } from '@strands-agents/sdk' import { httpRequest } from '@strands-agents/tools' import z from 'zod' import { writeFileSync } from 'fs' const BriefingSchema = z.object { headline: z.string .describe 'Summary' , developments: z.array z.string .describe 'Key developments' , sources: z.array z.string .describe 'URLs consulted' , } const agent = new Agent { systemPrompt: 'Research assistant. ' + 'Search the web. Cite sources.', tools: httpRequest , } const result = await agent.invoke 'AI agent frameworks: what happened yesterday?', { structuredOutputSchema: BriefingSchema }, const briefing = result.structuredOutput writeFileSync 'briefings/daily.md', ${briefing.headline}\n\n + briefing.developments .map d: string = - ${d} .join '\n'