Build a Memory-Powered Multi-Agent Financial Advisor with Strands SDK & Amazon Bedrock

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python) The Hidden Cost of AI Systems Nobody Talks About. undefined vs undeclared, and how typeof behaves Switching from file-based jobs to NATS/Kafka in Rust without changing code io_uring Adventures: Rust Servers That Love Syscalls Why Agentic AI is Killing the Traditional Database The POUR principles of web accessibility for developers and designers Quantum Neural Network 3D — A Deep Dive into Interactive WebGL Visualization How To Install Caveman In Codex On macOS And Windows Automation Pipeline Reliability: Why Your Workflow Breaks When Nobody Is Watching I Built an 'Open World' AI Coding Agent — It Works From ANY Folder From Freelancing to Product: A Tech Service Company's SaaS Transformation China's AI Giants: Adding Tencent Hunyuan & ByteDance Doubao to AI University (74 Providers) On the Vibe Coders and Their Lies clerk: Auto-Summarize Your Claude Code Sessions AI Weekly — 2026/04/10–04/17 | The Model Lockdown Is Here, but the Toolchain Is the Real Battleground AI 週報 — 2026/04/10–2026/04/17 模型封鎖潮來了，但工具鏈才是真戰場 Maybe this is how Open-Source apps are born... 🚀 Fine-Tune LLMs with LoRA and QLoRA: 2026 Guide tRPC v11 + Next.js App Router: End-to-End Type Safety Without the Boilerplate ShadCN UI in 2026: Why I Stopped Installing Component Libraries and Started Owning My Components SaaS Billing in React Server Components: Stripe + Supabase Without a Single `useEffect` Join our DEV Weekend Challenge — $1,000 in Prizes Across TEN winners! Submissions Due April 20 at 6:59 AM UTC. Implementing FSRS Spaced Repetition in Flutter + Supabase — Adding Memory Science to an AI Learning App "I Texted My Localhost From the Train — Claude Code Fixed the Bug Before I Got Home" I Built a Sales Prep AI and It Went Deeper Than Expected Design to Code #2: One JSON, Eleven Outputs Solving the 100M-Row Problem: A Summary Table Pattern for High-Volume Push Notification Logs Flutter Web With Wasm: What Actually Changes For Developers I Built 50 Royalty-Free Soundtracks for My Side Project in a Weekend Using AI Music Generation The Vibe Coding Security Checklist: 7 Things to Check Before You Ship Stop Letting Googlebot Guess Fix Your React App's SEO Right Desconstruindo o Streaming do LinkedIn: Como Criar um Engine de Extração de Vídeo de Alta Performance com HLS e FFmpeg (EDA Part-1) EDA (Exploratory Data Analysis) Explained With Real Life — Why Looking at Your Data Is the Most Important Step in Machine Learning Brand Relationship Management at Scale: Our 4-Touch Outreach System for 200+ Brands Why String.fromEnvironment() Might Return an Empty String in Dart JGuardrails 1.0.0 — Hardening Java LLM Apps Against Jailbreaks, Toxicity, and Prompt Injection Plan and Schedule a Full Week of Threads Content From One Claude Conversation Coding Cat Oran Ep3, Five Tables Changed Everything Updated: BFF Pattern I'm done watching freelancers get buried by 200 proposals. So I'm building the alternative. This is my first post BFS Algorithm in Java Step by Step Tutorial with Examples Tracking LLM Pricing Monthly: An Open Dataset for 22 AI Models How We Measure Content ROI on a Comparison Site: Revenue Attribution Without Perfect Data Introducing Nova AI Ops: The AI-Native Operating System for SRE Teams I built a free desktop video downloader for Windows — Grabbit How Talkie OCR Helps Vision-Impaired & Dyslexic Users Read the World Around Them VRCFaceTracking安装和iPhone面捕配置教程，有bug Even CrowdStrike Can't See Your Agents The Automation Gold Rush: What n8n Workflows and Claude Are Opening Up for Developers Right Now

Adeline Mako · 2026-04-23 · via DEV Community

Why Agents — Not Just Chatbots A chatbot answers your question and forgets you. An AI agent takes actions, uses tools, and loops until the job is actually done. The difference isn't the model, it's the architecture. <a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fw51u1zxzo1ytup8zuyre.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fw51u1zxzo1ytup8zuyre.png" alt=" " width="800" height="302"></a> The agent loop has four steps: <ol> <li> Perceive- read the user's request plus any injected context (memory, RAG results, past turns)</li> <li> Plan- reason about what to do next; choose which tool(s) to call</li> <li> Act- call the chosen tool(s), APIs, or sub-agents</li> <li> Reflect- evaluate the results; decide whether the task is done or the loop should continue</li> </ol> Unlike a simple LLM call, the agent decides autonomously when it has gathered enough information to answer and it keeps going until it has. The Project: A Multi-Agent Financial Advisor To make this concrete, we'll build a memory-powered multi-agent financial advisor. It: <ul> <li>Accepts natural-language questions ("Should I rebalance my portfolio?")</li> <li>Delegates to specialist sub-agents for portfolio data, market prices, and financial news</li> <li>Uses Amazon Bedrock Guardrails to enforce compliance rules at every step</li> <li>Stores client preferences and past conversations using Amazon Bedrock AgentCore Memory </li> <li>Deploys as a serverless endpoint with a single <code>agentcore deploy</code> command</li> </ul> The full stack: <div class="table-wrapper-paragraph"><table> <thead> <tr> <th>Layer</th> <th>Technology</th> </tr> </thead> <tbody> <tr> <td>Agent framework</td> <td> <a href="https://github.com/strands-agents/sdk-python" rel="noopener noreferrer">Strands Agents SDK</a> (open-source)</td> </tr> <tr> <td>Foundation model</td> <td>Claude 3.5 Sonnet via Amazon Bedrock</td> </tr> <tr> <td>Safety layer</td> <td>Amazon Bedrock Guardrails</td> </tr> <tr> <td>Memory layer</td> <td>Amazon Bedrock AgentCore Memory</td> </tr> <tr> <td>Runtime</td> <td>Amazon Bedrock AgentCore Runtime</td> </tr> <tr> <td>Observability</td> <td>AWS CloudWatch + OpenTelemetry</td> </tr> </tbody> </table></div> <a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fvha4c8lxnouayd1itbed.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fvha4c8lxnouayd1itbed.png" alt=" " width="800" height="401"></a> The orchestrator agent receives every user request and intelligently routes sub-tasks to the right specialist. Results are synthesized into a single, coherent response. Meet the Strands Agents SDK <a href="https://github.com/strands-agents/sdk-python" rel="noopener noreferrer">Strands</a> is an open-source Python framework from AWS Labs that makes building production agents dramatically simpler. You define tools, wrap them in an <code>Agent</code>, and Strands handles the loop. <code>pip install strands-agents</code> The core idea is minimal boilerplate. Three imports and a decorator are enough to expose any Python function to an agent as a callable tool. <h2> Step 1 — Define Tools with <code>@tool</code> </h2> <a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F6b1vxw3qw08fnhm93oth.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F6b1vxw3qw08fnhm93oth.png" alt=" " width="800" height="280"></a> The <code>@tool</code> decorator does the heavy lifting automatically: <ul> <li>Parses Python type hints into a JSON schema the model can read</li> <li>Converts the docstring into the tool's description (what the agent uses to decide when to call it)</li> <li>Handles invocation so the agent decides when, and with what arguments, to call the function </li> </ul> <div class="highlight js-code-highlight"> <pre class="highlight python"><code># tools/financial_tools.py from strands import tool from typing import Optional @tool def get_portfolio_value( client_id: str, include_unrealized_gains: bool = True ) -> dict: """Retrieve the current portfolio value and positions for a client.""" return fetch_portfolio_data(client_id, include_unrealized_gains) @tool def get_market_data(tickers: list[str], period: str = "1d") -> dict: """Retrieve current market prices and key metrics for a list of tickers.""" return fetch_market_prices(tickers, period) @tool def get_financial_news(query: str, max_results: int = 5) -> dict: """Retrieve recent financial news articles relevant to a query.""" return fetch_news_feed(query, max_results) @tool def get_risk_analysis( client_id: str, risk_tolerance: Optional[str] = None ) -> dict: """Perform a risk analysis on a client's portfolio.""" return compute_risk_metrics(client_id, risk_tolerance) @tool def get_investment_recommendations( client_id: str, goal: str = "growth", time_horizon_years: int = 10 ) -> dict: """Generate personalised investment recommendations for a client.""" return generate_recommendations(client_id, goal, time_horizon_years) </code></pre> </div> Each function becomes a first-class tool — no YAML, no schema files, no extra config. <h2> Step 2- Build Specialist Sub-Agents </h2> Rather than one monolithic agent with 15 tools, we split responsibilities. Each specialist agent gets only the tools it needs, which keeps the system prompt focused and improves tool selection accuracy. <div class="highlight js-code-highlight"> <pre class="highlight python"><code># agents/specialists.py from strands import Agent from strands.models import BedrockModel from tools.financial_tools import ( get_portfolio_value, get_risk_analysis, get_market_data, get_financial_news, ) MODEL_ID = "us.anthropic.claude-3-5-sonnet-20241022-v2:0" def _make_model(guardrail_id: str | None) -> BedrockModel: kwargs = {"model_id": MODEL_ID, "region_name": "us-east-1"} if guardrail_id: kwargs["guardrail_id"] = guardrail_id kwargs["guardrail_version"] = "DRAFT" return BedrockModel(**kwargs) def create_portfolio_agent(guardrail_id: str | None = None) -> Agent: return Agent( model=_make_model(guardrail_id), system_prompt=( "You are a Portfolio Specialist. Analyse holdings, risk metrics, " "and P&L. Be precise and cite specific numbers." ), tools=[get_portfolio_value, get_risk_analysis], ) def create_market_data_agent(guardrail_id: str | None = None) -> Agent: return Agent( model=_make_model(guardrail_id), system_prompt=( "You are a Market Data Specialist. Provide current prices, " "52-week ranges, and key indices. Stick to facts." ), tools=[get_market_data], ) def create_news_agent(guardrail_id: str | None = None) -> Agent: return Agent( model=_make_model(guardrail_id), system_prompt=( "You are a Financial News Analyst. Summarise recent news and " "provide sentiment analysis. Be objective." ), tools=[get_financial_news], ) </code></pre> </div> <h2> Step 3- The Orchestrator & Agent-as-Tool Pattern </h2> The orchestrator doesn't call specialist agents directly, it treats them as tools. This is the agent-as-tool pattern: each sub-agent is wrapped in a <code>@tool</code> function, so the orchestrator's model reasons about which specialist to consult, exactly like it would choose any other tool. <div class="highlight js-code-highlight"> <pre class="highlight python"><code># agents/orchestrator.py from strands import Agent, tool from strands.models import BedrockModel from agents.specialists import ( create_portfolio_agent, create_market_data_agent, create_news_agent, ) from tools.financial_tools import get_investment_recommendations def _build_specialist_tools(guardrail_id: str | None): portfolio_agent = create_portfolio_agent(guardrail_id) market_agent = create_market_data_agent(guardrail_id) news_agent = create_news_agent(guardrail_id) @tool def ask_portfolio_agent(query: str) -> str: """Delegate a portfolio analysis or risk question to the Portfolio Specialist Agent.""" return str(portfolio_agent(query)) @tool def ask_market_data_agent(query: str) -> str: """Delegate a market data or pricing question to the Market Data Specialist Agent.""" return str(market_agent(query)) @tool def ask_news_agent(query: str) -> str: """Delegate a news or sentiment analysis question to the News Analyst Agent.""" return str(news_agent(query)) return [ask_portfolio_agent, ask_market_data_agent, ask_news_agent] ORCHESTRATOR_PROMPT = """ You are a Senior Financial Advisor AI. Your role is to provide comprehensive, personalised financial guidance. You have three specialist agents available: - Portfolio Specialist: portfolio values, positions, risk metrics - Market Data Specialist: prices, indices, volatility - News Analyst: financial news and sentiment Always delegate to the right specialist(s), then synthesise their findings into a clear, actionable response for the client. """ def create_financial_advisor( guardrail_id: str | None = None, memory_context: str = "", model_id: str = "us.anthropic.claude-3-5-sonnet-20241022-v2:0", ) -> Agent: specialist_tools = _build_specialist_tools(guardrail_id) system_prompt = ORCHESTRATOR_PROMPT if memory_context: system_prompt += f"\n\n## Client Memory\n{memory_context}" model_kwargs = {"model_id": model_id, "region_name": "us-east-1"} if guardrail_id: model_kwargs.update({"guardrail_id": guardrail_id, "guardrail_version": "DRAFT"}) return Agent( model=BedrockModel(**model_kwargs), system_prompt=system_prompt, tools=specialist_tools + [get_investment_recommendations], ) </code></pre> </div> When the user asks "Should I rebalance my portfolio given today's market?", the orchestrator: <ol> <li>Calls <code>ask_portfolio_agent</code> → gets current holdings & risk score</li> <li>Calls <code>ask_market_data_agent</code> → gets today's index moves</li> <li>Calls <code>ask_news_agent</code> → gets relevant headlines</li> <li>Synthesizes everything into a single coherent recommendation</li> </ol> <h2> Step 4- Persistent Memory Across Sessions </h2> Without memory, every conversation starts cold. AgentCore Memory gives the agent a persistent, semantic store, the agent remembers past interactions and client preferences across sessions. <div class="highlight js-code-highlight"> <pre class="highlight python"><code># memory/memory_manager.py import boto3 from dataclasses import dataclass, field class MemoryManager: """ Wraps Amazon Bedrock AgentCore Memory with a local in-process fallback so the demo runs without any AWS credentials. """ def __init__( self, memory_id: str | None = None, session_id: str | None = None, region: str = "us-east-1", use_local_fallback: bool = False, ): self.memory_id = memory_id self.session_id = session_id or "default" self.use_local = use_local_fallback or (memory_id is None) self._local_memory: list[dict] = [] if not self.use_local: self._client = boto3.client("bedrock-agentcore", region_name=region) def save_turn(self, user_input: str, agent_response: str) -> None: """Persist a conversation turn.""" if self.use_local: self._local_memory.append( {"user": user_input, "assistant": agent_response} ) return self._client.save_memory( memoryId=self.memory_id, sessionId=self.session_id, messages=[ {"role": "user", "content": user_input}, {"role": "assistant", "content": agent_response}, ], ) def get_recent_context(self, max_turns: int = 5, query: str | None = None) -> str: """Return a formatted string of recent memory to inject into the system prompt.""" if self.use_local: recent = self._local_memory[-max_turns:] if not recent: return "" lines = ["Previous conversation context:"] for turn in recent: lines.append(f"User: {turn['user']}") lines.append(f"Assistant: {turn['assistant'][:200]}...") return "\n".join(lines) response = self._client.retrieve_memory( memoryId=self.memory_id, sessionId=self.session_id, query=query or "recent client interactions", maxResults=max_turns, ) return "\n".join(r["content"] for r in response.get("results", [])) </code></pre> </div> Memory context is injected into the orchestrator's system prompt on every turn: <div class="highlight js-code-highlight"> <pre class="highlight python"><code>memory = MemoryManager(use_local_fallback=True) # swap to AWS for prod context = memory.get_recent_context(query=user_input) advisor = create_financial_advisor(memory_context=context) response = advisor(user_input) memory.save_turn(user_input, str(response)) </code></pre> </div> <blockquote> Why this matters: "Persistent memory lets the agent remember past conversations and client preferences, enabling truly personalized financial guidance at scale." </blockquote> <h2> Step 5- Compliance with Bedrock Guardrails </h2> Financial applications have strict compliance requirements: no guaranteed return promises, no off-topic advice, PII must be redacted. Bedrock Guardrails handles all of this at the infrastructure level, zero code changes in your agent logic. <a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Flo8xbls0p8a3qxhxnirh.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Flo8xbls0p8a3qxhxnirh.png" alt=" " width="800" height="287"></a> Guardrails are applied at both the input and output layers: <ul> <li> Input filter: blocks prompt injection, off-topic requests (medical, legal), and PII before the LLM ever sees them</li> <li> Output filter: checks grounding, redacts any leaked PII, blocks harmful or hallucinated content</li> </ul> Here's how we configure it: <div class="highlight js-code-highlight"> <pre class="highlight python"><code># guardrails/config.py import boto3 from dataclasses import dataclass, field from typing import Optional @dataclass class GuardrailsConfig: name: str = "financial-advisor-guardrail" content_filter_strength: str = "HIGH" denied_topics: list[dict] = field(default_factory=lambda: [ {"name": "Non-Financial Advice", "definition": "Any advice outside personal finance, investments, or markets.", "examples": ["medical diagnosis", "legal advice", "relationship counselling"]}, {"name": "Guaranteed Returns", "definition": "Claims that any investment guarantees specific returns.", "examples": ["guaranteed 20% return", "risk-free investment"]}, ]) pii_redaction_types: list[str] = field(default_factory=lambda: [ "US_SOCIAL_SECURITY_NUMBER", "CREDIT_DEBIT_CARD_NUMBER", "US_BANK_ACCOUNT_NUMBER", "EMAIL", "PHONE", "NAME", ]) blocked_words: list[str] = field(default_factory=lambda: [ "guaranteed returns", "risk-free investment", "100% safe", "cannot lose", ]) enable_grounding_check: bool = True grounding_threshold: float = 0.7 def get_or_create_guardrail( config: GuardrailsConfig | None = None, region: str = "us-east-1", ) -> Optional[str]: """Create (or retrieve existing) guardrail and return its ID.""" config = config or GuardrailsConfig() client = boto3.client("bedrock", region_name=region) # Check if it already exists for g in client.list_guardrails().get("guardrails", []): if g["name"] == config.name: return g["id"] response = client.create_guardrail( name=config.name, contentPolicyConfig={ "filtersConfig": [ {"type": "SEXUAL", "inputStrength": config.content_filter_strength, "outputStrength": config.content_filter_strength}, {"type": "VIOLENCE", "inputStrength": config.content_filter_strength, "outputStrength": config.content_filter_strength}, {"type": "HATE", "inputStrength": config.content_filter_strength, "outputStrength": config.content_filter_strength}, ] }, topicPolicyConfig={"topicsConfig": config.denied_topics}, sensitiveInformationPolicyConfig={ "piiEntitiesConfig": [ {"type": t, "action": "ANONYMIZE"} for t in config.pii_redaction_types ] }, wordPolicyConfig={ "wordsConfig": [{"text": w} for w in config.blocked_words] }, groundingPolicyConfig={ "filtersConfig": [ {"type": "GROUNDING", "threshold": config.grounding_threshold}, {"type": "RELEVANCE", "threshold": config.grounding_threshold}, ] } if config.enable_grounding_check else {}, ) return response["guardrailId"] </code></pre> </div> Attach the guardrail ID to the <code>BedrockModel</code> and every request, input AND output, is automatically screened. <h2> Step 6- Deploy to Production with AgentCore Runtime </h2> AgentCore Runtime is a serverless execution environment for agents. It handles auto-scaling, session management, health checks, and observability out of the box. <a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fra2o1jnt26p8crrod2ys.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fra2o1jnt26p8crrod2ys.png" alt=" " width="800" height="264"></a> The deployment config lives in <code>agentcore.json</code>: <div class="highlight js-code-highlight"> <pre class="highlight json"><code>{ "name": "financial-advisor-agent", "runtime": "python3.12", "handler": "main.handler", "model": { "provider": "bedrock", "model_id": "us.anthropic.claude-3-5-sonnet-20241022-v2:0" }, "memory": { "enabled": true, "type": "agentcore", "session_ttl_days": 90 }, "guardrails": { "enabled": true, "guardrail_name": "financial-advisor-guardrail", "apply_to": ["input", "output"] }, "scaling": { "min_instances": 1, "max_instances": 10, "target_concurrency": 5 }, "observability": { "tracing": "xray", "metrics": "cloudwatch", "log_level": "INFO" } } </code></pre> </div> Three CLI commands take you from code to production: <div class="highlight js-code-highlight"> <pre class="highlight shell"><code># Develop locally with hot-reload agentcore dev # → Local agent running at http://localhost:8080 # Deploy to Amazon Bedrock AgentCore Runtime agentcore deploy # → Packaging agent... done # → Provisioning CDK stack... done # → Attaching guardrails... done # → Configuring AgentCore Memory... done # → Deployed! Endpoint: https://bedrock-agentcore.us-east-1.amazonaws.com/agents/fa-demo # Invoke the deployed agent agentcore invoke "What is the portfolio value for client ABC123?" --stream </code></pre> </div> <h2> Putting It All Together- Running the Demo </h2> Clone the repo and run the demo locally (no AWS credentials required): <div class="highlight js-code-highlight"> <pre class="highlight shell"><code>git clone https://github.com/awslabs/agentcore-samples cd agentcore-samples/financial-advisor pip install -r requirements.txt # Local demo with mock data python main.py # Full AWS mode with real Bedrock, Memory, and Guardrails python main.py --use-aws --enable-guardrails # Interactive REPL python main.py --interactive </code></pre> </div> The scripted demo walks through six representative turns: <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code>[1/6] What is the total portfolio value for client ABC123? → Portfolio Specialist retrieves holdings + P&L [2/6] What are the current prices for AAPL, GOOGL, and MSFT? → Market Data Specialist fetches live prices + 52w range [3/6] What's the latest news about Apple and Microsoft? → News Analyst returns headlines + sentiment scores [4/6] What's the risk level of my current portfolio? → Portfolio Specialist runs risk decomposition [5/6] Based on everything, should I rebalance? → Orchestrator calls all three specialists + synthesises [6/6] Given what I told you about my risk preference earlier, any concerns? → Memory-powered: agent recalls previous turns and personalises </code></pre> </div> <h2> Key Takeaways </h2> The financial advisor demo shows how modern agent patterns come together in a coherent production architecture: Strands SDK makes agents simple. The <code>@tool</code> decorator, <code>Agent</code> class, and <code>BedrockModel</code> eliminate most boilerplate. You describe your tools in plain Python; the SDK handles the rest. Specialisation beats monoliths. Breaking the system into focused sub-agents — each with its own system prompt and tool set — produces sharper, more reliable answers than a single agent trying to do everything. The agent-as-tool pattern is powerful. Wrapping sub-agents as <code>@tool</code> functions lets the orchestrator's model reason about delegation using the same mechanism it uses for everything else. No custom routing logic required. Guardrails are infrastructure, not code. Attaching a Bedrock Guardrail to <code>BedrockModel</code> protects every single request- input AND output — without any changes to your agent logic. Compliance becomes a deployment concern, not a development one. Memory makes agents personal. Injecting past conversations into the system prompt at runtime is simple but transformative. The agent genuinely remembers- and users notice immediately. <code>agentcore deploy</code> is production-ready. Serverless execution, auto-scaling, integrated tracing, and health management are all included. Going from local dev to a live endpoint is three CLI commands. <h2> Resources </h2> <ul> <li> Demo code: <a href="https://github.com/awslabs/agentcore-samples" rel="noopener noreferrer">github.com/awslabs/agentcore-samples</a> </li> <li> Strands Agents SDK: <a href="https://github.com/strands-agents/sdk-python" rel="noopener noreferrer">github.com/strands-agents/sdk-python</a> </li> <li> Amazon Bedrock AgentCore docs: <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html" rel="noopener noreferrer">docs.aws.amazon.com/bedrock-agentcore</a> </li> <li> Amazon Bedrock Guardrails: <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html" rel="noopener noreferrer">docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html</a> </li> <li> AWS Summit 2025 session: Use Agent Strategies to Streamline Complex Business Tasks </li> </ul> Built with ❤️ using open-source tools and AWS. Questions or feedback? Drop them in the comments below.

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。

推荐订阅源

DEV Community