Masud Hasan

An agent has no consistent definition. You can think of an agent as an autonomous or semi-autonomous system that can take actions on behalf of the user in a given environment, state, and make decisions or take actions that can accomplish certain tasks along a given time-frame, either by calling tools, dynamically selecting the next action to take or use a deterministic "workflow" (systems where LLMs and tools are orchestrated through predefined code paths). Using an Agent framework that gives you the ability to built systems in both, a reliable and a dynamic way can accelerate your agent development journey using agent abstractions. This means building Agentic systems that can reliably call tools, store memory (episodic/semantic/procedural), have comprehensive logging and observability, human in the loop workflows and the ability to build various multi-agent patterns flexibly based on your use case. A successful Agentic system in production is usually a combination of both, dynamic and predictable/reliable multi-agent systems. Strands Agents SDK gives you exactly these capabilities by treating each “agent” as a combination of a foundation model plus a suite of tools. You define a prompt and register your tools (decorated functions) in code, then Strands handles reasoning→planning→tool-execution cycles, local testing, and cloud deployment (ECS, Fargate, Lambda, EC2), along with support for all other agent abstractions provided above. Excited to share a hedge-fund analyst multi agent system: This uses the newest Anthropic's Claude 4 Sonnet/Opus that powers the Lead Analyst Agent, routing incoming queries to specialized sub-agents for fundamental, technical, and market analyses. Each specialist is wrapped as a callable tool (using the “agents-as-tools” multi-agent pattern), so the orchestrator never has to implement domain logic itself and can handoff the task to an agent as a tool. For sensitive operations (insider lookups), we utilize a HITL approval step that halts execution until a human grants consent. We also use meta-tooling that enables the Lead Analyst to generate, load, and invoke new custom tools at runtime—whether it’s a portfolio beta calculator or a pricer—without redeployment. Strands also embeds observability (Langfuse) and OpenTelemetry tracing so you can trace reasoning events, tool invocations, errors, and end-to-end workflows in real time. View more information on the code implementation here: https://lnkd.in/gJmwVyGi Code implementation: https://lnkd.in/gzTtJvJq Thanks to 🏄‍♂️ Cagatay Cali for being a reviewer/collaborator on this! Feel free to try it out and reach out with any questions/ideas. #aws #agenticAI #strands #agents #generativeAI

60

6 Comments

🚀 Exciting News for FinOps Teams & Cloud Practitioners! 🚀 AWS has just launched the Billing and Cost Management MCP Server (Model Context Protocol)! This new feature makes advanced cost analysis and optimization capabilities directly accessible via AI assistants, chatbots, and dev tools, no need to drop into the console or write custom scripts. 🔗 Read more here: https://lnkd.in/diBJYGKJ Why this is a game-changer: ❓ - Natural-language cost insights on demand Just ask your AI assistant questions like “What were my top spending services last month?” or “Where can I optimize resource costs?” and get immediate, clear answers. - Real-time access with secure local credentials The MCP server securely taps into AWS Cost Explorer, Cost Optimization Hub, Compute Optimizer, Savings Plans, Cost Anomaly Detection, and more streamlining your FinOps visibility. - Boosted transparency & efficiency No more sifting through dashboards or tedious CLI commands. Cost transparency, actionable insights, and audit-ready reports, all through simple prompts. - Goodbye to custom scripts This managed solution replaces fragile scripts and manual workflows. You now have a robust, reusable way to tap into cost data, without reinventing the wheel 😅 Honestly, I’m just relieved I don’t have to think and build this from scratch with custom scripts anymore!

218

5 Comments