# AWS Open Source Blog Published articles for AWS Open Source Blog. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Unified Knowledge Graph RAG on AWS: GraphRAG and LightRAG on one stack DevFeed: [Unified Knowledge Graph RAG on AWS: GraphRAG and LightRAG on one stack]() Original publisher: [Read original article]() Author: Jonas Kim Published: 2026-09-14T16:55:58Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [Retrieval Augmented Generation (RAG)](), [Graphs](), [Amazon Bedrock](), [Amazon OpenSearch Service](), [Amazon Web Services]() Tags: [amazon-bedrock](), [amazon-opensearch-service](), [aws](), [knowledge-graph](), [open-source](), [rag](), [retrieval](), [search](), [vector-search]() ### AI overview This article presents a unified knowledge-graph RAG stack that brings Microsoft GraphRAG and HKUDS LightRAG together on Amazon Bedrock, Amazon Neptune, and Amazon OpenSearch Service. The shared stack supports common ingestion, indexing, caching, and multilingual handling while allowing the retrieval methodology to be selected per query. ### Source excerpt Picture a compliance analyst staring at a few thousand contracts, amendments, and internal memos, trying to answer one question that sounds straightforward: "Which of our obligations are exposed if this one milestone slips?" The answer isn't written in any single document. It's stitched across three -- a master agreement that ties a payment to a [...] ## Introducing Pizza Bot, an open source inbox for AI agents that work in the background DevFeed: [Introducing Pizza Bot, an open source inbox for AI agents that work in the background]() Original publisher: [Read original article]() Author: Joseph Dolivo Published: 2026-09-10T16:01:44Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [AI Bots]() Tags: [agents](), [ai](), [ai-agents](), [announcements](), [artificial-intelligence](), [open-source]() ### AI overview Pizza Bot is introduced as a self-hosted, open-source inbox for background AI-agent work. It lets users start, schedule, or trigger tasks by webhook, then surfaces completed work or requests requiring approval. ### Source excerpt Give an agent a task actually worth delegating and you'll be waiting a while. Ask it what needs your attention this morning and it has to read your mail, your messages, and your task list before it can answer. Then it stops halfway, because one step needs your approval. Meanwhile you're watching a chat window [...] ## Build full-stack AWS applications in minutes with AI-powered scaffolding DevFeed: [Build full-stack AWS applications in minutes with AI-powered scaffolding]() Original publisher: [Read original article]() Author: Jack Stevenson Published: 2026-09-08T21:24:59Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [App](), [cloud-infrastructure](), [Amazon Bedrock](), [Command-line interface](), [Kiro](), [Terraform](), [Bun]() Tags: [agentic](), [ai](), [ai-coding](), [amazon-bedrock](), [announcements](), [applications](), [aws](), [kiro](), [observability](), [security](), [technical-how-to](), [terraform]() ### AI overview The article introduces version 1.0 of the Nx Plugin for AWS, an open-source set of deterministic Nx generators for scaffolding deployable AWS application components and their infrastructure. It describes using AI assistants or a CLI to generate applications with security, observability, and type-safety practices included, and begins a quick start for an agentic application using Amazon Bedrock. ### Source excerpt AI assistants can stand up an app or website that runs on AWS in minutes. Getting to a production-ready version you would put in front of real customers is still the hard part. Security, observability, type-safety, and resilience are non-negotiable for production. An assistant rarely gets all of that right in one pass, and hardening [...] ## AWS Supports Agent Plugins: An Open Standard for Portable Agent Extensions DevFeed: [AWS Supports Agent Plugins: An Open Standard for Portable Agent Extensions]() Original publisher: [Read original article]() Author: Libby Clark Published: 2026-08-06T17:21:21Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [Agent Skill](), [Agent Skills](), [AI Agent](), [MCP Server](), [Open Source](), [Amazon Web Services](), [Model Context Protocol]() Tags: [agent-skill](), [agent-skills](), [ai-agent](), [aws](), [cursor](), [javascript](), [mcp](), [mcp-server](), [microsoft](), [model-context-protocol](), [open-source](), [openai](), [vercel](), [vs-code]() ### AI overview AWS supports Agent Plugins 1.0.0, an open source, vendor-neutral specification for packaging AI agent extensions in a common format. The standard is intended to let developers package an extension once and distribute it across compatible clients such as Kiro, VS Code, Cursor, and other tools. Its initial version standardizes Agent Skills and MCP servers, with hooks and custom agents planned for future versions. ### Source excerpt If you've ever built an MCP server or agent skill, you know that packaging it means adapting for one client, re-writing for another, and repeating that for every tool your team uses. Agent Plugins 1.0.0 is an open source, vendor-neutral specification that gives AI agent extensions a common packaging format so you can package an [...] ## Introducing Dogwood: runtime verification for AI agents DevFeed: [Introducing Dogwood: runtime verification for AI agents]() Original publisher: [Read original article]() Author: Marc Brooker Published: 2026-08-06T16:30:54Z Content type: release Language: en Sources: [AWS Open Source Blog]() Topics: [AI Bots]() Tags: [agent](), [agentic](), [agents](), [ai](), [ai-agents](), [amazon](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [automated-reasoning](), [open-source](), [policy](), [safety](), [tool](), [tools](), [workflows]() ### AI overview Dogwood is an open-source governance language for runtime verification of AI-agent tool use. It supports policies over sequences of actions, such as approval prerequisites, rate limits, ordering, and restrictions after accessing confidential information. ### Source excerpt Part of what makes AI agents so useful is their ability to interact with the external world by running tools. But these tool calls are also the source of the biggest risks when it comes to making agents safe to use. The best way to address these risks in a dependable and reliable manner is [...] ## Open Protocols with the Strands Agents SDK DevFeed: [Open Protocols with the Strands Agents SDK]() Original publisher: [Read original article]() Author: Madhu Samhitha Vangara Published: 2026-07-16T17:29:21Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [SDKs]() Tags: [ai-agent](), [apis](), [mcp](), [open-source](), [strands-agents]() ### AI overview An overview of how the Strands Agents SDK uses open agent protocols, including MCP, to connect AI agents with tools, APIs, other agents, user interaction, and payments. ### Source excerpt If you are building AI agents, you have likely encountered a growing list of protocol acronyms--MCP, A2A, UTCP, AG-UI, and x402--that can feel overwhelming. The open source community has converged on several complementary protocols. An AI agent is only as useful as the systems it can reach: internal tools and data, the external APIs your [...] ## Building secure AI agents at scale: Introducing Loom for AWS DevFeed: [Building secure AI agents at scale: Introducing Loom for AWS]() Original publisher: [Read original article]() Author: Heeki Park Published: 2026-07-09T21:16:33Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [AI Agent](), [Security](), [Amazon Web Services](), [Amazon Bedrock](), [Authorization](), [API](), [Serverless](), [Back end](), [Inference](), [Python](), [Low code](), [No-code]() Tags: [agentic](), [agents](), [ai](), [ai-agent](), [ai-agents](), [amazon-bedrock-agentcore](), [api](), [aws](), [backend](), [code](), [deployment](), [mcp](), [model](), [no-code](), [open-source](), [python](), [security](), [serverless](), [strands-agents]() ### AI overview Loom for AWS is an enterprise-grade platform for building, deploying, and operating secure AI agents at scale. It combines AWS Strands Agents with Amazon Bedrock AgentCore and provides management, authorization, identity integration, lifecycle controls, memory, MCP and A2A integrations, governance, and usage tracking. Loom supports low-code Python agents and no-code deployment through AgentCore's managed harness. ### Source excerpt As organizations move to adopt agentic capabilities to accelerate their business objectives, they are challenged with enabling those capabilities within a security and governance framework that complies with enterprise requirements. Some organizations lean into the promise of serverless capabilities, as those fully managed services enable them to build fast and deliver customer value quickly. Amazon [...] ## Introducing MCP server for Registry of Open Data on AWS DevFeed: [Introducing MCP server for Registry of Open Data on AWS]() Original publisher: [Read original article]() Author: Guyu Ye Published: 2026-07-07T20:12:39Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [MCP Server](), [Model Context Protocol](), [datasets](), [Amazon Web Services](), [Open Source](), [Claude Code](), [Kiro](), [Artificial Intelligence]() Tags: [ai](), [ai-assistants](), [aws](), [claude-code](), [datasets](), [kiro](), [mcp-server](), [model-context-protocol](), [model-context-protocol-mcp](), [open-source]() ### AI overview AWS introduces an open-source Model Context Protocol server for the Registry of Open Data on AWS. It lets compatible AI assistants search datasets, inspect metadata, explore bucket contents, and sample files, helping researchers evaluate data through a conversational workflow. ### Source excerpt Today, we are launching an open source Model Context Protocol (MCP) server that brings AI-powered dataset discovery to Registry of Open Data on AWS (RODA). As of today, RODA hosts over 1,100 high-value datasets from more than 400 organizations, spanning satellite imagery, life sciences, climate, geospatial, and more. Ask a research question in Kiro, Claude [...] ## Building a Stateful IT Service Desk Agent with LangGraph on Amazon EKS DevFeed: [Building a Stateful IT Service Desk Agent with LangGraph on Amazon EKS]() Original publisher: [Read original article]() Author: Sunil Ramachandra Published: 2026-06-26T14:16:08Z Content type: tutorial Language: en Sources: [AWS Open Source Blog]() Topics: [AI Agent](), [Amazon EKS](), [Kubernetes](), [Amazon DynamoDB](), [Persistence](), [FastAPI](), [OpenTelemetry](), [Orchestration](), [autoscaling](), [Graphs](), [tracing](), [Open Source]() Tags: [ai-agent](), [amazon-dynamodb](), [amazon-eks](), [amazon-elastic-kubernetes-service](), [autoscaling](), [backend](), [graphs](), [kubernetes](), [open-source](), [opentelemetry](), [orchestration](), [persistence](), [tracing]() ### AI overview This article presents a stateful IT service desk AI agent built with LangGraph. It autonomously handles routine Level 1 support requests, escalates complex issues with context, persists state in Amazon DynamoDB, and uses Amazon EKS, FastAPI, OpenTelemetry, and Kubernetes autoscaling. ### Source excerpt IT support teams face a persistent challenge: employees expect instant answers to common questions (VPN setup, single sign-on troubleshooting, new-hire onboarding), but novel or complex issues still require human expertise. An AI agent that confidently answers, "How do I reset my VPN?" but hallucinates a response to "My IAM Identity Center session keeps expiring after [...] ## Open Governance for MySQL: A Step Forward for the Community DevFeed: [Open Governance for MySQL: A Step Forward for the Community]() Original publisher: [Read original article]() Author: Pravin Mittal Published: 2026-06-25T17:14:14Z Content type: opinion Language: en Sources: [AWS Open Source Blog]() Topics: [MySQL](), [Databases](), [Open Source](), [Amazon Web Services](), [GitHub]() Tags: [announcements](), [aws](), [collaboration](), [community](), [contributors](), [github](), [mysql](), [open-source]() ### AI overview AWS explains Oracle's new community governance model for MySQL, including defined roles for contributors, committers, project leads, and a Steering Committee. The post presents open governance and a public GitHub presence as ways to broaden participation and support MySQL's long-term development. ### Source excerpt MySQL -- the open source database behind millions of applications worldwide -- is opening a new chapter. Today, Oracle announced a community governance model for MySQL that creates pathways for the broader community to participate in the project's development and direction. This post explains why AWS supports this move and what it means for the [...] ## Governing AI Assets at Scale with MCP Gateway and Registry DevFeed: [Governing AI Assets at Scale with MCP Gateway and Registry]() Original publisher: [Read original article]() Author: Amit Arora Published: 2026-06-17T16:24:44Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [Model Context Protocol](), [MCP Server](), [Agent Skills](), [Artificial Intelligence](), [Authorization](), [Security](), [observability](), [React](), [GitHub](), [GitLab](), [bitbucket]() Tags: [agents](), [ai](), [mcp](), [observability](), [open-source](), [react](), [security](), [skills](), [workflows]() ### AI overview MCP Gateway and Registry is an open-source Apache 2.0 system for governing and discovering enterprise AI assets, including MCP servers, AI agents, agent skills, and custom entities. It combines a human-facing catalog with machine-readable discovery for AI agents, while providing access control, security scanning, observability, audit logging, semantic search, and centralized MCP server routing. ### Source excerpt Enterprises that onboard AI assets (MCP servers, agents, skills, and multi-step workflows) need to govern these assets and make them discoverable without blocking innovation. Central IT maintains a list of approved MCP servers and skills for the organization. Each line of business also publishes its own assets to its team, and often to the wider [...] ## Introducing Trusted Remote Execution: Policy-Enforced Scripts for AI Agents and Humans DevFeed: [Introducing Trusted Remote Execution: Policy-Enforced Scripts for AI Agents and Humans]() Original publisher: [Read original article]() Author: Nick MacDonald Published: 2026-05-04T15:34:36Z Content type: release Language: en Sources: [AWS Open Source Blog]() Topics: [AI Bots](), [SDKs]() Tags: [agent](), [agentic](), [agents](), [ai](), [ai-agents](), [case-study](), [code](), [logs](), [model](), [open](), [open-source](), [operations](), [policy](), [production](), [remote](), [review](), [safety](), [sandboxes](), [scripting](), [software]() ### AI overview Trusted Remote Execution (Rex) is an open-source scripting runtime that authorizes each host operation against a Cedar policy. It is designed to give service owners runtime control over scripts generated by AI agents or used by humans. ### Source excerpt Today, we're announcing Trusted Remote Execution (Rex, for short) -- an open source scripting runtime where every system operation is authorized by policy. Scripts are written in Rhai, a lightweight language with no built-in system access. The only way to reach the host is through operations Rex explicitly provides, which are authorized against a Cedar [...] ## Decoupling Authorization at Scale: MongoDB Atlas and Cedar-Based Resource Policies DevFeed: [Decoupling Authorization at Scale: MongoDB Atlas and Cedar-Based Resource Policies]() Original publisher: [Read original article]() Author: Sergio Ariel de la Campa Published: 2026-04-23T15:49:59Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [Authorization](), [MongoDB](), [Security](), [Architecture & Design](), [Provisioning](), [Software as a service](), [Amazon Web Services]() Tags: [database](), [enterprise](), [infrastructure](), [open-source](), [policy](), [saas](), [security]() ### AI overview The article explains how MongoDB Atlas uses Cedar-based resource policies to decouple authorization logic from application code. It discusses role- and attribute-based access control, policy verification, centralized governance, and enforcement across multi-tenant database deployments and cloud providers. ### Source excerpt As organizations scale applications, managing authorization becomes increasingly complex. What starts as role-based permissions quickly evolves into intricate rules spanning multiple services, regions, and compliance requirements. Traditional approaches of embedding authorization logic in application code lead to fragmented policies scattered across codebases, making them difficult to maintain, audit, and scale. These challenges have become more [...] ## Deploying cloud-based engineering workbenches with the Virtual Engineering Workbench on AWS DevFeed: [Deploying cloud-based engineering workbenches with the Virtual Engineering Workbench on AWS]() Original publisher: [Read original article]() Author: Andrea Meroni Published: 2026-04-21T21:38:49Z Content type: tutorial Language: en Sources: [AWS Open Source Blog]() Topics: [Deployment](), [Embedded Software Dev](), [Amazon API Gateway](), [Domain-driven design (DDD)](), [Authorization]() Tags: [amazon-api-gateway](), [amazon-dynamodb](), [amazon-eventbridge](), [aws](), [aws-lambda](), [cloud](), [deployment](), [design-patterns](), [embedded](), [open-source](), [react](), [serverless]() ### AI overview A tutorial for deploying the open-source Virtual Engineering Workbench on AWS. It describes a self-service platform for publishing and provisioning preconfigured development environments, its serverless architecture, and creating and launching a workbench. ### Source excerpt Introduction Organizations in automotive, manufacturing, and embedded systems increasingly rely on cloud-based development environments to reduce hardware dependency and accelerate software delivery. As vehicle architectures shift toward software-defined platforms, engineering teams need access to specialized toolchains, virtual hardware models, and simulation environments that are consistent across sites and reproducible across projects. Provisioning these environments manually [...] ## OCSF Achieves ITU Support: Powering AI-Ready Security Operations DevFeed: [OCSF Achieves ITU Support: Powering AI-Ready Security Operations]() Original publisher: [Read original article]() Author: Rod Wallace Published: 2026-03-24T16:48:50Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [Security](), [AI-Ready Data](), [Open Source](), [Cybersecurity](), [Artificial Intelligence](), [data](), [Detection engineering](), [Programming]() Tags: [ai](), [ai-ready-data](), [algorithms](), [black-hat](), [cybersecurity](), [data](), [logs](), [machine-learning](), [open-source](), [security]() ### AI overview OCSF is presented as a vendor-neutral, open source security-data standard supported for ratification by the ITU. By normalizing logs from data centers, cloud environments, and SaaS applications into a common language, it creates AI-ready data for correlation, pattern detection, and more effective security operations. ### Source excerpt The security industry stands at an inflection point. In November 2024, the Open Cybersecurity Schema Framework (OCSF) joined the Linux Foundation, cementing its role as a vendor-neutral, open source standard for the global security community. Last summer at Black Hat 2025, we showed you how OCSF was powering AI-driven security operations. Then in December 2025, [...] ## AWS and Others Invest $12.5M to Defend the Open Source Ecosystem from AI Threats DevFeed: [AWS and Others Invest $12.5M to Defend the Open Source Ecosystem from AI Threats]() Original publisher: [Read original article]() Author: Mark Ryland Published: 2026-03-17T16:09:55Z Content type: news Language: en Sources: [AWS Open Source Blog]() Topics: [Vulnerabilities](), [AI Chat]() Tags: [ai](), [ai-models](), [announcements](), [anthropic](), [aws](), [foundation-models](), [generative-ai](), [google](), [maintainers](), [microsoft](), [open-source](), [openai](), [security](), [supply-chain](), [vulnerability]() ### AI overview AWS, Anthropic, Google, Microsoft, and OpenAI announced $12.5 million in Linux Foundation funding to help open source projects validate real AI-assisted vulnerability reports, remediate issues, and filter low-quality submissions. ### Source excerpt AWS, Anthropic, Google, Microsoft, and OpenAI today announced a joint $12.5 million investment with the Linux Foundation to help open source projects address a surge in AI-enhanced and AI-generated security vulnerability reports. Both the Alpha Omega initiative and the Open Source Security Foundation (OpenSSF) will receive funding through the Linux Foundation grants. Software security is at [...] ## Introducing Strands Labs: Get hands-on today with state-of-the-art, experimental approaches to agentic development DevFeed: [Introducing Strands Labs: Get hands-on today with state-of-the-art, experimental approaches to agentic development]() Original publisher: [Read original article]() Author: Joy Chakraborty Published: 2026-02-23T18:24:30Z Content type: release Language: en Sources: [AWS Open Source Blog]() Topics: [AI, ML & Data Engineering](), [SDKs]() Tags: [agentic-ai](), [agents](), [ai-development](), [github](), [open-source](), [physical-ai](), [python](), [robots](), [strands-agents](), [typescript]() ### AI overview AWS introduces Strands Labs, a separate GitHub organization for experimental agentic AI projects built around the open-source Strands Agents SDK. Its launch projects include Robots, Robots Sim, and AI Functions. ### Source excerpt We're introducing Strands Labs, a new Strands GitHub organization designed to give developers the ability to get hands-on with experimental, state-of-the-art approaches to agentic AI development. The Strands Agents SDK - available for both Python and TypeScript - has gained incredible traction in the developer community since we released it as open source in May [...] ## Cedar Joins CNCF as a Sandbox Project DevFeed: [Cedar Joins CNCF as a Sandbox Project]() Original publisher: [Read original article]() Author: Lara Langdon Published: 2025-12-15T18:21:10Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [Access Control](), [Open Source](), [Authorization](), [Cloud Native Ecosystem](), [SDKs](), [Automated reasoning](), [Lean](), [Rust](), [Testing]() Tags: [authorization](), [automated-reasoning](), [cloud-native](), [cncf](), [open-source](), [rust](), [sdk](), [security-identity-compliance](), [testing](), [verification]() ### AI overview Cedar, an open source authorization policy language and SDK, has joined the Cloud Native Computing Foundation as a Sandbox project. The article explains Cedar's purpose-built approach to fine-grained access control, its support for RBAC, ABAC, and ReBAC, and its focus on performance, analyzability, and safety through formal verification and differential testing. It also describes adoption by organizations including Cloudflare, MongoDB, StrongDM, Cloudinary, and AWS services. ### Source excerpt Cedar, an open source authorization policy language and SDK, has joined the Cloud Native Computing Foundation (CNCF) as a Sandbox project. CNCF provides a neutral home for early stage and developing open source projects. Cedar fulfills the need for a fast, safe, and analyzable authorization policy language in cloud-native environments by allowing developers to define, [...] ## Building intelligent physical AI: From edge to cloud with Strands Agents, Bedrock AgentCore, Claude 4.5, NVIDIA GR00T, and Hugging Face LeRobot DevFeed: [Building intelligent physical AI: From edge to cloud with Strands Agents, Bedrock AgentCore, Claude 4.5, NVIDIA GR00T, and Hugging Face LeRobot]() Original publisher: [Read original article]() Author: Arron Bailiss Published: 2025-12-12T21:03:04Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [AI Bots]() Tags: [ai-agents](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [artificial-intelligence](), [best-practices](), [cloud](), [edge](), [embedded](), [generative-ai](), [inference](), [jetson](), [latency](), [nvidia](), [open-source](), [physical-ai](), [robotics](), [strands-agents](), [technical-how-to]() ### AI overview An AWS article explores physical AI agents that combine cloud reasoning with low-latency edge execution. It demonstrates a robotic arm and a quadruped robot controlled through Strands Agents on NVIDIA Jetson hardware. ### Source excerpt Agentic AI systems are rapidly expanding beyond the digital world and into the physical, where AI agents perceive, reason, and act in real environments. As AI systems increasingly interact with the physical world through robotics, autonomous vehicles, and smart infrastructure, a fundamental question emerges: how do we build agents that leverage massive cloud compute for [...] ## Shaping the future of MCP: AWS's commitment and vision DevFeed: [Shaping the future of MCP: AWS's commitment and vision]() Original publisher: [Read original article]() Author: Nick Aldridge Published: 2025-12-09T17:09:35Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [AI, ML & Data Engineering](), [AI-assisted coding]() Tags: [ai-agents](), [amazon-bedrock-agentcore](), [anthropic](), [artificial-intelligence](), [aws](), [generative-ai](), [linux](), [mcp](), [open-source]() ### AI overview AWS outlines its continued support and contributions to the Model Context Protocol as it moves under Linux Foundation governance. The article highlights MCP capabilities including asynchronous Tasks, Elicitations, and structured tool output. ### Source excerpt AWS is excited to continue our support for Model Context Protocol (MCP) as it moves under the Linux Foundation. This move enables us, our partners, and our customers to be more confident in the long-term success of the protocol which has become a standard component of agentic architectures. By open sourcing MCP in 2024, Anthropic [...] ## Introducing Strands Agent SOPs - Natural Language Workflows for AI Agents DevFeed: [Introducing Strands Agent SOPs - Natural Language Workflows for AI Agents]() Original publisher: [Read original article]() Author: James Hood Published: 2025-11-20T21:34:48Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [AI Bots](), [Language models]() Tags: [agents](), [ai](), [ai-agents](), [language-models](), [open-source](), [orchestration](), [workflows]() ### AI overview The article introduces Agent SOPs, a standardized Markdown format for defining AI-agent workflows in natural language. It presents them as a middle ground between code-defined workflows and model-driven orchestration, intended to make agent behavior more reusable and steerable. ### Source excerpt Modern AI can write code, compose symphonies, and solve complex reasoning problems. So why is it still so hard to get them to reliably do what you want? Building reliable AI agents that consistently perform complex tasks remains challenging. While modern language models excel at reasoning and problem-solving, translating that capability into predictable workflows often [...]