All news with #agentic ai tag

🛠️ Cloudflare describes how the Agents SDK provides durable execution, dynamic code execution, a durable filesystem, and dynamic workflows as platform primitives to run agent harnesses in production. The new Flue framework (1.0 Beta) builds on the Pi harness and targets Cloudflare Durable Objects to offer declarative agent development, integrations with Slack/GitHub/Discord, headless UI hooks, and Durable Streams for reliable checkpointing. Flue uses runFiber(), stash(), onFiberRecovered(), @cloudflare/codemode, and @cloudflare/shell to securely execute LLM-generated code, provide a virtual filesystem, and enable durable, resumable agent turns at low cost.

🛡️ Microsoft Security describes codename MDASH, a multi-model agentic scanning system built to discover, validate, and help remediate software vulnerabilities at enterprise scale. The system orchestrates specialized AI agents in a structured pipeline and integrates findings into Microsoft Defender, GitHub, and Azure DevOps workflows so issues become actionable engineering work. Early use across Windows, Azure, and identity teams uncovered numerous high-severity vulnerabilities before exploitation and helped raise CyberGym benchmark performance to 96.5%. The post reviews deployment lessons, failure modes, and planned improvements like fuzzing integration and broader artifact support.

🛡️ The Estonian AI Council proposes government-backed digital identities for AI agents to define delegated powers and responsibilities. Prime Minister Kristen Michal emphasized that clear attribution, rights, and accountability are essential as AI increasingly acts on behalf of people and organizations. The ID could specify permissions such as data viewing, document editing, or making payments with defined limits. Estonia aims to leverage its digital ID leadership and become the first country to formalize agent identities.

🤖 Amazon Quick receives major updates including autonomous agents, multi-dataset analytics, and a redesigned activity feed. Quick connects to common business apps and learns workflows to automate recurring tasks and reduce manual notifications. The multi-dataset analytics lets users query across sources like Snowflake and relational databases using natural language while inheriting semantics from catalogs such as AWS Glue and Databricks Unity Catalog. The updated activity feed provides a conversational, personalized workspace for approvals, messaging, and sharing Quick applications externally.

🛡️ Cloudflare announced the Cloudflare One stack, a pair of agent skills designed to automate planning, deploying, migrating, and managing Zero Trust environments. The toolkit packages Cloudflare’s institutional migration expertise into two skill files — cloudflare-one and cloudflare-one-migration — to assist with VPN replacement, Gateway policies, connectivity, vendor-to-vendor translation, and troubleshooting. When paired with the Cloudflare code mode MCP server, agents gain typed, controlled access to the Cloudflare API for live inventory, configuration inspection, and curated change workflows.

🚀 Amazon Bedrock AgentCore announces general availability of its managed agent harness, enabling teams to deploy production-grade agents in minutes. The harness handles orchestration, tool execution, session isolation, persistent memory, failure recovery, and context management so customers define agents via configuration rather than coding the loop. It supports any model, mid-session model switching, integrated security and observability, and exports to code for custom orchestration, and is available today in all AWS Commercial Regions where AgentCore is offered.

🔍 AWS announces new AgentCore optimization capabilities that turn production traces into continuous agent improvements. The features surface failure, intent, and trajectory insights across sessions to reveal silent and recurring failures, then generate data-grounded recommendations for prompts and tool descriptions. Batch evaluation and A/B testing validate fixes against defined metrics before rollout, and capabilities work across AgentCore runtime, Lambda, EKS, and non-AWS environments.

🔒 AWS Secrets Manager introduces a secret safety skill in the aws-core plugin for the Agent Toolkit for AWS, enabling AI coding agents to use secrets without exposing values to models or session logs. The skill prevents models from requesting raw secret values and prompts developers to clarify intent while constructing commands that reference secrets. A child process resolves secret references at execution time, keeping plaintext secrets out of agent context and logs. The feature is available across supported agent harnesses and Regions where Secrets Manager is offered.

🔍 AWS Transform now provides a model-to-model migration custom transformation that evaluates generative AI workloads and generates a migration plan to Amazon Bedrock. The agent scans codebases to identify AI SDKs and models, collects migration requirements interactively, and maps models to Bedrock equivalents with cost comparisons and production-ready code changes. It preserves application architecture while recommending routing, caching, and Bedrock integrations for secure, consolidated deployment.

🛠️ Siemens and Google Cloud built Knowledge Fabric, an AI system using knowledge graphs on Spanner Graph, the Google Agent Development Kit, and LLM APIs to modernize large industrial codebases. The platform models code relationships with GQL, uses embeddings and ANN for semantic search, and combines full-text search to deliver precise impact analysis. By "slicing the elephant," agentic workflows break large refactors into smaller tasks with human oversight, reducing engineering effort and preserving system integrity.

🔒 Palo Alto Networks and Databricks announce an integrated runtime security solution to protect agentic AI across the enterprise. The partnership embeds Prisma AIRS into the Databricks Unity AI Gateway to provide centralized governance, real-time inspection, and policy-driven enforcement for prompts, tool calls, and model interactions. This approach aims to prevent prompt injections, data exfiltration, and malicious tool usage while enabling faster, secure AI deployments.

🤖 Starting today, AWS Partner Central agents qualify every co-sell opportunity in real time and make actionable recommendations to accelerate AWS engagement and deal progression. Building on agents released March 16, 2026, the agent can act on the partner's behalf via conversation to enrich opportunity details, removing manual review delays. Each opportunity now receives an Opportunity Quality Score and is matched to a co-sell motion—AWS field-engaged, Agent-engaged, or Partner-led—with the score and motion recalculated in real time as recommendations are applied.

🤖 AWS Marketplace introduces AI-assisted product listing within the Partner Assistant chat to help Independent Software Vendors (ISVs) and Consulting Partners create optimized product listings using existing digital assets. The assistant imports content from websites, PDFs, case studies, and documentation, then generates, validates, and formats listing fields to meet AWS Marketplace requirements and improve search discoverability. Field-level recommendations and a quality score help partners align listings with best practices. Available via AWS Partner Central, the AWS Marketplace Management Portal, and programmatically through the Partner Agent MCP server; not available in AWS GovCloud (US) or China Regions.

🔔 AWS Partner Central introduces Business Value Realization (BVR), a new experience and funding motion that helps partners drive customer adoption and measurable business outcomes after deploying strategic AWS services. Partners can self-enroll, nominate customer opportunities, and monitor progress through defined adoption stages with guided activities. AI agents generate weekly adoption reports highlighting progress, risks, and recommendations, while funding is automatically disbursed when stages are completed.

🤝 Today AWS announced general availability of onboarding agents for AWS Partner Central. The agent serves as an always-available advisor that guides new partners through profile setup, verifications, tax and payment setup, compliance, and preparing listings on Marketplace. Partners can interact with the agent in the AWS Partner Central console or programmatically via Model Context Protocol (MCP). The agent auto-populates partner profiles using company website data and provides a personalized roadmap to accelerate readiness to sell with AWS.

🤖 Google announces expanded Agentic Data Cloud capabilities, introducing new data agents and tools to enable conversational analytics and agent-driven workflows across BigQuery, Lakehouse, AlloyDB, Spanner, and Cloud SQL. The update includes Data Engineering, Data Science, Database Observability, Looker Dashboard, Data Insights, and Deep Research agents, plus developer toolkits like the Data Agent Kit and Managed MCP servers. These features aim to ground agents in real-time enterprise data with unified governance and near-100% accuracy for tasks such as NL-to-SQL conversions and automated pipeline maintenance.

🧭 This post describes how Yahoo and Google Cloud built Seller Agent, an agentic media-buying platform that collapses multi-week manual workflows into governed campaigns executed in seconds. The architecture uses a dual-graph approach — a knowledge graph for deterministic business logic and a context graph for auditable decision traces — combined with Google Cloud services like Spanner Graph, BigQuery Graph, and Gemini. The design emphasizes explainability, regulator-grade governance, and closed-loop learning to ensure autonomous actions remain transparent and accountable.

🟢 AWS Partner Central now offers lead enrichment and prospecting, letting AWS Partners enrich AWS-sourced or partner-sourced leads with AWS-generated propensity insights and recommendations for program, funding, and sales motion eligibility. Partners can upload leads in the console or programmatically via the AWS Partner Central API. Each enriched lead returns propensity-to-buy signals, Marketplace purchase likelihood, solution-category alignment, and eligibility for programs like Partner Greenfield Program and Pioneer Credits. The feature is available to ACE-eligible Partners in the US East (N. Virginia) Region.

🔒 European enterprises tested sovereign cloud under regulatory pressure and found residency alone doesn’t equal control. Vendors offer sovereignty features, but practitioners at EIC 2026 emphasized that identity governance — not just data location — determines operational sovereignty for AI workloads. Weak identity controls, especially for non-human AI agents, undermine claims of control despite customer-managed keys or regional data centers.

📘 Today Google Cloud introduces the Open Knowledge Format (OKF), an open, vendor-neutral specification that formalizes the LLM-wiki pattern into a portable directory of markdown files with YAML frontmatter. OKF v0.1 defines a small set of conventions so different producers’ wikis can be consumed by agents without translation. The spec is intentionally minimal — one required type field per concept — and is accompanied by reference producer and consumer implementations and sample bundles.