New
How are you evaluating AI features in your ERP/CRM suites?
Vendors are bundling copilots into every suite. How are you deciding what to switch on, and how are you measuring value?
Topic
AI agents
525 stories in the last 90 days · 3 community threads
In short
AI agents are software that uses a language model to plan steps and call tools, such as searching systems, updating records or running code, to finish a task with limited supervision. Buyers care because an agent acts with real permissions: what it can reach, how its actions are logged and who approves the risky ones matter as much as how capable it is.
Written by Techarda editors · Updated · How we work
Latest stories
The newest AI agents stories from the last 90 days. Each one opens with our summary and a link to the original source.
Developer ToolsHow-to
How to continue a GitHub Copilot app session in VS Code
Learn how to move an agent session from the GitHub Copilot app into VS Code without losing the conversation, code changes, or working context.
Containers & Kubernetes
Meet Tigera at KubeCon + CloudNativeCon North America 2026
Ask a platform team how many AI agents are running in their clusters and you usually get a pause. Agents arrive through application teams, not platform teams. They call tools over MCP, invoke other agents...
Security
Your Next Insider Threat Won’t be Human: Securing AI Agents From the Outside in
Why the controls on an AI agent have to live outside of it, and what a security operations team can implement and maintain those controls. The new privileged user in your environment Security teams spent two decades learning how to work with the people they trust most. Domain admins, DBAs, finance approvers and contractors with VPN access all get a mature playbook: verified identity, scoped…
Containers & KubernetesHow-to
Developer’s guide to implementing MCP apps in Gemini
Enterprise assistants still respond mostly in text. However, that can break down for visual, multi-step work, where every adjustment costs another slow chat turn. MCP Apps ( SEP-1865 ) solves this. This open Model Context Protocol (MCP) extension pairs a tool with a live UI. In Gemini Enterprise , that UI renders directly in the chat flow inside a sandboxed iframe, and can expand to fullscreen or…
Data & Analytics
How Snowflake Built an Agent to Fix Broken Data Pipelines
Snowflake's data team built an AI agent that diagnoses monitored pipeline failure and opens a proposed fix in under 16 minutes. Here's how.
HPC & Accelerated Compute
NVIDIA Advances Agentic Security for Media, From European Public Service Broadcasting to Global Content Production
At a creative industry event that took place today in Berlin, hosted in collaboration with Adobe, Bertelsmann, NVIDIA and UFA, the latest advancements in intelligent media were on display. Key to the news: the European Broadcasting Union (EBU) is collaborating with NVIDIA to expand its sovereign framework with cloud, open models and integration […]
Security
Unmasking the robots: Why it’s critical to discover AI agent identities and how Tenable helps you secure them
Discover how to secure AI agents in your cloud environment with Tenable One Cloud Exposure. We explore Microsoft Entra Agent ID and provide essential best practices for robust agentic AI identity security. Key takeaways Understand your current maturity level and then build an appropriate action plan to secure your agent identities. Use your cloud providers’ native tools or Tenable One Cloud…
DevOps & Platform Engineering
Platform Beaver: How Port Runs Its Own Agentic SDLC on AI Agents
Platform Beaver brings Port's agentic SDLC to Slack, with AI agents handling bug triage, incident response, PR review and Q&A.
Earlier in the last 90 days
- What Is Data Access?Starburst · 19 Oct 2026
- Google named a Leader in the 2026 IDC MarketScape for Agentic AI PlatformsGoogle Cloud · 19 Oct 2026
- Day 0 support for Reflection’s Beam on Google Cloud: 5x faster perf with llm-d and NVIDIA DynamoGoogle Cloud · 17 Oct 2026
- Architecting autonomy: A design pattern for high-compute, governed agents in biotechGoogle Cloud · 17 Oct 2026
- Beam model by Reflection is now available on Amazon SageMaker JumpStart and AWS TrainiumAmazon Web Services · 17 Oct 2026
- From Containers to Sandboxes: Developer Trust in the Agentic EraDocker · 17 Oct 2026
- Four evaluation engineering lessons learned from building agent pluginsGoogle Cloud · 17 Oct 2026
- Powering Agentic Commercial<sup>™</sup>: <br>Latest Innovations in Veeva Vault CRM SuiteVeeva Systems · 17 Oct 2026
- How Kong Built an Agentic Engineering PlatformKong · 17 Oct 2026
- Agentic AI and You: What Makes AI Agentic?Dell Technologies · 17 Oct 2026
- Securing AI Agents from Discovery to Runtime: Check Point on Google Cloud’s Gemini EnterpriseCheck Point Software · 17 Oct 2026
- AI Coding Assistants: Trust Is the Attack SurfaceHarness · 16 Oct 2026
- Model Context Protocol gateway for Red Hat OpenShift is now generally availableRed Hat · 16 Oct 2026
- Web Search on Amazon Bedrock AgentCore expands to AWS GovCloud and 3 RegionsAmazon Web Services · 16 Oct 2026
- Arm at the OCP Global Summit 2026: How Arm AGI CPU is scaling agentic AI infrastructure from CPU to rackArm · 16 Oct 2026
- From Discovery to Remission: How Agentic AI Is Reshaping the Oncology ContinuumSnowflake · 16 Oct 2026
- AWS Transform for migrations is now available in Asia Pacific (Singapore)Amazon Web Services · 16 Oct 2026
- Muse Spark Open model now available on Amazon SageMaker JumpStartAmazon Web Services · 16 Oct 2026
- Be There for the Beginning: Celebrate the Launch of NVIDIA RTX SparkNVIDIA · 16 Oct 2026
- Adobe and NVIDIA Expand Collaboration to Speed Agentic CreationNVIDIA · 16 Oct 2026
- Build at AI Speed on CloudBees CI: MCP Router OAuth and Secrets Masking | CloudBeesCloudBees · 16 Oct 2026
- Bringing the borderless Lakehouse into the agentic era with innovations for GeminiGoogle Cloud · 16 Oct 2026
- Temporal Serverless Workers on Cloud Run: Scale workers ahead of demandGoogle Cloud · 16 Oct 2026
- AI in Platform Engineering: When Agents Join Your PlatformSpacelift · 16 Oct 2026
- Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt ModelsNVIDIA · 16 Oct 2026
- BigPanda has been recognized as a Niche Player in the 2026 Gartner® Magic Quadrant™ for AI Applications in IT Service Management reportBigPanda · 16 Oct 2026
- How Netflix Made AI Coding Agents More Efficient with JetBrains IDE IntelligenceJetBrains · 15 Oct 2026
- How to Set Up a Software Factory: Platform GuidePort · 15 Oct 2026
- Amazon Managed Workflows for Apache Airflow now offers AI agent skillsAmazon Web Services · 15 Oct 2026
- Tottenham Hotspur Launches Ask Spurs on AgentforceSalesforce · 15 Oct 2026
- VulnBump: Can AI Agents Fix Vulnerable Dependencies Without Breaking the Build?Snyk · 15 Oct 2026
- Introducing Evo Agentic AppSec: Security That Keeps Up With AI DevelopmentSnyk · 15 Oct 2026
- How to Build a Voice AI Agent with OpenAI's GPT-Live, Twilio Agent Connect, and TypeScriptTwilio · 15 Oct 2026
- Connect your agents to your software lifecycle with the GitLab MCP serverGitLab · 15 Oct 2026
- MCP Events support in Vercel Connect is now in public betaVercel · 15 Oct 2026
- What is agentic identity? Securing AI agents in 2026Twilio · 15 Oct 2026
- Unblock agentic software delivery with governed code reviewGitLab · 15 Oct 2026
- Threat Actor Abuses Agentic AI Pentesting Framework to Target South Korean Financial InstitutionsZscaler · 15 Oct 2026
- AI Agent Security Risks: What Can Go Wrong When Agents Act on Their OwnDocker · 15 Oct 2026
- Why Observability Needs a Context GraphSnowflake · 15 Oct 2026
- Which Agent Sandbox Scales? NVIDIA OpenShell vs. Agent Substrate | Solo.ioSolo.io · 15 Oct 2026
- Agents at the Edge: Extending AI Security Governance to Physical AI with DefenseClawCisco · 15 Oct 2026
- NVIDIA and Semiconductor Leaders Advance AI Across Chip Design and Manufacturing for AI-Defined FabsNVIDIA · 15 Oct 2026
- Steer Your Agents Until They Steer ThemselvesPostman · 15 Oct 2026
- 5 signs your technology estate isn’t ready for AI agentsFlexera · 15 Oct 2026
- AI Agents Are Becoming Part of the IT Environment. They Need to Be Managed That Way.LogicMonitor · 15 Oct 2026
- The best workstations for running agentic AI workflows locally in 2026Dell Technologies · 15 Oct 2026
- How Cloud-Based Agent Sandboxing Works in AirJetBrains · 14 Oct 2026
- Amp puts AI agents to work beyond code with OpenAI modelsOpenAI · 14 Oct 2026
- Securing the Mission at Machine Speed: Wiz AI Agents Arrive in Wiz for GovWiz · 14 Oct 2026
- What Is Agentic Analytics?Starburst · 14 Oct 2026
- From Enterprise to Earthshot: UK’s Ecosystem Moves From Ambition to Application With NVIDIANVIDIA · 14 Oct 2026
Showing the newest 60 of 525. The feed archive lists every story by month.
What practitioners are discussing
Stories say what companies announced. These threads are where people who work with AI agents compare notes.
New
Which workflow did you automate with an AI agent first, and did it stick?
We are hearing a lot about agent pilots and far less about agents still running six months later. What was the first use case, what guardrails did you need, and is it still in production?
New
Build vs buy for internal AI agents: framework or platform?
LangGraph/CrewAI-style frameworks versus packaged agent platforms from the big vendors. If you have tried both, where did each win on time-to-value, control and cost?
Companies in these stories
The active companies with the most AI agents stories in the last 90 days. It counts news coverage, not quality, market share or fit for your needs.
Related categories
Where AI agents sits among the categories Techarda covers. Each hub shows who is active, and each guide sets out how to evaluate vendors.
Terms to know
Plain definitions of terms that come up in AI agents stories, from the Techarda glossary.
Frequently asked questions
What is the difference between a chatbot, a copilot and an agent?
A chatbot answers questions. A copilot suggests actions inside an application while a person stays in control. An agent carries out a sequence of actions itself, calling tools and systems, and stops when it finishes or needs approval.
How should agents be given access to our systems?
Treat each agent like a service account: its own identity, the narrowest permissions that do the job, short-lived credentials and a full audit trail. Avoid letting an agent act with a person’s full access.
What is the Model Context Protocol?
The Model Context Protocol (MCP) is an open standard for connecting AI applications to tools and data through a common interface, so one connector can serve many assistants and agents. Each connector is also a route into your systems and needs access controls like any API.
Where do agents tend to go wrong?
Common failure points are vague instructions, tools that return unexpected data, loops that repeat the same step, and prompt injection, where text in a document or web page tries to redirect the agent. Testing with your own messy data shows these quickly.
Stories are filed under topics automatically from their headline and summary, so the odd one may sit in the wrong place. Spotted one, or a topic we should add? Email engage@techarda.com. All topics.