agentic workflows

Evidence (19)

• 7The New Stack·8/25/2026research
  Telemetry costs surge as AI agents hit production

  Enterprises are seeing telemetry and observability costs rise sharply as autonomous AI agents generate far more traces, model calls, and tool interactions than conventional applications. The article says many organizations have delayed or canceled deployments because monitoring bills are becoming difficult to predict and justify, especially in high-stakes use cases like cybersecurity and fraud detection.

• 7The New Stack·8/25/2026research
  AI agents outpace enterprise sovereignty controls

  A new IDC survey commissioned by Cohere says AI agents are already widely used in large enterprises, but understanding of sovereign AI and the controls needed to govern them remains limited. The report highlights gaps in observability, access controls, and deployment control as agents begin interacting directly with company systems and data.

• 6InfoQ·8/22/2026open_source
  AWS Releases aws-bench for Evaluating AI Agents on Cloud Tasks

  AWS has open-sourced aws-bench, a benchmark designed to test AI agents on real AWS tasks such as fixing misconfigurations and provisioning infrastructure. It runs in disposable AWS accounts and uses automated verifiers to score agent performance.

• 7Hacker News·8/21/2026security
  Felony Bench ranks AI agent security incidents

  Felony Bench is a benchmark that scores AI models and agents by the number of illegal or harmful real-world incidents they have been associated with, rather than by task performance. The page lists recent cases involving Anthropic, OpenAI, Meta, Google, and Moonshot, and explains that only unique incidents affecting third parties are counted.

• 3Martin Fowler·8/19/2026research
  Citizens build, agents execute, experts govern

  Martin Fowler argues that AI has made it much easier for non-technical people to create working software, but that this is not the same as building enterprise-grade systems. He emphasizes that experienced engineers remain essential for design, governance, risk management, and long-term maintainability when software enters production.

• 6InfoQ·8/18/2026open_source
  Netflix Open Sources Agentic Workflow for Causal Inference

  Netflix has open-sourced an agentic workflow for observational causal inference to reduce manual effort in causal analysis. Using observational data and a human-provided analysis plan, the system applies an actor-critic loop to estimate causality, generate a report, and recommend next steps.

• 5InfoQ·8/17/2026research
  Grab Reduces Mechanical Analytics Work with AI Agents

  Grab says it is using AI agents to automate analytics workflows, reducing mechanical analyst work from 44% in February to 30% in June. The system combines agent autonomy, certified data, context management, and human oversight, with self-service analytics handling more metric, data, and SQL requests without analyst intervention.

• 5The New Stack·8/13/2026research
  Why AI pipelines can cost far more after launch

  The article argues that AI application costs often rise sharply in production because token usage grows with prompts, history, retrieval, tool output, and multi-step agent workflows. It says the biggest savings usually come from reducing unnecessary tokens through better architecture, prompt design, caching, routing, and memory management rather than simply switching to a cheaper model.

• 5InfoQ·8/8/2026research
  OpenAI Uses Always-On Agents to Keep ChatGPT Fast

  Martin Spier describes how agentic workflows at OpenAI have sharply increased the volume and pace of code changes. He says the company is using always-on AI agents to automate profiling, regression detection, and continuous optimization to preserve performance at global scale.

• 5The New Stack·7/31/2026framework_update
  Thoughtworks Engineer Says AI Software Needs Human Oversight On the Loop

  Thoughtworks distinguished engineer Kief Morris argues that teams using AI to build software need humans “on the loop” to define what counts as good code and good systems. He says production-ready CI/CD, tests, and guardrails must be built into agentic workflows now to keep software safe, secure, and maintainable. The article frames continuous delivery practices as the way to control AI agents rather than relying on post-hoc fixes.

• 7Hacker News·7/29/2026model_release
  GPT-5.6 boosts intelligence efficiency

  OpenAI says GPT-5.6 improves efficiency across models, inference, and agentic workflows. The update is positioned to deliver more useful intelligence per dollar.

• 6OpenAI Blog·7/16/2026product_launch
  Cars24 expands AI voice and chat operations

  Cars24 says it uses OpenAI-powered voice and chat agents to manage more than 1 million monthly conversation minutes across its business. The company reports that these systems helped recover 12% of lost leads and enabled faster, more agentic workflows for internal teams.

• 7Hacker News·7/6/2026research
  Anthropic’s Compute Spend Surpasses Payroll

  The article argues that Anthropic now spends about 2.3 times its payroll on compute, highlighting a cost structure where inference and training dominate staffing costs. It compares this with broader software-market AI spending and projects three possible paths for how per-engineer AI costs could evolve by 2029.

• 4InfoQ·6/29/2026security
  Virtual Panel on Evolving AI Security Threats

  This virtual panel features AI security experts discussing how threats are evolving as AI systems become more autonomous and embedded in critical workflows. The conversation covers prompt injection, data poisoning, agent abuse, AI-driven social engineering, and the operational challenges of incident response.

• 5Hacker News·6/29/2026open_source
  Herdr: Terminal-based agent multiplexer

  Herdr is an open-source tool that lets users manage multiple AI agents from the terminal. It aims to multiplex agent interactions in a developer-friendly command-line workflow, making it easier to run and coordinate several agents at once.

• 7InfoQ·6/26/2026open_source
  Vercel Launches Eve Open-Source AI Agent Framework

  Vercel has released Eve, an open-source framework for building, deploying, and operating AI agents in production. It uses a filesystem-based project structure to organize agent instructions, tools, skills, subagents, communication channels, and scheduled tasks, aiming to reduce the supporting infrastructure developers need to build themselves.

• 6The New Stack·6/26/2026security
  The hidden identity challenge in AI agents

  The article argues that many AI agent projects fail security review because their identity and permission models are poorly defined. It recommends workload identities, short-lived credentials, brokered access, and full identity lineage to improve accountability, least-privilege access, and auditability.

• 6OpenAI Blog·6/25/2026research
  OpenAI Research on How AI Agents Are Changing Work

  OpenAI published a research paper examining how AI agents are being used to transform work across roles. The paper says these systems can handle longer and more complex tasks, which may expand productivity in professional settings.

• 4GitHub Blog·6/23/2026product_launch
  GitHub employee says automations improved leadership workflow

  A GitHub senior director describes how scheduled automations in the GitHub Copilot app helped her manage fragmented work across calendar, email, messages, and repositories. The article explains how agents, canvases, and integrations can surface priorities, prep meetings, and reduce context switching for leadership work.