agent workflows

Anthropic has published a practical taxonomy for “loop engineering” in Claude Code, framing autonomous AI work not as a single prompt but as repeated agent actions governed by explicit stopping conditions. The company’s June 30 post identifies four loop types: turn-based, goal-based, time-based...

Shared grep, glob, and view tools initially increased Copilot code review’s cost and reduced useful comments. Reviewer-specific instructions—start with the diff, narrow with grep and glob, then view exact evidence—cut average cost by roughly 20% without producing a quality signal that GitHub...

Microsoft published its April 2026 Copilot Studio update on May 11, 2026, adding broader agent governance, richer workflow automation, connected app experiences in Copilot Chat, an expanded usage estimator, Work IQ previews, agent-to-agent communication, and early access to GPT-5.5 Reasoning in...

Microsoft’s new Azure Skills Plugin aims to close the gap between code that works on a developer’s laptop and code that actually runs, scales, and behaves correctly in a real Azure environment by packaging operational know‑how as executable skills paired with tool-backed MCP servers that let...

OpenAI has quietly begun building an internal code‑hosting platform intended to reduce its reliance on Microsoft’s GitHub, a move first reported by The Information and confirmed in multiple news summaries that describe the effort as an early, internally driven engineering project prompted in...

Microsoft’s internal Copilot builds now show signs of a unified “Tasks” experience that bundles scheduling, agent selection, and end-to-end automation into a single interface — and a recent TestingCatalog report suggests Microsoft is testing built-in Researcher and Analyst agents inside that...