Devlery - AI news for builders
Devlery blog
AI news for builders.
Review comments become run buttons in Copilot Agent Merge
GitHub Copilot app, low-cost model routing, Fix batch, and Agent Merge are turning PR review into an agent execution loop.
Goal Mode by default, Codex targets agent waiting time
OpenAI Codex Goal Mode and locked computer use move the coding-agent bottleneck from prompts toward goals, context, approvals, and policy.
Agents Need PCs Too, and Windows 365 Defines the Isolation Layer
Windows 365 for Agents isolates AI agent execution inside Cloud PCs and pairs with Agent 365 governance.
Antigravity 2.0, Google Turns the IDE Into an Agent Command Center
Google Antigravity 2.0 connects the IDE, CLI, SDK, Gemini API managed agents, and Android app generation into one agent operating surface.
Agents compiled into ABL, and the runtime bottleneck Kore.ai is targeting
Kore.ai Artemis frames enterprise agents as compiled ABL artifacts controlled by runtime governance, not loose prompt bundles.
OpenAI’s unit-distance proof puts AI research automation on the record
OpenAI’s counterexample to the Erdős unit-distance conjecture shows both the promise of AI research automation and the reproducibility gap left by an unnamed model.
SKILL.md is not documentation, it is the new signed supply chain
NVIDIA Verified Agent Skills treats agent skills as scanned, carded, and signed artifacts, pointing to a new supply-chain checkpoint for AI agents.
SageMaker opens an OpenAI-compatible door for enterprise LLM infrastructure
AWS SageMaker AI now supports OpenAI-compatible inference endpoints, moving enterprise LLM friction from model deployment toward API surfaces, IAM, and routing layers.
The 160ms Action Channel Voice Agents Need
The DuplexSLA paper reframes real-time voice-agent latency around a 160ms action channel where speech, planning, and tool calls share one timeline.
88-Core Vera Shows Agent Bottlenecks Moving To The CPU
NVIDIA Vera CPU deliveries show that AI agent competition is shifting beyond GPU inference toward CPU-bound sandboxes, tool calls, and RL evaluation.
DevTools 1.0 gives coding agents eyes on the browser runtime
Chrome DevTools for agents 1.0 moves coding-agent competition from code generation toward browser runtime validation, debugging, and safety.
40% of PRs now start in the cloud, Cursor shows the agent operating layer
Cursor Cloud Agent lessons show coding-agent competition moving from models alone to VMs, Temporal workflows, indexing, permissions, and self-healing operations.