AGENT INFRASTRUCTURE

OpenAI's model-misalignment reporting framework doubles as an agent operations template: incident intake, severity labels, and evidence-led disclosure.

Hermes Agent now supports Vercel AI Gateway and Vercel Sandbox. What shipped, how to switch, and why agent infrastructure is going bring-your-own.

Cloudflare is merging Workers AI and AI Gateway into one control plane with a unified /ai/ API, default gateways and shared credits. What changes for you.

Vercel Chat SDK durable approvals pause a Workflow SDK run until a human clicks Approve in chat, with one requestApproval call and a wait that survives deploys.

DeepSeek V4 Flash via Novita on Vercel AI Gateway was 90% off for Pro customers through August 11. The before/after cost math and the provider-pinning setup.

The v0 API is GA: send a prompt to Vercel's app-building agent, get a running app with an embeddable preview URL, then deploy it to Vercel in one more call.

Vercel AI Gateway spend budgets now cover teams and projects, with hard dollar limits, 50/75/100% email alerts and CLI defaults. How the three scopes compose.

Harness Handbook maps coding-agent behavior to code evidence. Why code search falls short when one behavior spans prompts, tools, state and permissions.

Image token compression cuts agent costs by rendering bulky context as images, but it is lossy. Where to use it, the byte-safety rule, and the evals it needs.

Agent sandbox architecture: how to pick a runtime boundary: filesystem isolation, network policy, secrets, snapshots and when shell access is overkill.

Agent workflows as code: why finite state machines with typed gates, validated evidence and controlled transitions beat prompt checklists for coding agents.

Oak rebuilds version control for AI coding agents with virtual workspaces and branch-per-session flows. Why Git is awkward for agents and what Oak must prove.

Agentic AI reliability is a systems problem. The Bayer and Thoughtworks PRINCE case study shows it comes from context routing, traces, evals and human review.

AI coding agents move the bottleneck from code generation to review queues, CI minutes, environment reliability and merge discipline. What teams must fix next.

Agent evals need baseline receipts: Hex's data-agent lab compares candidates against stable production baselines, keeps evidence and judges changes by behavior.

GitHub's latest agent workspace trend points at a boring but important primitive: agents need explicit filesystem contracts before they get more tools.

Claude Agent SDK credits split programmatic agent usage from subscription usage on June 15. What changed and how to budget agent work in separate lanes.

Ruflo is an agent meta-harness for Claude Code and Codex with plugins, memory, swarms and MCP tools. What it adds, and how much harness you actually need.

DD shipped six paid agent infra products for small teams in one day, at $20 a month each or $50 for the bundle. What each does and what is still alpha.

Ten private tools shipped overnight - observability, skills, hooks, prompts, and evals - aimed at the agent infrastructure gap small teams keep falling into.