Dev UX

In a randomized trial, Figma Make cut completion time by about 20% among finishers, with larger gains for product managers and less certain benefits for professional designers.

Vercel now exposes per-deployment billable duration and CPU minutes in its dashboard, CLI, and API, making agent-triggered build costs easier to inspect.

Algebraic RMSNorm changes can cut launch, memory, and wait overhead, but a CUDA stream race shows why inference optimizations need long-generation correctness tests.

Vercel CLI can return a live URL in under a second for small static artifacts, making agent-generated reports and prototypes easier to share without a build step.

Vercel’s CLI can now give coding agents searchable, machine-readable product updates, reducing stale recommendations about platform features.

Adobe’s prototype assembles intent-specific page blocks from existing site content in roughly a second, making model latency and per-site evaluation part of frontend architecture.

Ironclad argues against optimizing token volume or spend alone: measure reviewed, merged code and fix review and CI bottlenecks before judging coding-agent ROI.

Vercel CLI 59.6.2 adds agent-friendly control over DNS, domains, projects, observability, and membership, with JSON output and confirmation gates for risky actions.

Agents increasingly choose developer tools, so test whether your docs connect real user pain to your product—not merely whether comparison prompts mention it.

Vercel agents can now manage DNS, domains, project state, observability, and members through structured CLI commands, while purchases and destructive actions retain confirmation gates.

Replit’s Free Mode uses GPT-5.6 Luna to remove token-cost concerns from initial software creation, lowering friction for experimentation inside its agent workflow.

Cursor explains why Git hosting resists naive distribution: DAG walks and delta-packed files punish network round trips, favoring local NVMe replicas kept consistently in sync.

Vercel can now turn Cursor Origin pull requests into previews and merged changes into production deployments, giving agent-built repositories a conventional deploy loop.

GitHub Next’s prototypes move coding agents from personal chat into governed background workflows and shared cloud workspaces that can act on team conversation.

Cursor Start gives developers in India a ₹649 monthly tier with Grok 4.5, Composer, cloud agents, mobile control, and UPI payments, positioned between Free and Pro.

Sandstone pairs composable agent workflows with preview deployments and private data connectivity, showing the infrastructure a small team used to operate enterprise legal automation.

Chat SDK can put Claude Managed Agents behind browser and messaging interfaces while Anthropic retains the loop, tools, session state, and research sandbox.

Cursor's Bugbot is now 3x faster (90% of runs under 3 minutes), 22% cheaper, and finds 10% more bugs per review, powered by Composer 2.5. A new /review command runs it locally before you push.

Cursor's Design Mode lets you prompt agents visually in a running app: click or multi-select elements, draw annotations on a frozen frame, or narrate by voice; the agent gets each element's xpath, props, and styles.

Cursor shipped a native iOS app in public beta: launch cloud agents, remote-control agents on your local machine, and merge PRs from your phone. Paid plans only; Composer 2.5 runs are 75% off until July 5.

Cursor Enterprise adds organizations: a teams-within-org hierarchy with per-team budgets, model access controls, and spend and token analytics rolled up in one admin dashboard.

Meta's Diff Risk Score, a fine-tuned Llama model, predicts whether a code change will cause a production incident — used to replace blanket code freezes, landing 10,000+ changes during one 2024 freeze period.

OpenCode provides open-source terminal and desktop coding agents, with separate full-access and read-only modes plus a general-purpose subagent.

Claude Code handles codebase tasks and git workflows from the terminal, IDE, or GitHub, now favors native installers over npm, and supports plugins with custom commands and agents.

i-have-adhd is a coding-agent skill that enforces action-first, compact responses with numbered steps and a concrete next action. It is a useful prompt-policy example for reducing agent verbosity.

Cline now presents one open agent core across IDE, CLI, desktop, and SDK surfaces, with custom tools, persistent teams, schedules, and headless automation.

Claude Code Templates packages reusable agents, commands, hooks, MCPs, skills, and settings behind a CLI, plus session monitoring and diagnostics for managing agent setups.

Reasonix is a configurable terminal coding agent built to preserve DeepSeek prefix-cache reuse across long sessions, with optional planner/executor models and subprocess-based plugins.

Terminal multiplexer for coding agents: a real terminal per agent across Claude Code, Codex, Copilot and 15+ others, with blocked/working/done state in a sidebar, persistent sessions, and a socket API.

Codex offers one coding agent across the terminal, supported IDEs, a desktop app, and the web, with local CLI installs for major desktop platforms and ChatGPT-plan sign-in.

OpenAI's plugin lets you drive Codex from inside Claude Code—slash commands for code review, adversarial critique, and delegating or handing off tasks to Codex background jobs. ~629 stars today.

Tick Stock Panel is a self-hosted A-share research stack with screening, backtesting, monitoring, and an AI assistant whose 18 read-only tools expose auditable data calls.

Orca puts multiple CLI coding agents in isolated worktrees and adds shared monitoring, review, browser context, remote execution, and mobile steering.

macOS menu bar app showing live usage limits and reset countdowns for Claude Code, Codex, Cursor, and 57+ other AI coding providers, reusing your existing auth — no extra login. Includes a CLI for scripts and CI.

PI-Desktop packages coding agents, reviews, permissions, models, MCP, skills, and subagents into a local-first workspace, but its early-preview interfaces remain unstable.

Codex-X puts provider switching, prompt injection, session history, Skills, MCP, and TOML settings behind one cross-platform UI for people juggling multiple Codex setups.

vercel deploy --dry (CLI v54.17.2+) prints the framework and full file manifest a deploy would upload, as JSON when piped — a pre-deploy check agents can loop on without ever creating a deployment.

Vercel open-sourced konsistent, a deterministic CLI linter that enforces structural conventions in TypeScript repos — the folder/export patterns agents drift on that TypeScript and ESLint don't catch.

Vercel’s Flags SDK evaluates flag batches around 10x faster by reducing promise and microtask overhead; upgrade both packages and replace Promise.all with evaluate().

New vercel flags segments command lets you create and edit flag-targeting segments from the terminal; --json output makes targeting scriptable from CI and agent-driven pipelines.