16 articles tagged
Cognition's 21 August 2026 release streams integrated terminal activity and local user edits to third-party ACP agents by default, with no matching control in the documented admin settings tables.
Cursor's 19 August 2026 release runs each cloud subagent on its own VM. No machine-hour fee exists, so a five-way swarm costs roughly five times the tokens instead, and the docs restrict CI autofix to Teams.
GitHub published two Copilot launch posts on 21 August 2026 and two docs pages to match. They disagree on which plans qualify, what a session costs and whether the extra merge approval is on by default.
Zed's 1.16.1 release on 19 August 2026 switched the default model for OpenAI subscription users to GPT-5.6 Sol. Its hosted price table still carries OpenAI's pre-30-July rates for Terra and Luna, so the published Luna
Cursor now hosts code. Origin shipped in early beta on 17 August 2026 to Pro, Teams and Enterprise plans, but two Cursor doc pages contradict each other on who can claim your permanent namespace, and no pricing page
Google Cloud's DORA team models a 39% first-year return on AI-assisted development, then tells you not to treat it as a formula. What it assumes, the productivity dip it hides, and the cost line most rollouts miss.
Muse Code's contributor tier prices Muse Spark 1.2 at $0.10 per million input tokens against $1.25 on standard. The discount is real, and so is the second price: 50x fewer requests and a licence to train on your code.
Google announced a Play Policy Insights skill in the 15 July 2026 policy update, an open-source SKILL.md that grounds a coding agent in Play policy. It shares a name with an older Android Studio lint feature, and
GitHub will remove six models from every Copilot surface on 1 September 2026. The suggested replacements cost more per token, and Enterprise admins have to enable them first. Here is the map.
Antigravity is free for individuals and consumption-billed through Google Cloud, with no organisational tier by contract. Cursor sells seats from $32 to $120. Five gaps decide which one survives a rollout.
Teams want AI coding agents without betting on one vendor. This 2026 guide shows the harness pattern across Claude Code, Codex CLI, Gemini CLI and Copilot: what to standardize, the portability seams, and where costs
Anthropic's Claude Opus 5 matches near-Fable-5 intelligence at 26% lower cost per task. A guide to the coding-agent benchmarks, the token economics, and when Opus 5 should be your default.
AI coding studies contradict each other: 55% faster in the lab, 19% slower in a field trial. A senior engineer's playbook for measuring the real delivery impact of AI coding agents in 2026.
Microsoft's July 2026 study found adopters of Claude Code and Copilot CLI merged 24% more pull requests. The per-tool numbers, the dose-response curve and the paper's caveats matter more than the headline.
Cursor Automations, live since March 2026, run cloud agents on a timer or on events from Slack, GitHub, Linear and PagerDuty. This guide covers setup, six useful workflows, costs on Pro and Ultra, and guardrails.
Amazon Bedrock's new Mantle console connects Claude Code, Codex, Cursor and more to GPT, Claude and open-weight models with IAM or a Bedrock API key. Here is how to wire each coding agent through Bedrock.
