Claude Code adds subagent and gateway controls: AI development is becoming a managed team

Claude Code's latest releases add controls for running several AI agents at once: pinning workflow agents to one model, subagent effort levels and policy settings for company-wide rollout. AI coding tools now behave like managed teams.

Look at the release notes for Claude Code over the first ten days of October and a pattern shows up. Almost none of the changes are about writing code better. They are about managing more than one AI agent at once.

Version 2.1.296 lets a team run every agent in a workflow on a single chosen model while other helper agents keep their own. Version 2.1.292 lets a requested effort level be set per helper agent. Earlier releases added background skills, session names you can attach to, and a policy setting in the Claude apps gateway, which an organisation uses to control how tools are rolled out across staff. These details come from Claude Code’s public changelog, as tracked by Releasebot.

OpenAI’s Codex command-line tool has moved in the same direction, with recent versions adding a command-centre view of agent history and managed Git worktrees, so several agents can work in parallel without colliding. Trade coverage this month describes Cursor, Claude Code and Codex settling into a layered stack rather than one winner.

What it means in plain English

AI-assisted development is no longer one clever assistant in one developer’s editor. It is a small team of agents, each with a job, a budget and a set of permissions, supervised by a human. That has three consequences for anyone commissioning software.

So what

When a supplier says “we use AI”, the useful follow-up is “how do you run it?” Look for a named process: which agents do what, who reviews, what is logged. Our approach to AI-assisted development keeps experienced engineers in charge of agents rather than the other way round. If you want that explained against your own project, start a project.

← All research

More research.

GitHub's Copilot metrics now count OpenCode and Claude Code traffic: who really uses which AI coding tool

On 23 October 2026 GitHub added a per-tool breakdown to the Copilot usage metrics API, so tools such as OpenCode and Claude Code are counted even without editor telemetry. It shows how mixed the AI coding tool stack inside software teams has become.

Read ›

GitHub Copilot retires Claude Opus 5 and GPT-5.6 Terra on 16 November: the model-churn bill for buyers

GitHub has announced that Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra leave every Copilot experience on 16 November 2026. For anyone commissioning AI-assisted development, model retirement is now a monthly event to plan around.

Read ›

GitHub Copilot now benchmarks how 'agent-first' your developers are against your industry

On 22 October 2026 GitHub added opt-in industry comparisons to its Copilot impact dashboard, ranking firms by share of agent-first developers and by the merge rate of agentic pull requests. Here is how to read the numbers when you are buying software.

Read ›

Apple's new bait-and-switch rule 2.5.19: what it means for AI-built and fast-shipped apps

On 16 October 2026 Apple updated its App Review Guidelines: apps that change after approval can be removed from the App Store and the Developer Program, and AI-generated intimate imagery is now explicitly covered. Here is what founders commissioning an iOS app should check.

Read ›

GitHub Copilot agentic autofix is generally available: AI now fixes security alerts, and bills for it

GitHub made agentic autofix for code scanning alerts generally available on 15 October 2026. Copilot can now fix up to 25 security alerts in one pull request, using AI credits your supplier or your team pays for.

Read ›

GitHub AI Scan for pull requests goes GA: AI security checks for PHP, Terraform and Dockerfiles

GitHub's AI Scan for pull requests became generally available on 15 October 2026, checking languages the standard scanner misses. Findings are advisory and cannot block a merge, which matters when you buy software.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work