Find published research by company, product, platform or technology.
Showing 1–20 of 303 dossiers
Copilot code review now moves from advisory assessment toward a governed merge gate. The public preview remains off by default, and GitHub’s current docs let administrators separate AI approval itself from whether that approval counts toward required-review policy.
A detailed engineering case study links a 68% AI-review cost reduction to prompt-cache structure and effort tuning, with security-review trade-offs still unresolved.
GitHub has moved local Copilot sandboxes from preview to GA. Enterprises can now combine centrally managed approval policies with operating-system-enforced limits on what coding agents can actually reach.
The useful boundary change is that Copilot can now cross from code and terminals into ordinary desktop interfaces, with per-app approval and organisation-level controls.
The useful part is not the 800,000-line headline. GitHub has published unusually detailed receipts for a production-scale agent-assisted migration: roughly $120,000 of token spend, 14.5 weeks of incremental releases, dozens of regressions, extensive compatibility tests and a workload-specific jump from 7.55 to 120 session lifecycles per second.
The material change is that model routing is no longer a single opaque optimization target. Developers can now tell Copilot whether to bias Auto toward lower cost, a middle ground or higher quality while GitHub still chooses a model prompt by prompt.
The technical-preview feature separates Copilot CLI from GitHub Cloud for core coding, shell and repository workflows, giving regulated and isolated environments a supported agent path while leaving cloud-dependent capabilities such as GitHub-hosted model selection and web search unavailable.
From September and October, Copilot Business and Enterprise seat access becomes more tightly coupled to upfront payment. A separate September 28 policy migration enables a unified Copilot experience by default, retains github.com chat data for the life of the account and changes code review’s default effort from Lite to Balanced.
GitHub Copilot can now turn Slack or Teams threads into collaborative cloud-agent sessions. Teammates can add context and steer the work in public, while repository permissions, agent budgets and optional extra PR approvals remain the main control boundaries.
Stacked pull requests are now generally available on GitHub. The shift matters as coding agents make large changes faster than humans can safely review them: teams can keep one coherent change dependency-ordered while reviewing it as smaller PRs.
The interesting change is above the model picker: Copilot can now choose an execution workflow, not merely a model, and can spend extra model calls selectively when a task appears to need them.
AI image and social-app developers face clearer moderation and review obligations; hiding features can threaten an entire developer account.
The platform now offers an objective-oriented /goal interface as well as Custom Flows; availability depends on GitLab 19.3+, Duo CLI 9.17+ and eligible tiers.
OpenAI's agent containment story has moved beyond RubyGems: a rolling review is finding access-control bypass, credential use, command injection, runtime access and agent spam across third-party services.
The important change is enforcement. WordPress.org already had a release cooldown and automated scanning, but high-risk results can now stop a plugin update automatically instead of waiting for the Plugins Team to intervene.
The staged release is complete: GLM-5.3’s public weights and serving artifacts are now available. That makes Z.ai’s coding and cyber-capability claims independently testable while turning the earlier safety delay into a concrete self-hosting and audit decision.
A hard shutdown date makes this more than a hosting refresh: unmigrated Codeberg Pages sites will go offline, and the replacement changes deployment and URL behaviour.
Two distinct access paths matter more than the benchmark headlines: Muse Wonder is available through Meta Model API and Muse Code, while Wonder Full is currently subscriber-only in Muse Code.
Rashomon's experimental local recorder can expose discrepancies between a coding agent's closing claims and its tool execution. It is an observability aid, not a sandbox or tamper-proof security product.
Pi’s first stable release is interesting less for another coding-agent version number than for what its deliberately minimal core now considers mature enough to include: MCP, code-driven tool orchestration and model routing.