Find published research by company, product, platform or technology.
Showing 21–40 of 298 dossiers
GitHub's 2026 platform data shows agent-started PRs rising sharply. The implications concern code review, security and multi-model workflows, not proof of higher software quality.
GitHub's gh-aw reaches GA, making Markdown-defined agent jobs a supported Actions workflow pattern. Security boundaries, model costs and privileged triggers still matter.
GitHub Apps can now authenticate Copilot SDK workloads without a user's credentials. Organisation admins control installation permissions, usage attribution and budgets.
WooCommerce 11.3 removes /wp-json/woocommerce/mcp, REST-key MCP authentication and REST-derived abilities. Migrate clients to the WordPress MCP Adapter plugin, application passwords and explicit ability metadata before upgrading.
Small SaaS teams can now move supported Paddle setup and billing tasks into Claude Code, Codex and similar agent workflows, but production account writes still require careful access control; native metered billing is not generally available.
ChatGPT Ads expands into 26 more countries. An October 29 default-on creative-enhancement change creates an immediate advertiser decision: review account and campaign opt-outs before automatically generated variations run.
WebKit's Safari MCP server is available in stable Safari 27.0 as well as Technology Preview. It runs locally, but captured page data passes to the connected agent; remote automation must be enabled explicitly.
A new GitHub ruleset can stop unapproved dependency licences at merge time, and agents can check packages before recommending them.
Shopify is turning off its old cross-merchant catalog REST API on November 2. The replacement is a UCP-compatible MCP server, not a renamed URL: agents must remap tools, payloads and saved-catalog identifiers.
The browser-for-machines project has reached 1.0 with a major web-compatibility jump and new cross-origin protections. It is not a drop-in replacement for every Chrome use case.
The funding headline is less interesting than the workload signal: Supabase says agents now create most new databases on its platform, and it is buying Turso to handle higher-volume database creation for those workloads.
The interesting change is not another CLI rename. Cloudflare is redesigning its command surface around software agents: JSON is the default, commands can be discovered through natural-language search, configuration is typed TypeScript, and Wrangler now has an eventual migration path.
The useful shift is not another AI wrapper around CI. sem-ai exposes CI/CD as structured, self-describing operations that Claude Code, Codex and other MCP-aware agents can call directly, including failure diagnosis and pre-push testing in CI.
Branch previews are common for frontend code, but Worker Previews extends the boundary to the runtime itself. Each branch can have independent bindings, state and logs, making parallel human and agent work safer while preserving a production-like execution path.
Android Bench 2.0 moves coding-agent evaluation away from small repository fixes toward dependency upgrades, app builds, migrations and other jobs that can take a human engineer days. The results expose a much larger reliability gap than short-task benchmarks—and show that the agent harness can materially change cost and outcome.
The important failure is not another prompt injection. Plugin4Shell breaks the mechanism intended to guarantee that an AI-agent plugin is still the exact code a marketplace reviewed.
OpenAI’s internal data turns “agents make researchers faster” into a measurable operating model: heavy concurrent agent use, record experiment throughput and rising task complexity, alongside high token spend and persistent human intervention on longer work.
Funes treats agent memory as user-owned data rather than a hosted account feature: retrieval and reranking run locally, provenance stays attached to recalled passages, and cross-machine sharing is optional. The main risk is that publishing session-derived memory can still expose secrets if redaction misses them.
Cloud Run instances sit between autoscaling serverless services and a small VM. They run one individually addressable container continuously, can be stopped and restarted, and use shared CPU economics; Google’s launch example prices 1 vCPU plus 1 GiB running for 30 days at $5.70.
TRACE targets a gap between audit promises and what an AI agent actually did at runtime. Its v0.2 developer preview can bind model, policy, data and tool-use claims to confidential-computing attestation, but it is still pre-ratification and explicitly not ready to treat as a production compliance guarantee.