Find published research by company, product, platform or technology.
Showing 81–100 of 349 dossiers
The benchmark runs agents against Prometheus, Loki, Tempo and Grafana, checks actual outcomes across three attempts, and makes the task and grading code inspectable. Synthetic tests and vendor-run leaderboard scores still need local validation.
A free open-source video editor gains a scriptable, headless editing surface: import and trim clips, apply effects, inspect contact sheets, export and hand projects back to a human. Auto-Optimize separately speeds up 4K editing without lowering final output quality.
Self-hosted CI teams should upgrade to 3.20.1, audit runner and secret boundaries, and test workflow selection and substitution after the 3.20.0 regression.
Retailers and commerce-tool developers can now query first-party UCP shopping funnels rather than infer agentic checkout performance from traffic alone, but the alpha API needs careful query design.
Copilot Projects can coordinate agents, files and recurring tasks across repositories or non-code work; review and permissions remain human responsibilities.
Shopify Flow becomes agent-operable for store owners, but its automation APIs are not a general third-party app integration.
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 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.
Agent skills join prompts and models as managed runtime configurations; approvals and pinned versions make changing agent behaviour auditable rather than an untracked edit to skill files.
The concrete API price and access limits close a key gap in the October launch: developers can cost Wonder through Model API but must not confuse maximum reasoning effort with Wonder Full.
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.
Vendor-run live-store testing exposes the trade-off between containment, quality and response speed. Store configuration matters, and the evaluator's commercial conflict requires care.
Agent checkout builders using UCP 2026-08-25 can now negotiate consent options, propagate customer choices and handle missing-data warnings instead of hardcoding merchant privacy defaults.
Beam makes a large agent-focused model commercially reusable without a bespoke licence, but the open weights are not a small local download.
A new GitHub ruleset can stop unapproved dependency licences at merge time, and agents can check packages before recommending them.
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.
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.
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.
Together Link connects six existing coding-agent/desktop harnesses to open models with reversible profiles, per-session routing and cost receipts. The important shift is portability at the harness boundary, not Together's unverified savings claim.