Find published research by company, product, platform or technology.
Showing 21–40 of 302 dossiers
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.
The architecture matters as much as the voice quality: developers can replace a chained speech-to-text → LLM → text-to-speech loop with one full-duplex conversational model while keeping their own choice of backend reasoning model, tools and agent harness.
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.
WebKit’s Safari MCP server turns browser debugging into an agent-callable interface. It runs locally and makes no network calls itself, but captured page data is sent directly to the connected agent, so browser-session trust and model data handling become part of the development security model.
Ada has added code tools that run a restricted Python subset inside agent conversations. They can transform API responses, perform deterministic calculations and call allowlisted domains, while MCP-authored changes can be staged and reviewed before promotion.
Codex 0.149.0 includes the async-message tool, delivery metadata and removal of the client-side feature gate that BTN previously tracked only on main. Parallel human-agent work is now in a stable client, but late replies can still race with decisions and model capability metadata remains the final exposure gate.
Azure Document Intelligence v2.0 reaches retirement on August 31, 2026. Microsoft recommends moving workloads to the current v4.0 API; the post-v2 REST surface was redesigned, so teams should verify the actual api-version their SDK or HTTP client sends rather than assuming a package upgrade is enough.
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.
Bing’s AI Performance reporting now shows not just whether a site is cited in AI answers, but how its visibility breaks down by query intent, topic and citation share over time.
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.
Jev’s launch claims were interesting; Vercel’s usage data is more useful. Nearly 13% of paid AI Gateway teams tried the typed decision model in its first day, while Jev also rose to a material share of gateway requests. That does not establish retention or production success, but it is unusually fast developer uptake for a model designed to make bounded software decisions rather than generate prose.
For agent and untrusted-code workloads, the useful change is not simply lower latency. Sandbox location becomes an explicit execution policy, so teams can align code execution with nearby data and avoid a resilience fallback quietly moving work outside an allowed region.
The migration turns integration identity from an implicit platform detail into an operational dependency. Teams may need new run-as accounts and `Service Account User` grants not only for runtimes but also for editors, publishers, approvers and deployment automation.
Fin’s new Evals and Releases features let teams test agent changes against simulated conversations before publishing, bundle configuration into a release, ramp traffic or A/B test it, and feed failures from live Monitors back into the next iteration.
Email operations can now query Resend’s deliverability and engagement data directly through `/emails/metrics`. The API makes bounce and complaint thresholds, domain-level trends and campaign reporting usable by internal dashboards, scheduled checks and agents.