GitHub Copilot Projects gives coding agents persistent goals across repositories
Copilot Projects can coordinate agents, files and recurring tasks across repositories or non-code work; review and permissions remain human responsibilities.
Search
Search results for “AI inference architecture”
Find published research by company, product, platform or technology.
Showing 121–140 of 281 dossiers
Shopify opens Flow automation management to external AI agents — but not third-party apps
Shopify Flow becomes agent-operable for store owners, but its automation APIs are not a general third-party app integration.
TanStack AI 1.0 stabilises its provider-neutral SDK — but the agent harness is still experimental
The three-maintainer TanStack AI project has reached stable 1.0 for its core SDK, with 23 providers; its long-running agent harness is not yet stable.
GitHub says agents started over 40% of September pull requests — Octoverse reveals a review bottleneck
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 Copilot SDK gains organisation-owned server-to-server authentication for agents
GitHub Apps can now authenticate Copilot SDK workloads without a user's credentials. Organisation admins control installation permissions, usage attribution and budgets.
Artificial IntelligenceWeb DevelopmentJavaScriptAI CodingBrowsers & Web StandardsDeveloper ToolsActive dossier
Google's AI bug hunter finds different V8 flaws from fuzzing — Project Zero says keep both
A six-month real-world comparison shows AI code-review agents and specialised fuzzers find substantially different V8 vulnerabilities. Replacing fuzzing with agents would leave gaps, and cost per bug remains unknown.
Artificial IntelligenceWeb DevelopmentSaaSCloud & InfrastructureAI AgentsSaaS OperationsDeveloper ToolsObservabilityActive dossier
MLflow CrewAI tracing leaked API keys into telemetry — upgrading does not remove old secrets
MLflow CrewAI autologging silently logged API keys; 3.17.0 patches it, but previously exported traces and keys still need remediation.
Artificial IntelligenceCloud & InfrastructureAI AgentsCloud PlatformsDeployment & DevOpsActive dossier
Cloudflare Computer 0.7 lets agent code survive crashes and pause for approval — but replay can repeat writes
Cloudflare Computer 0.7 makes agent code resumable and interruptible. The important catch: recovery replays code, and unrecorded external actions can be repeated even if they already succeeded.
GitHub Copilot adds model-judged permissions to its GA agent sandbox — with unattended-run traps
Copilot now offers model-reviewed action approvals between manual and Allow All. Unlike OS sandboxing, this probabilistic gate can approve unsafe operations; unattended CLI flags may leave unexpectedly broad permissions.
OpenAI’s Decisions API turns GPT-6 Luna into a bounded decision layer for software
Jev, CLM and GLiNER2.5-Decide made bounded software decisions look like a distinct model category. OpenAI is now validating the same architectural split with a Luna-powered API designed to answer finite questions rather than generate open-ended prose.
Artificial IntelligenceWeb DevelopmentCloud & InfrastructureCompute & AI InfrastructureOpen ModelsDeveloper ToolsActive dossier
PyTorch 2.15 release candidate brings FP8 and major Metal fixes to local AI on Macs
The PyTorch 2.15 RC changes what Apple-silicon developers can run locally: FP8, faster MPS decoding, new GPU operators and a video VAE memory fix. The reported 5–6.5x gain is not universal.
Muse Wonder's API prices and 1M context are public, while Wonder Full stays inside Muse Code
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.
Artificial IntelligenceWeb DevelopmentCloud & InfrastructureDeployment & DevOpsInference & APIsDeveloper ToolsActive dossier
LiteLLM 1.107.0 was backdoored on PyPI and Docker: startup hooks stole credentials even without an import
The unusual risk is that Python startup hooks execute without an application importing LiteLLM, while the public source tag lacked the malicious files. Check the exact installed wheel or image digest, not just the repository.
OpenAI frontier models reach Google Cloud — with Marketplace billing against cloud commitments
Google Cloud customers gain a new route to OpenAI models with unified governance and cloud-commitment billing, but broad availability and some privacy features are still forthcoming.
Artificial IntelligenceWeb DevelopmentAI AgentsWordPressBrowsers & Web StandardsDeveloper ToolsActive dossier
WebMCP gives websites a structured tool layer for browser agents
WebMCP is no longer a Chrome-only browser experiment: Microsoft Edge now has its own active origin trial, while ChatGPT’s built-in browser and WordPress Playground show agent-client and platform implementation paths.
Artificial IntelligenceWeb DevelopmentCloud & InfrastructureAI ModelsOpen ModelsInference & APIsDeveloper ToolsActive dossier
Cloudflare previews Clairic: typed extraction and forecasting without generative output tokens
Clairic joins Clef as a specialised one-pass model on Workers AI; typed extraction has a different failure model from LLM-generated JSON, with vendor-only benchmarks and preview limitations.
Artificial IntelligenceWeb DevelopmentAI CodingBrowsers & Web StandardsDeveloper ToolsActive dossier
Safari 27 gives coding agents a local MCP path into live browser debugging
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.
DeepSeek opens Search and Fetch APIs at $0.75 per 1,000 calls, with a temporary agent-tool free window
Developers get another paid web retrieval option for coding agents and applications; the introductory harness exemption expires October 31.
Apple extends App Store moderation to AI-generated content and tightens hidden-feature rules
AI image and social-app developers face clearer moderation and review obligations; hiding features can threaten an entire developer account.
OpenAI will shut down GPT-4o and GPT-4.1 API snapshots on January 14 — including fine-tunes
Production integrations using GPT-4o, GPT-4o mini, GPT-4.1 or GPT-4.1 mini dated snapshots need model inventory, tool-call regression testing and migration before January 14, 2027.