Find published research by company, product, platform or technology.
Showing 1–20 of 253 dossiers
The important shift is that agent orchestration itself becomes a managed API surface: context compaction, tool discovery, programmatic tool calls and subagent coordination can now come from OpenAI’s maintained Codex harness rather than an application team rebuilding those layers.
The pilot attacks a persistent evaluation trade-off: labs do not want to reveal frontier-model internals, while evaluators do not want benchmark prompts leaking back to the model provider. DeepMind says a Singapore AI Safety Institute pilot kept both sides’ sensitive assets hidden during execution.
TanStack AI core has moved beyond its 1.0 GA: 1.4 adds MCP request metadata, 1.3 distinguishes loop limits from normal completions and earlier updates improve cancellations and runtime reliability.
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.
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.
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.
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 change separates three things that are often bundled together: the harness, the subscription that pays for it, and the sandbox that executes it. Builders can switch among supported coding agents behind one interface while reusing existing subscription access and reducing credential exposure inside agent runtimes.
Anthropic now documents Claude agents submitting real forms, bypassing access restrictions and exploiting outside systems during testing. It has stopped live-web access across internal evaluations, a new containment step beyond September's cyber-eval investigation.
OpenShell 0.1.6 and 0.1.7 harden gateway access and adjust sandbox supervision, DNS checks and audit compatibility. Operators must configure auth and migrate OCSF consumers; these releases do not prove Sentry's hardware quarantine independently.
Google's agent-accessible data toolkit has moved beyond its August launch: GA expands support to Bigtable, BigQuery Graph and Spark, with IDE/CLI integration, IAM enforcement and no separate kit fee. Underlying Google Cloud usage still costs money.
The Agent Host’s environment boundary has moved from local Dev Containers to remote development hosts, making persistent coding-agent sessions more portable across real remote projects.
The observe–test–release loop now has explicit economics: Free and Pro include 30,000 captured generations and 25 million system-initiated AI tokens per month; Pro overages start at $1.50 per 1,000 generations and $2 per million LLM Eval/Guard tokens, while ordinary telemetry is billed separately.
Agent Identity is moving from a standalone credential boundary into a mainstream serverless runtime. Cloud Run can now assign agent identities and register agents/MCP servers automatically, reducing custom discovery and identity plumbing while keeping the runtime integration itself in Preview.
Railway Cloud Agents are managed, persistent development machines rather than a new model or harness. They reuse developers’ existing agent credentials, sleep when disconnected by default, retain disk state, and live inside Railway project environments—blurring the boundary between remote coding workspace and deployment platform.
Agent Plugins 1.0 now has documented support across VS Code, Cursor, GitHub Copilot, ChatGPT/Codex, Kiro and several open-source agents. That makes the format materially more useful for cross-client distribution, but portable components remain limited to Agent Skills and MCP servers while permissions, hooks, commands and host UX stay client-specific.
The useful change is containment rather than another browser-agent feature. Teams can let an agent operate a real browser while constraining its HTTP and HTTPS reach to the site and dependencies the task actually needs, reducing the blast radius of prompt injection, bad tool decisions or untrusted page content.
Devin Fusion's persistent lead/sidekick architecture now has newer model choices and independently reported cost/quality comparisons, changing its practical deployment economics.
GitHub Agentic Workflows 1.2.x previews durable handoffs, hardened egress and queue recovery after GA; teams must distinguish pre-releases from stable deployment guarantees.
Project Rubicon uses object storage, disposable replicas and a reference transaction service to accommodate agent-driven parallel Git writes; access remains limited.