Find published research by company, product, platform or technology.
Showing 21–40 of 329 dossiers
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.
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 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.
Repository growth tools can measure when star counts changed again without rebuilding individual-user histories. The new API deliberately separates aggregate popularity data from stargazer identity, so integrations need to distinguish trend analytics from user-level community data.
Muse Spark 1.3 is more than a routine model refresh: Meta is pairing stronger agent behavior with lower vendor-reported tool/token use at the same published unit price. Independent testing supports a capability gain, but max reasoning can consume substantially more reasoning tokens.
Notion Workers are now metered inside the same credits system as Custom Agents. The important builder shift is that schedules, webhook fan-out and agent tool-call counts now directly affect cost.
The EDG front end moved from commercial licences to a public repository and C++ Alliance stewardship on September 30. A fresh October 20 statement confirms permissive commercial reuse, experienced maintainers and work still needed on reflection, coroutines and back ends.
JPEG XL now ships by default in Chrome 155 and Firefox 158; Safari supports still images, but Edge, installed-version lag and format tooling still warrant fallback delivery.
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.
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.
Void SDK adds server routes and typed data access to Vite, Void CLI provisions Workers resources, and Void Platform provides a controlled multi-user deployment surface. The convenience comes with Cloudflare runtime dependencies and real deployment limits.
A new public MCP endpoint lets agents search without an API key and complete shopper-authorised purchases. It is separate from the Global Catalog REST API retirement and earlier browser-only WebMCP checkout; webhooks are not available at launch.
Shopify's App Pricing migration is now clearer: directly matching subscriptions can move through plan setup, while usage-based and price-mismatched subscriptions stay on the Billing API until a separate Migration API arrives.
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.
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.
DuckDB's agent-aware CLI aims to make tool output safer and more compact for coding agents. Its own experiment showed 59% fewer CLI-output tokens but only about 0.5% lower total input cost, so practical gains need careful interpretation.
From December 3, agent workflows that ask Atlassian's Teamwork Graph for cross-product context will need a cost budget. Most enriched tool calls use 1–10 Rovo credits, with paid overages at $0.01 per credit.
Preact's long-awaited major release brings concrete rendering changes and a packaging break. Most modern projects should migrate easily, but old import paths and CommonJS tooling need attention.
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.
Jev made bounded decision models visible; Strands Decider makes the pattern reproducible inside an agent stack. AWS replaced Qwen3.5-2B's language-generation head with a small scoring head and released the recipe, creating a local alternative for decisions that do not need a full generative model.