Find published research by company, product, platform or technology.
Showing 161–180 of 202 dossiers
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.
GPT-5.6 Sol Ultrafast remains in limited preview, but OpenAI’s August 21 standard-tier price cut changes its economics: Sol input is now 20% cheaper and output 33% cheaper through at least November 21. Ultrafast pricing is still undisclosed.
Panda CSS 2.0 keeps the familiar styling API but changes the compiler, minimum Node version and how teams can distribute design systems.
Shopify's new Events system can send the change and the data your app needs in one delivery. It's a significant alternative to classic webhooks, but not a forced shutdown or universal replacement yet.
Google's distributed SQL database can now run in production beyond Google Cloud, but 'deploy anywhere' doesn't mean free or fully managed. Spanner Omni GA brings security, backup and paid commercial licensing, with important limits on its developer edition.
Woodpecker's agent labels were self-reported and unsuitable for authorization. Version 3.19 adds server-held filters and patches a clone-step environment-variable leak; administrators should verify their worker policies.
This is a compatibility boundary for old Windows build hosts, not the end of Rust support for 32-bit Windows applications.
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.
The May Antigravity agent ID is retired. Managed Agents now require the September preview ID and default to Gemini 3.8 Flash, alongside hooks, token budgets and scheduled sandboxes.
Training experiments and batch inference can use Together AI's discounted preemptible GPUs in existing clusters. Workloads must checkpoint or requeue on interruption, and at least one standard node is required.
PostgreSQL operators gain per-statement and per-transaction estimated-cost limits across versions 14–18, useful for runaway reports and ORMs. The guard is disabled by default and can be bypassed by users allowed to change planner cost parameters.
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 release is more than routine maintenance. OpenSSH is changing cryptographic defaults, sacrificing some compression effectiveness for side-channel safety, and warning that AI-assisted security reports are pushing it toward a faster release cadence.
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.
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 Hyperdrive integration was the practical database unlock; the larger September 21 change is that Python Workers themselves are now GA. Cloudflare is explicitly positioning Python as a production language on Workers, with native platform bindings and framework support rather than an experimental compatibility layer.
The useful part is not the 800,000-line headline. GitHub has published unusually detailed receipts for a production-scale agent-assisted migration: roughly $120,000 of token spend, 14.5 weeks of incremental releases, dozens of regressions, extensive compatibility tests and a workload-specific jump from 7.55 to 120 session lifecycles per second.
The material change is that model routing is no longer a single opaque optimization target. Developers can now tell Copilot whether to bias Auto toward lower cost, a middle ground or higher quality while GitHub still chooses a model prompt by prompt.
Fusion is interesting less as another routing feature than as a different agent-cost architecture: two persistent model contexts divide planning, review and execution instead of making one expensive model handle every token. The practical question for builders is shifting from token price to cost per completed task.