Find published research by company, product, platform or technology.
Showing 521–528 of 528 dossiers
DynamoDB vector indexes add native similarity search through SearchVectors and now have clear per-GB write, search and storage pricing, plus published throughput quotas.
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.
Buttondown’s 'Great Pruning' is a small-SaaS operations story about deleting architecture rather than adding it. The company removed duplicated or over-retained request and email-event data after changing how those workloads were processed.
Cloud SQL’s SQL Server HA path is becoming more transparent to applications: supported proxies and connectors can target one write endpoint and be redirected when the primary changes. Teams still need retry-safe connection handling around the failover itself.
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.
Blocking OAI-SearchBot is not a complete removal signal for ChatGPT Atlas. OpenAI says a disallowed page can still appear as a link and title when the URL is learned elsewhere and judged relevant; publishers that want to suppress that result need a crawlable noindex directive, while GPTBot remains the separate training control.
The bug is a useful warning for AI application plumbing: turning a user-supplied URL into a model attachment also turns the application server into a network client unless the adapter enforces an outbound trust boundary.
Laravel now has a framework-native approval flow for AI tools: approvable tools can pause an agent, surface arguments and reasons, then resume the same persisted conversation after a human decision.