Insights
Practical writing on software architecture, SaaS products, AI automation, legacy modernisation, and the business of building reliable systems.
Curated links from external sources — not 360Softy original articles.
Type "songs for a rainy Sunday morning" into a music app and you'll get results that match the mood, even though none of those words appear in the track titles. That kind of result is often powered by vector embeddings, numerical representations of me...
Agents connected to Model Context Protocol (MCP) servers with addMcpServer can now handle elicitation requests. Elicitation lets an MCP server request user input while it handles a tool call. Form mode collects structured, non-sensitive data. URL mode asks for consent before opening an out-of-band flow, such as third-party authorization or payment. sequenceDiagram participant User participant Agent as Agent (MCP client) participant Server as MCP server participant Browser Se
Precursor is rolling out to all customers starting today. Precursor is client-side JavaScript that enables session-based bot detection. You can read the announcement blog for background on why we built Precursor and how session-level behavioral detection works. With Precursor enabled, Cloudflare can: Continuously evaluate behavioral signals across a session Re-validate challenge clearance as behavior changes Update bot scores with session context Provide client-side visibility where none previou
Markdown for Agents now preserves security- and cache-relevant response headers from your origin when converting HTML to Markdown: Markdown for Agents preserves security headers such as Strict-Transport-Security (HSTS), Content-Security-Policy (CSP), X-Frame-Options, Set-Cookie, and CORS headers (for example, Access-Control-Allow-Origin) on the converted response. Caching headers (Cache-Control, Expires, Age) continue to pass through. Your origin's Content Signals policy is now authoritative. If
R2 Data Catalog now accepts read-only API tokens, so query engines and clients that only read data no longer need a read-write token. Previously, every catalog operation required an Admin Read & Write token, which meant read-only clients were granted more access than they needed. You can now authenticate your Iceberg engine based on your workload: Read-only operations (such as listing namespaces, loading tables, and querying data) work with an Admin Read only token (R2 Data Catalog read and R2 s
R2 Data Catalog, a managed Apache Iceberg catalog built into R2, now automatically optimizes manifest files as part of compaction. Manifest files track the data files that make up an Iceberg table. As a table accumulates many small or fragmented manifests, query engines must read more metadata during query planning, which slows down queries even before any data is scanned. When compaction runs, R2 Data Catalog now rewrites and clusters manifest files by partition as a best-effort pre-step. This
You can now inspect subagent activity for eve projects in . Agent Runs The new Subagents tab shows every subagent, organized by which turn started it. Each row shows the prompt, duration, and any failures, all on a shared timeline. Click any subagent to open its run. The tab shows the same details as a parent run: turns, tool calls, metadata, cost, and token usage. Open to try it, or read the to learn more.Agent Runsdocumentation Read more
You can now manage targeting rules for through the . With the command, you and your agents can add new rules, move existing ones, and inspect the current ordering without leaving your terminal.Vercel FlagsVercel CLIvercel flags rules Rules you create from the CLI use the same model as the dashboard. Conditions can target or reusable , outcomes can serve a single variant, a weighted split, or a progressive rollout, and rules evaluate top to bottom. For scripts and agents, prints the full rule
Work with 360Softy
Book a free consultation and we will tell you honestly whether we can help.
