Ask AI splits one question across the UI, `/api/chat`, Planner, Research, Writer, Validation, Critic, and Related stages. Answer text, displayed sources, and related-reading cards come from separate paths with separate gates.
Cloudflare Workflows turns multi-step Workers processes into durable steps: each step can retry, sleep, wait for events, and register rollbacks, while instances can be inspected, paused, resumed, or terminated. Queues fit single-step background work; Workflows fit long processes that must remember progress.
A local sandbox limits the blast radius of an agent on your machine; a cloud sandbox is about moving code safely onto someone else's machine. All five mature projects solve the first problem; only looplane actually deployed the second. Lessons from production: mocks can't catch SSE framing, green CI can't catch a stale wheel, and cleanup paths deserve timeouts just as much as success paths.
Groundlane is an open-source TypeScript remote MCP server (v0.1.0) giving AI agents web_search, web_fetch, and web_extract through a single stable contract, with auth, provider routing, and resource limits kept at the operator boundary.
Hands-on parameter choices and response structures for web_search (ten adapters, RRF merge, dual-provider default), web_fetch (format/render strategies, finalUrl provenance), and web_extract (CSS selector determinism, no implicit LLM step), with verifiable error boundaries.
Cloudflare Sandboxes uses a Worker as the entry point, a named Durable Object as the control plane, and a Container inside an isolated VM as the execution plane. It fits Cloudflare-native fleets of ephemeral Linux workspaces, but persistence, security boundaries, and three layers of billing remain your responsibility.
Cloudflare Queues is the message queue beside Workers: producers enqueue slow work, consumers process it with batching, ack/retry, delays, and DLQs. It is good for single-step background jobs; durable multi-step state belongs in Workflows.
The Workers AI catalog currently holds 84 models. For general chat pick glm-4.7-flash ($0.06 / $0.40 per M, 131K context), for vision pick gemma-4-26b-a4b-it ($0.10 / $0.30, 256K), for cheap high-volume steps pick granite-4.0-h-micro ($0.017 / $0.112), and for embeddings pick qwen3-embedding-0.6b or bge-m3 (both $0.012 per M). This post is updated on a schedule.
Query: 'I just sent Beauty in the Mirror 5.11b — recommend routes of similar difficulty.' The results came back full of routes with similar-sounding names, not similar grades. Root cause: dense embeddings compress multiple attributes into a single vector, and the rarity of the route name drowns out the grade signal. The fix: three layers of defense — metadata pre-filtering, query rewriting, and score fusion.
D1 is Cloudflare's serverless SQLite database that binds directly to Workers, supports full SQL (JOINs, transactions), and handles automatic backups. It's well-suited for small-to-medium relational data needs — NobodyClimb uses it as its primary database.
KV is Cloudflare's globally distributed key-value store. Reads are served from the nearest edge node with extremely low latency. It's ideal for caching, feature flags, and ephemeral data — but writes are eventually consistent.
R2 is Cloudflare's object storage service — S3-compatible API, zero egress fees, and native Workers binding. Stop worrying about bandwidth bills for media-heavy applications.
Cloudflare Workers uses V8 Isolates instead of containers — no cold starts, global edge deployment, and direct access to D1, R2, KV, and AI via Bindings. Great for APIs, SSR, and lightweight backends; not suited for CPU-heavy work.
Hono is a web framework designed specifically for edge runtimes like Cloudflare Workers, Deno, and Bun. It's an order of magnitude lighter than Express, natively supports Web Standard APIs, and is the go-to choice for edge environments.
@opennextjs/cloudflare enables Next.js App Router deployments on Cloudflare Workers — dynamic SSR runs in a Worker, static assets are served from Cloudflare Assets. Zero server management, but with clear feature limitations.
Upgraded action-maker from hardcoded mock data to live Cloudflare Workers AI generation. The architecture splits into Worker (AI only), Server (data storage), and Frontend (orchestration). Hit two gotchas along the way: Qwen3's thinking block and the Workers AI response format.
RAG doesn't have to be a rigid three-step process. It's a set of steps that can be dynamically enabled, skipped, or reordered. Pipeline as Code lets the system adapt its behavior without redeployment.
LLM generation takes 3-5 seconds, and waiting for the full response before displaying it makes for a terrible experience. SSE pushes tokens as they're generated, reducing time-to-first-character from 5 seconds to under 1 second.
Limiting request count alone is not enough — a single long query can consume ten times the tokens of a normal one. Dual quotas (request count + token count) are what truly control costs.
A climbing community platform where the web app, mobile app, and AI Q&A all run on Cloudflare — no dedicated servers.