REGISTERED TAG
Deployment
Build, publish and verify independently operated services.
Cloudflare at the edge: products, boundaries, and deployment evidence
Learn how Workers, static assets, data products, and deployment checks fit into a small independently deployable service.
Cloudflare Sandbox SDK 1.0: execution state, snapshots, and migration boundaries
Read Sandbox SDK 1.0 as an execution-state contract: Durable Object control, immutable snapshots, explicit network policy, and a rehearsed one-way migration.
Version agent work with Cloudflare Artifacts
Separate Git history, execution state, and large outputs; scope credentials and validate the exact commit before accepting agent work.
Access service authentication: verify the machine principal on every request
Use an offline request matrix to separate a service credential, a browser session, an edge decision, and an authorized application action.
Maintain comparisons across updates
Keep Skills in maintainable units rather than simply adding more.
Deliver your work through social media and services
Connect presentation, publication checks, analysis and improvement
Choose a GPU platform and cost model
Align runtime, storage, stopping and data-transfer assumptions before comparing prices.
Record experiments and integrate AI into a service
Turn small experiments into reproducible decisions and controlled operation.
Read this before adopting OSS AI: repository, weights, dependencies, and operations
Move OSS safely from learning into operations by separating licenses, maintenance, reproduction, vulnerabilities, and model weights instead of trusting star counts.
vLLM 0.29–0.30: treat a runner default as a serving-boundary change
A dated release note on testing vLLM runner, queue, and route authorization changes before adopting a new serving release.
Choose AI providers as operating layers, not a capability table
Design OpenAI, Anthropic, Google, ElevenLabs, Databricks, Vercel, and Cloudflare as model, data, execution, voice, and delivery layers.
Evaluation, safety, and cost design before placing generative AI in production
Connect evidence, authority, recovery, observability, and updates before measuring model cleverness, so answer quality remains reproducible in operation.
AI apps on Vercel: put AI SDK, Gateway, and Workflow at product boundaries
Use Vercel’s agentic-infrastructure announcements to design streaming, tool calls, durable jobs, secrets, and evaluation as one web product.
Edge AI with Cloudflare: boundaries for Workers AI, AI Gateway, and Agents
Design state, authentication, cost, caching, and tool execution separately before shipping edge inference or an AI app quickly.
Build Trail: Rust stages 11–30
Use one work-log product to practice contracts, persistence, web boundaries, recovery, measurement, and release.
Y Combinator observation: turn public signals into constrained experiments
A dated reading of YC RFS and company material, separated from recommendations and adoption claims.