Build logSeptember 12, 20248 min read
Featured

Shipping an AI feature in a single weekend

The constraints, scaffolding, and observability I lean on to take an idea from notebook to production by Monday morning.

nextjs
edge
openai
supabase
shipping

Side projects only ship if the scaffolding is boring. I keep the stack opinionated: Next.js App Router, tRPC for the thin API, drizzle for migrations, and a single feature flag guarding the new path to prod.

The weekend checklist

  • Friday: write a one-pager, choose latency/error budgets, decide what gets logged
  • Saturday: build happy path, seed realistic fixtures, wire eval harness
  • Sunday: remove sharp edges, add feature flag + rollout script, prepare rollback

Every prompt is treated like code: checked in, versioned, and logged as structured JSON so I can diff behavior across model upgrades. Shadow deployments let me compare responses in production without risking the primary path.

Instrumentation that catches surprises

  • Trace every request with request id, prompt hash, and model version
  • Emit structured errors for rate limits, content filters, and tool failures
  • Keep a rolling sample of raw prompts/responses for fast root cause analysis

Practice

If you only have one weekend, bias toward traceability. You cannot tune what you cannot see.

The release ritual ends with a kill switch, a 15-minute runbook, and a follow-up task list for Monday. Speed is fine; reversible speed is better.

Key takeaways
Highlights you can reuse.
Scaffold: tRPC, drizzle, and a single feature flag per bet
Observability before users: traces + structured prompts
Fast follow: shadow deploys for inference changes
Downloadable template
Copy the checklist and adapt it to your stack.

Includes prompts, runbooks, and rollout steps referenced here.

LLM evaluation that does not hurt
A lightweight rubric I use to grade LLM features before users do, with examples for reasoning and tool-heavy prompts.
AI/ML
9 min read
Read
Edge AI with Workers and Rust
Running inference at the edge with predictable latency, shared wasm modules, and a hybrid routing plan for heavier models.
Edge
8 min read
Read
Practical data contracts for small teams
How to stop schema breakage without drowning in governance: contracts, lineage, and a 30-minute weekly review.
Data
6 min read
Read