Product blog
Product blog
Product updates, field guides, and field notes—each with links to docs and the hub where relevant. High-level milestones also appear on the changelog.
Topic
ReadField notes · Jun 7, 2026
How we standardized on Claude Code to build our apps
Our path through AI coding tools and LLMs, and why an agentic flow won out for a small business.
- Copilot → Cursor → Claude Code
- One model: Claude
- Agentic flow for business
Novus Stream Solutions (hub)
ReadField guide · Jun 7, 2026
Reliability hardening: device lifecycle, model integrity, and honest failures
An engineering note on the unglamorous guarantees that make a tool trustworthy — and why honest failures beat silent wrong answers.
- WebGPU device + quality detection
- Model-asset integrity checks
- Honest errors, no [object Object]
Stack & engineering
ReadField guide · Jun 6, 2026
Audit every tool, not just the broken one: the "all-tools" doctrine behind our refactors
Why a bug reported in one place is almost always a pattern that lives in several, and the discipline of fixing the pattern everywhere at once.
- One report, many instances
- Fix the pattern, not the example
- Prevents whack-a-mole regressions
Engineering
ReadField guide · Jun 5, 2026
Running a multi-agent research sprint before touching code
How to use parallel agents to understand a problem completely before changing anything, and why that front-loaded research pays for itself on large work.
- Research as its own sprint
- Parallel investigation agents
- Research-first beats patch-first
Engineering
ReadField guide · Jun 5, 2026
Managing the context window on a large refactor: what broke and how we fixed our sessions
A workflow lesson, not model marketing: how to structure a large refactor so it survives the limits of what can be held in working context at once.
- The whole problem won't fit at once
- Structure work into self-contained units
- Durable artifacts over live memory
Engineering
ReadField guide · Jun 4, 2026
The approver model: running a build pipeline where AI writes and you review
The operating model for one person directing AI execution: what the human keeps, what the agent takes, and how to keep the review meaningful.
- Human as approver, agent as executor
- Where it works and where it breaks
- Review discipline that scales
Engineering
ReadField guide · Jun 4, 2026
Guardrails and human review: where we let the agent run and where we don't
A practical map of where AI agents operate autonomously and where a human checkpoint is non-negotiable, and the reasoning behind each boundary.
- Autonomous zones vs hard gates
- Reversibility decides the line
- The build as a tireless reviewer
Engineering
ReadField guide · Jun 3, 2026
Shipping on Vercel solo: the deploy and preview workflow that keeps overhead near zero
The deploy, preview, and rollback loop that removes the ops tax from running multiple apps as a solo operator.
- Every push gets a preview URL
- Promote to production in a click
- Instant rollback to any prior deploy
Engineering
ReadField guide · Jun 3, 2026
Our three-mode workflow: prompt expansion → planning → coding (and why we never skip the middle)
Why the planning pass between understanding a request and writing code is the step that determines whether AI-assisted development produces something maintainable.
- Expand → plan → code
- The planning pass is non-negotiable
- Where rework actually comes from
Engineering
ReadField guide · Jun 2, 2026
Generating social share images at the edge
How an edge image route turns the typed post data into a per-page share card automatically, and why dynamic beats static here.
- OG images generated on demand
- Rendered at the edge per page
- No static asset to maintain
Engineering