Find a field note.

Building Fullscript Assist, Part 2: Keeping the Context Small

See how we treat the context window as a budget in Fullscript Assist: on-demand skills, isolated sub-agents, and auditable compaction.

Scaling Shopify's maintenance_tasks (Part 3): Observability and Governance for the Gem

See how Fullscript added durable logs, threaded Slack alerts, metrics, and self-cleaning governance around Shopify's maintenance_tasks gem.

Building Hospital-Grade Networks for Our Warehouse Operations

How Fullscript IT built hospital-grade network redundancy for automated warehouses — see how we design for the failure case first.

Building Fullscript Assist

How Fullscript rebuilt its clinical AI assistant with Elixir, BEAM processes, and MCP to support 120K+ providers with stateful conversations.

Scaling Shopify's maintenance_tasks (Part 2): Real-Time Progress for the Gem

Part 2: See how Fullscript layered live progress, shared lifecycle hooks, and queue isolation onto a gem they don't own — no fork required.

Scaling Shopify's maintenance_tasks (Part 1): A Custom UI for the Gem

How Fullscript rebuilt the maintenance_tasks UI as a React app over a JSON API — typed params, masked secrets, live status.

Using an LLM as a Test Compiler

End-to-end tests are usually expensive to maintain or too flaky to trust. We treated an LLM as a compiler to get tests that are neither.

Why green tests stopped meaning shipped

Why green tests aren't enough for AI systems. Learn how evals catch behavioral regressions that unit tests miss.

So You Want to Refactor Code with an Agentic Developer

Learn how agentic developers automate large-scale code refactors, reducing migration costs, engineering overhead, and delivery risk.

Feature-Flagging a Major Design System Upgrade

Shipping a major mobile redesign without stopping releases: adapters, build flags, and parallel design systems.

Being An Intern In The Age Of AI

What it’s like starting a software engineering career in the age of AI coding tools, code review, and agentic development.

Turning Wearable Noise Into Clinical Signal

Explore how we process wearable health data into personalized, explainable insights for clinical decision support.

From Signal to Solution

What if user feedback could become a working prototype automatically? Inside our AI-powered Feedback Builder.

Teaching Our Merge Requests to Teach Back

How to improve AI code reviews: turn merge requests into learning tools with context, patterns, and engineering decisions.

Streamlining Dependency Updates using RenovateBot

Outdated dependencies piling up? See how we automated updates across dozens of repos.

Using Nitro for Terraform deprecations

Use Nitro in Linear to automate repetitive Terraform updates and generate PRs instantly at scale.

How PMs Use Nitro for Small Code Changes

Nitro empowers PMs to ship changes faster, reduce overhead, and collaborate without interrupting dev teams.

Human First, AI Empowered - How’s it going?

Team GSD - Year 1 Reflection: Unlocking Operational Velocity

Team GSD scaled AI and automation across real workflows, improving operational velocity across multiple departments. Here’s how they did it.

Building Flurry: How We Used Agents to Democratize Data Access at Fullscript

Flurry lets anyone ask data questions in plain English and get trusted insights instantly. Learn how we built it at Fullscript.