Security5 min readAI Security: Humans Before The Loop How Fullscript's Project Glycerin triages and fixes security vulnerabilities in minutes, with engineers owning the standards the AI applies.Read investigation
Engineering14 min readBenchmarking the Agents That Write Our CodeSee how we built a benchmark from our own git history to compare AI coding models, skill packs, and agent harnesses on our real codebase.Read investigation
Technology8 min readSmart Rollouts: Adding Control Groups and Exposure Tracking to FlipperSee how Fullscript added 50/50 experiments to Flipper feature flags using a second salted hash and exposure tracking that waits for first use.Read investigation
Engineering11 min readBuilding Fullscript Assist, Part 2: Keeping the Context SmallSee how we treat the context window as a budget in Fullscript Assist: on-demand skills, isolated sub-agents, and auditable compaction.Read investigation
Software7 min readScaling Shopify's maintenance_tasks (Part 3): Observability and Governance for the GemSee how Fullscript added durable logs, threaded Slack alerts, metrics, and self-cleaning governance around Shopify's maintenance_tasks gem.Read investigation
Engineering10 min readBuilding Hospital-Grade Networks for Our Warehouse OperationsHow Fullscript IT built hospital-grade network redundancy for automated warehouses — see how we design for the failure case first.Read investigation
Engineering16 min readBuilding Fullscript AssistHow Fullscript rebuilt its clinical AI assistant with Elixir, BEAM processes, and MCP to support 120K+ providers with stateful conversations.Read investigation
Engineering7 min readScaling Shopify's maintenance_tasks (Part 2): Real-Time Progress for the GemPart 2: See how Fullscript layered live progress, shared lifecycle hooks, and queue isolation onto a gem they don't own — no fork required.Read investigation
Engineering7 min readScaling Shopify's maintenance_tasks (Part 1): A Custom UI for the GemHow Fullscript rebuilt the maintenance_tasks UI as a React app over a JSON API — typed params, masked secrets, live status.Read investigation
Engineering10 min readUsing an LLM as a Test CompilerEnd-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.Read investigation
Technology11 min readWhy green tests stopped meaning shippedWhy green tests aren't enough for AI systems. Learn how evals catch behavioral regressions that unit tests miss.Read investigation
Technology4 min readSo You Want to Refactor Code with an Agentic DeveloperLearn how agentic developers automate large-scale code refactors, reducing migration costs, engineering overhead, and delivery risk.Read investigation
