Building the platform behind small business.
How we design, ship, and operate the systems that turn an idea into a registered, compliant business — increasingly with AI in the loop. Deep dives on product engineering, platform migrations, ML infrastructure, and architecture.
Latest
A Living Engineering Knowledge Graph, Refreshed From Every PR
How we auto-extract source-grounded engineering knowledge across more than a dozen repositories, keep it current from every merged PR, and make it trustworthy enough for AI agents to build on.
LegalZoom Engineering · · 7 min read
How We Used a Grounded Coding Agent to Accelerate a Commerce-Platform Migration
A large commerce migration is a coordination problem before it is a coding problem. Here is how we replaced cross-team handoffs with a spec-driven, pattern-classifying coding agent — and the validation scaffolding that kept it from hallucinating its way into production.
LegalZoom Engineering · · 7 min read
Earning the Right to Act: Putting Autonomous Agents into Production Operations
How we run AI agents in real support and incident-response workflows without letting them run wild: capability constraints that make unsafe actions structurally impossible, a Slack-native approval contract, and a confidence-building diagnosis pipeline grounded in production telemetry.
LegalZoom Engineering · · 7 min read
Describe It, and Ship It: AI-Assisted Frontend at Scale
How we turned an AI-generated UI prototype into a production dashboard experience: wired to live state, fully accessible, and shipped behind feature flags in days, not sprints.
LegalZoom Engineering · · 7 min read
How We Ship Continuously Without the Coordination Tax
Velocity isn't about typing faster. It's about removing handoffs, moving knowledge into reusable AI harnesses, and treating tests, monitoring, and review as part of "done."
LegalZoom Engineering · · 7 min read
Putting Machine Learning in the Checkout Path Without Making Checkout Depend on It
How we run multiple production ML predictors inside a latency-sensitive purchase funnel — and why the funnel never blocks on inference.
LegalZoom Engineering · · 8 min read
One API in Front of Every LLM: Building a Cost-Aware Model Gateway
Cost-per-token is a sticker price that tells you almost nothing. After an autonomous agent quietly burned through its monthly model budget and went dark for two days, we built a gateway that optimizes for what actually matters: realized cost per completed task.
LegalZoom Engineering · · 8 min read
Rewriting Document Generation Without the Big-Bang Risk
How we replaced a legacy, vendor-backed document engine that touches every product line — turning a high-stakes rewrite into a per-template routing decision that was always one flag flip away from rollback.
LegalZoom Engineering · · 7 min read
From Model Sprawl to a Shared ML Platform
How we consolidated dozens of one-off model deployments into a single FastAPI-based, Kubernetes-served paved path that carries everything from classic prediction services to LLM agents and shared MCP tool servers — without turning shared infrastructure into a bottleneck.
LegalZoom Engineering · · 7 min read
Unifying a Business Filings Platform Around Core APIs and Events
How we replaced a tangle of overlapping post-purchase systems with one filing domain — built on core APIs, BPMN workflows, and events, anchored by a single canonical business record — without halting the business.
LegalZoom Engineering · · 7 min read
Unifying Feature Entitlements Across a Commerce Platform Without Breaking It Mid-Flight
Entitlements are the load-bearing glue between a purchase and what a customer can actually do. Here is how we consolidated two generations of that glue into one authoritative store, migrated hundreds of thousands of historical records idempotently, and never once risked a paid order without its grant.
LegalZoom Engineering · · 8 min read
Browse by topic
How we ship customer-facing product with AI in the loop — from prototype to production in record time.
Agent-assisted approaches to the unglamorous, high-stakes work of moving large systems without breaking them.
The shared serving, model-routing, and ML infrastructure that powers AI across the company.
Autonomous agents in production operations, automated diagnosis, and living engineering knowledge.
Domain-driven, event-based architecture for the systems behind small-business formation and compliance.
Every post, straight to your reader — subscribe to the RSS feed.