3 min read
Leadership
Running a Model Locally Makes Your Team the Vendor
Running a model locally shifts production work to your team. Evaluate capacity, reliability, security, and engineering time before replacing an external API.
Browse the notebook
Software Architecture
Articles in this topic
3 min read
Architecture
Your AI System Needs a Deletion Path
Deleting an uploaded file is only one step. Design and verify deletion across extracted text, search indexes, saved answers, logs, caches, and backups.
3 min read
Architecture
Before Building an MCP Integration, Try the CLI
Before building an MCP integration, test whether an existing CLI meets the agent's needs. Weigh maintenance, permissions, reliability, and workflow fit.
7 min read
Architecture
AI Cost Starts with Architecture
Model selection, caching, context, batch processing, and bounded workflows shape AI costs. Measure the full cost of a successful resolution.
2 min read
Architecture
Claude Got Banned From Government Systems --- Here's the Lesson.
When Claude was banned from government systems, some teams swapped providers in a day. Others faced months of refactoring. The difference? Building every integration for replaceability. Here's why this principle applies to every dependency you have.