Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
mla: Coordination for Claude Code
Learn how a coordination layer prevents coding agent drift by managing context, tracking decisions, and enabling human review of agent-generated memory.
I built mla, a coordination layer for Claude Code that helps developers keep coding agents aligned with existing architecture decisions, rules, policies, and project memory.
In the live demo, I’ll work on a real feature in a real repo with Claude Code running alongside mla. I’ll show how mla injects only the relevant approved context into the agent, tracks which decisions, rules, claims, and relationships were used during the session, detects new coordination objects produced by the agent, and surfaces them in the Console for human review.
The demo will include the working Console UI, the Claude Code workflow, injected context, session logs/artifacts, newly detected decisions and relationships, and the review/promote/reject flow that controls what becomes reusable memory for future sessions. The goal is to show how mla catches coding-agent drift early and gives developers control over what agents are allowed to know, use, and remember.
mla is a human-in-the-loop control surface managing agent memory and policies.
- TypeScriptTypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).
- NodeNode.js is a high-performance JavaScript runtime built on the V8 engine for executing scalable network applications.Ryan Dahl launched Node.js in 2009 to rethink server-side concurrency. It utilizes an event-driven, non-blocking I/O model to manage thousands of concurrent connections on a single thread. The system runs on Google's V8 engine (C++) and provides access to npm (a registry with over 2 million packages). Companies like Netflix and LinkedIn use it for its speed and scalability: it remains the top choice for real-time data streaming and microservices.
- PostgreSQLPostgreSQL (Postgres): The world's most advanced, open-source object-relational database (ORDBMS), built for reliability and extensibility.PostgreSQL is the premier open-source ORDBMS, proven over 35+ years of active development. It adheres strictly to ACID properties (Atomicity, Consistency, Isolation, Durability), ensuring data integrity for mission-critical workloads. Key features include robust SQL compliance, Multi-Version Concurrency Control (MVCC), and superior extensibility (e.g., custom data types, functions in multiple languages). Advanced capabilities like native JSON/JSONB support and the PostGIS extension (geospatial data) make it a powerful, flexible choice for complex enterprise applications.
- PrismaPrisma is an open-source database toolkit: it provides a modern ORM, database migrations (Prisma Migrate), and a data visualization tool (Prisma Studio) for Node.js and TypeScript.Prisma delivers a next-generation ORM, fundamentally changing how developers interact with databases. Its core component, the Prisma Client, is a type-safe query builder automatically generated from the Prisma Schema, ensuring all database operations are safe and predictable in TypeScript applications. This setup drastically reduces runtime errors and boilerplate code. It supports major relational databases (PostgreSQL, MySQL, SQL Server) and MongoDB, offering a unified, declarative data modeling language. The toolkit includes Prisma Migrate for managing schema changes and Prisma Studio for efficient data viewing and editing: a complete, productivity-focused data layer solution.
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
Compose Email
Loading recent emails...