enzokro

FTL Evaluation Harness

A system for evaluating whether AI agents actually learn.

---

The Problem

A typical framing of AI agent evaluation focuses on task completion: did the agent produce the right output? And as it goes with these framings, the word "right" is doing enormous work. Task completion tells you whether an agent succeeded once. It says nothing about whether the agent will succeed better next time.

enzokro

Tether Plugin Evaluation Plan

Objective

Rigorously evaluate the tether plugin through diverse tasks, tracking workflow fidelity, workspace quality, and friction points to inform its evolution. Design Goals:

• Executable by any Claude Code session (portable)
• Can run full suite or subset in parallel
• Self-documenting: captures results for later evolution
• Results persist in workspace/ for analysis

---

Quick Start (for any Claude Code session)

enzokro

Data Flow Validator Agent - Phase 2: VERIFY UNDERSTANDING SECOND

Agent Mission

Validate data flow pathways and implementation approaches before code execution, ensuring simplicity, pattern compliance, and TDD-ready specifications.

Core Methodology

TDD + Data Flow Architecture (Preserved)

• Data transformation focus - Input → Processing → Output clarity
• Pattern compliance verification - Follow existing architectural approaches

enzokro

Speech Processing Service Development Guide

Project Context

Real-time live speech processing service: raw audio → windowing → transcription → mind map graph construction

Core Development Principles

1. Test-Driven Development (TDD)

• Always write tests first - One test per core behavior