workflow-evaluation

A portable company workspace for Codex and Claude Code. Build recurring workflows with Director, preserve context, and improve work through evaluated runs and experiments.

Portable evaluation bundles for agents and agent-shaped workflows: bounded, reproducible, regression-aware proof surfaces for quality claims.

Retail support agent with tool execution, persistent business state, and outcome-based evaluation.

A small benchmark for agent skills, verification artifacts, and fresh-session resumability.

Your portable company workspace. Build lead research, outbound and recurring workflows with Director; inspect context, evaluations and real usage in a live dashboard. Codex & Claude Code.

Preprint paper package — Lightweight Evaluation and Operational Scorecards for Tool-Using AI Agents (Zenodo DOI 10.5281/zenodo.20034550)

Reproducible PoC comparing certified reusable workflows against flat direct control on bounded repository-maintenance tasks, with deterministic audit, replay, drift, and maintenance.

Lightweight proof-of-concept for oversight-centered metrology in coding agents: workflow-aware evaluation, interrupt channels, and claim-margin reporting beyond raw success scores.