Spaces:
Running
Running
| title: Ops Scorecard Lab | |
| colorFrom: green | |
| colorTo: blue | |
| sdk: gradio | |
| sdk_version: 5.29.0 | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| tags: | |
| - agents | |
| - operations | |
| - evaluation | |
| - scorecards | |
| models: [] | |
| datasets: | |
| - mukunda1729/agent-eval-scenarios | |
| # Ops Scorecard Lab | |
| Ops Scorecard Lab turns a rough agent workflow into an operator-facing scorecard. | |
| It helps builders outline: | |
| - the operating surface | |
| - review priority | |
| - verification expectations | |
| - rollout notes | |
| - next action items | |
| The Space is intentionally lightweight and portfolio-friendly: fast to inspect, easy to extend, and aligned with the public eval dataset on Hugging Face and Kaggle. | |
| ## Associated Papers | |
| - Primary paper: [Lightweight Evaluation and Operational Scorecards for Tool-Using AI Agents](https://doi.org/10.5281/zenodo.20034550) | |
| - Paper landing page: [lightweight-agent-eval-paper](https://mukundakatta.github.io/lightweight-agent-eval-paper/) | |
| - Companion evaluation harness paper: [AI Eval Forge: Mixed-Check Regression Testing for LLM and Agent Workflows](https://doi.org/10.5281/zenodo.20044318) | |
| - Artifact repo: [MukundaKatta/ai-eval-forge-paper](https://github.com/MukundaKatta/ai-eval-forge-paper) | |
| ## Related Public Artifacts | |
| - Hugging Face dataset: [mukunda1729/agent-eval-scenarios](https://huggingface.co/datasets/mukunda1729/agent-eval-scenarios) | |
| - Hugging Face collection: [Agent Labs Portfolio](https://huggingface.co/collections/mukunda1729/agent-labs-portfolio) |