Readiness quiz

2. Do we have a dated, reasonably optimised baseline?

Frontier Development research deskSection 08 · Page 4 of 20Last updated 26 October 2026

A — 0: There is only a demo or an undocumented current model. B — 1: The current configuration is recorded, but obvious prompt/schema/retrieval fixes are untested. C — 2: The current and improved practical baseline have been tested with versions, settings and results saved.

Evidence to attach: model/endpoint, prompt, corpus version, date and measured outcomes. If weak: spend a bounded period improving the comparator; do not let the supplier choose a deliberately weak baseline.

Question 2 of 12

Do we have a dated, reasonably optimised baseline?

Evidence to show: model/endpoint, prompt, corpus version, date and measured outcomes.

Read the full question →

A desk-designed readiness rubric, not a validated prediction of success. Progress stays in this browser; no answers are sent to the desk.

TRACE THE EVIDENCE

Section source library

This page contains no direct external citations. These are the section’s references; they do not independently validate the desk’s proposed scoring or methods.

Demystifying evals for AI agents — Anthropic, 9 January 2026 →www.anthropic.com
Llama 3.3 Community License Agreement — Meta →github.com
AI Risk Management Framework — NIST →www.nist.gov
RouteLLM: Learning to Route LLMs with Preference Data — Ong et al., revision 23 February 2025 →arxiv.org
A Field Guide to Rapidly Improving AI Products — Hamel Husain →hamel.dev
GroupKFold — scikit-learn documentation →scikit-learn.org
Pricing — Together AI, snapshot checked 26 October 2026 →www.together.ai
The Inference Engineering Masterclass — Philip Kiely and Ali Taha, Latent Space, 3 August 2026 →latent.space
The Open Source AI Definition 1.0 — Open Source Initiative →opensource.org
SB26-189 Automated Decision-Making Technology — Colorado General Assembly →leg.colorado.gov
Guidance on HIPAA & Cloud Computing — HHS Office for Civil Rights →www.hhs.gov