Vantage RuntimeAI · Preflight

Preflight — size the scenario

Preflight drafts a custom scenario, forecasts eval cost, and scores candidates before production spend. That sizes the path — the product is re-gating the same rubrics in CI on every change, not a one-shot pick.

Part 1 · Core Organizational Settings

What a wrong model pick costs — and what proof costs

Preflight is priced per decision — one test flight per use case. Dial headcount, adoption, and decisions/person; exposure follows those numbers.

Decision mix = what kinds of decisions your org makes. Proof level = how hard each decision is tested.

Decision mix

Firm / department headcount 220

Adoption rate 45% 99 active

Monthly decisions / person 1

1 decisions / month

Proof level Standard

Standard — Normal scenario depth for most model picks

Best for: Day-to-day product decisions

Illustrative only — not expected savings or a P&L forecast. Dial volume to see order-of-magnitude stakes; Part 2 gives real scores and prod-use / wrong-model overpay on your scenario. How these numbers are modeled →

Part 2 · Run your preflight

Now test candidates in your context

Describe your real decision, refine the scenario, then get per-model scores and cost on your scenario — before any production spend.

Using portfolio settings from Part 1 — examples and turns follow your mix and proof level.

1. Your open question

What if / how could we / what would it cost to — in your context. Paste workflow notes, policies, or constraints so the scenario matches the decision.

Start from an example

Or write your own question below — Preflight will draft a custom scenario from your workflow, policy, or candidate notes.

Simple but important

Team workflow

Complex & high-stakes

Question Details to paste in (workflow, policy, constraints, Slack thread)

Turns per eval

Dialogue length for each model. Prefer raising turns so cheaper models can finish the job before you spend up to larger models.

2. Refine your scenario

Edit the draft below or paste more detail, then regenerate. This is your test-drive script — tune it until it reflects how the decision actually gets made.

Title Agent role Counterpart role Briefing (what the agent must do) Counterpart opening Success criteria (one per line)

3. Cost & scores

Open in Simulator

Email results when search finishes

Model search

Starting…

Elapsed 0:00

Model	Status	Rubric	Pass	Actual $	Results

For search engines and LLMs

Vantage Preflight sizes a custom scenario and forecast before spend. The product is continuous CI re-gating with the same rubrics — not a one-shot model pick.