open source · BYOK · MIT

ask-the-board

A board of expert personas whose every decision is a pre-registered, time-anchored, reality-graded bet.

Not a chatbot that agrees with you — a board that keeps score, before the fact.

$ pip install asktheboard
asktheboard in the terminal: create a board-minute, resolve it against reality, then score -- the dissenting seat was wrong this time, and the board kept the receipt.

Mechanism on sample data — the 60-second, no-key walkthrough below reproduces it exactly.

LIVE · bet #1 of a public cadence

The board's first public call — graded by reality on a fixed date

Filed in the open, anchored in git, resolved on the date against a source nobody controls. No edits after the anchor — that is the whole point.

Will the June 2026 US jobs report show +150,000 nonfarm payrolls or more?
The board calls yes at 56%. Anchored 2026-06-27; resolves 2026-07-02 against the BLS Employment Situation release.

seatstanceP(+150k)the call
researcheraffirm60%central case clears the line; revisions shave the margin
strategistaffirm58%labor market has beaten every cooling call this cycle
skepticdissent40%150k is the median — a coin-flip dressed as a call

Come back July 2 and watch it grade. The board may turn out wrong, and the git anchor means it cannot pretend otherwise. Full board-minute: examples/2026-06-jobs-report.md.

Why this exists

Anyone can clone a “panel of AI personas” in a weekend, and a dozen have. The debate mechanic is a commodity. What it leaves out is the thing that makes advice worth trusting: a record of having been right before the outcome was knowable. That record is hard to fake — you can buy model outputs, but you can’t back-date a timestamp.

So ask-the-board records, for every decision:

  1. your stated prior — what you believed going in;
  2. the per-seat dissent vector — each seat’s stance + its own probability;
  3. a dated, falsifiable prediction, anchored before the outcome is knowable;
  4. on the resolution date, reality’s realized outcome, auto-reconciled into a Brier / calibration score per seat.

The board-minute is a git-committable ADR. Your git history is the external attestation of the anchor timestamp. The accumulating, reality-graded record is the durable asset.

See it keep score

create → resolve → score is pure data — no LLM, no key, no network. This is a worked example on sample data: you supply the outcome with resolve, and the engine computes each seat’s Brier score (lower is better). It shows the mechanism, not a track record — the integrity comes from the anchor timestamp your git history attests, which no demo can fabricate.

seatnmean_brierwinslosses
pragmatist10.04000
skeptic10.42301

On a real, dated minute the same mechanic produces a contrarian win — a seat that dissents and turns out more right than the board. That’s the gold the aged public scoreboard is built from, once minutes resolve against reality you didn’t set.

What you get

BYOK, zero COGS

The engine ships no provider and makes no calls of its own. You bring your own key and pay your own inference, so it costs nothing to run at any scale.

Zero runtime dependencies

The OpenAI-compatible HTTP client is stdlib-only. Point it at OpenAI, OpenRouter, Together, or a local server.

Integrity enforced in code

You can’t pre-register a prediction onto a known outcome, and you can’t grade a minute before its resolution date. That’s what makes it foresight.

A bundled board

Role archetypes — architect, skeptic, pragmatist, researcher, operator, strategist — and named panels, so seating one is a single lookup. The skeptic sits on every panel by design.

Hosted tier — join the waitlist

The OSS engine is free forever and runs on your own key. If you’d rather not manage keys — or you want the aged, reality-graded public scoreboard hosted for you — a managed, capped paid tier is coming.

Email [email protected] with the subject waitlist

A one-liner on what you’d decide with it helps, but isn’t required. No spam — one note when it opens.