Find what could change your view. Research the unknowns in chat, compare evidence and saved model reasoning, and keep your team’s decisions connected to why they were made.
New teams: send a non-confidential inquiry. Workspace access is by invitation.
Follow one hypothetical rates review from its starting view to a revised thesis. The evidence and interpretations are authored illustrations.
Illustrative committee rationale: easing inflation should create room for lower policy rates.
The assumptions underneath it
Price pressure continues to ease rather than becoming persistent.
The policy-rate path has room to move lower as inflation moderates.
The case for longer duration survives a less favorable rate path.
Suppose a new inflation release challenges the disinflation assumption while an employment release points to softer demand. The signals pull the thesis in different directions.
In a real review, attach the source, release date, exact series and relevant vintage before treating either observation as evidence.
Authored interpretations for this example. In your workspace, compare available saved model reasoning and dates alongside the evidence.
An investment view with defined supporting questions, a review horizon and evidence that could change it.
Thesis: easing inflation supports duration. Supporting Yes / No condition: will December 2027 core PCE inflation be at or below 2.5% year over year?
Numeric questions and ranges for rates, inflation, valuation or another driver, with units, horizons and saved estimates.
What will the average U.S. 10-year Treasury yield be during Q4 2027, expressed as a percentage?
Compare several plausible pathways and the conditions behind each for questions that need more than a binary outcome.
How would sticky inflation, orderly disinflation or recession change the policy-rate path?
A view moves through research, debate and decisions. Keep the people, evidence and rationale connected so the next review can start from what actually happened.
The public corpus and private workspace track records are separate. Personal forecasts and model estimates are scored against their own eligible outcomes.
Start with a question in chat. Crene helps connect the investment view to supporting questions, dated research, saved model reasoning and review decisions. The structured record makes the assumptions and subsequent changes easier to inspect.
They show available models’ saved assessments of a defined question, with their reasoning and dates. Differences help the team examine competing assumptions. Disagreement is not a confidence interval or proof of forecast accuracy.
Workspace members can assign an owner and reviewer, set a task due date, comment and mention colleagues in the app. A review task, a team decision, a personal forecast and an event outcome are separate records.
Requests depend on workspace access, selected models and usage limits. On-demand assessments show a cost preview and require confirmation. Recurring monitoring has its own controls; opening saved results does not run another assessment.
Eligible resolved binary forecasts can be evaluated using Brier scores and calibration analysis. Public historical corpus scores are separate from private workspace track records; personal forecasts and model estimates use their own eligible outcomes. These scores do not establish trading returns.
A private review is scoped to one team and arranged by invitation. If a shared demo is offered, use sample information only. Send a non-confidential summary in the public inquiry, then agree member access, provider usage and the information to be shared before the review.
Use a six-week private review to define one thesis, examine the evidence and model disagreement, and retain the team’s review decisions.
One thesis. One team. Six weeks.
Workspace access is arranged by invitation after the scope review. Sending an inquiry does not create an account. Share a non-confidential summary to start.