Verdict

All 6 tools

Pull the unchecked beliefs out of a brief and turn each into a question you could answer this week.

find_assumptions

Before: what you give it

The example input, as sent.

Problem: agencies waste hours every month building client SEO reports by hand. Users want a one-click monthly report emailed to their clients automatically, so we will add a Reports tab with a branded PDF export and a scheduler. Most agencies already use Google Search Console, and clients obviously care about clicks and impressions. Success is a 20% increase in paid seats within a quarter. We will launch to all users at once.

After: what comes back

A real run of this tool has not been captured for this page yet, so there is no sample to show. Run the request below to see the answer for yourself.

What you get

Assumptions ranked by risk, each paired with a research question.

What gets better

The riskiest guess in the plan gets tested first, before it is built into the roadmap.

When to use it

Before a PRD goes to review, or before a launch plan is committed.

What it cannot do

It works from the text of the brief, up to 30,000 characters. It cannot know what your team has already validated.

Run it

Two free calls a day with no key. Send your own Anthropic key in an x-anthropic-key header to lift the limit.

curl -X POST https://verdict.allthepossibles.com/api/find_assumptions -H 'content-type: application/json' -d '{"prd_text":"Problem: agencies waste hours every month building client SEO reports by hand. Users want a one-click monthly report emailed to their clients automatically, so we will add a Reports tab with a branded PDF export and a scheduler. Most agencies already use Google Search Console, and clients obviously care about clicks and impressions. Success is a 20% increase in paid seats within a quarter. We will launch to all users at once."}'

Full input schema in the docs

The other reviews