Source-weighted fusion
Every source carries a reliability score. A filing outweighs an anonymous tweet; conflicts of interest are discounted automatically.
Housecarl Arbiter · Formal reasoning engine
Decisions you can defend.
Three credible sources. Three different conclusions. Your AI picks one and sounds certain. Arbiter weighs every source by reliability and recency, fuses contradictory claims into a single scored verdict, and shows you exactly where the uncertainty lives.
No gut calls. No vibes. The reasoning is on the record.
$0
To start — no card
5 min
From Claude to first verdict
100%
Decisions on the record
The capability set
Contradiction detection
See where analysts actually disagree — every coherent interpretation, who supports it, and how confident you should be.
Temporal decay
Claims lose weight as they age. Stale rumors don't pollute a live thesis.
A full audit trail
Every claim has a source, a score, and a timestamp. Retrace the reasoning after the decision.
Available via API and MCP — connect from Claude, ChatGPT, or any agent. No CLI required.
Sound familiar?
Your AI sounds sure — and it's wrong.
Fluent answers, invented citations, contradictions smoothed over. What to do when you can't trust the confidence →
Your sources don't agree.
Twelve tabs, three conclusions, one decision that won't wait. How to settle it with the evidence weighed →