Housecarl
Operational Open the console →
Docs

How it works, with a worked example

How it works

The problem

You have a question with real money or real consequences attached. Multiple sources are telling you different things. Some are trustworthy, some aren't. Some claims are old, some are fresh. Some directly contradict each other. You need to know: what should I actually believe, how confident should I be — and can I defend this call when someone asks how I made it?

A summary won't get you there. A summary doesn't tell you who to trust, what's gone stale, or what happens to your conclusion if one source turns out to be wrong. That's the job Housecarl Arbiter does.

What the engine does

Four things, automatically, on every investigation:

  • It weighs who's talking. Not every source deserves an equal say. A regulator on the record carries more weight than an anonymous tip. A company commenting on its own conduct gets discounted for the obvious conflict of interest. You set how much you trust each source; Arbiter applies it consistently, on every claim, without fatigue or favoritism.
  • It knows what's gone stale. Old information quietly loses its grip on the verdict. How fast depends on what kind of information it is — financial figures go stale in months, scientific findings hold for decades — and a claim that independent sources keep confirming stays fresh longer. When a newer statement explicitly replaces an older one, the older one stops driving the conclusion, though it stays visible in the record.
  • It doesn't double-count. One source repeating itself ten times is still one source. Two independent sources saying the same thing — that's real corroboration, and the verdict gets stronger. This is the single most common way people fool themselves with research, and Arbiter simply doesn't allow it.
  • It handles disagreement honestly. When sources contradict each other, Arbiter doesn't quietly average them or pick a side for you. It lays out every reading of the evidence that holds together, shows you who backs each one and how strong each is, and lets you see exactly why the leading interpretation leads. Claims that only look like they conflict — "global revenue" versus "US revenue" — aren't forced into a fight.

What you get back

  • A bottom-line verdict for each thing you asked about: what the evidence supports, a single confidence number you can act on, and an honest statement of how much is still unknown — stated, not hidden.
  • Every claim, ranked from strongest to weakest on a five-level scale: strong, moderate, contested, weak, refuted. You can see at a glance which parts of the story are solid and which are riding on thin evidence.
  • The reasoning, on the record. Any conclusion can be traced back to who said what, when, and how much weight it carried. When someone asks "why did you believe that?" — a partner, a board, a compliance review, your future self — the answer is sitting right there.
  • What to check next. Arbiter tells you which piece of missing evidence would most change the answer. That's your next phone call, your next document request, your next hour of research — chosen for maximum effect instead of guessed at.

Worked example

A financial fraud investigation using characters from Arthur Conan Doyle's Sherlock Holmes stories (public domain).

The scenario

Moriarty Enterprises Ltd is a London-based consulting firm run by Professor James Moriarty. It also manages the Reichenbach Investment Fund. Multiple sources have raised concerns about fabricated revenue and fund insolvency. The research question: "Is Moriarty Enterprises engaged in financial fraud?"

If you held a position in that fund, this is not an academic question. The cost of believing the wrong people is the position.

The sources

SourceType · reliabilityRole
Sherlock HolmesExpert · 0.92Private consulting detective. Deep forensic analysis of financial records.
Dr. John WatsonJournalist · 0.75Medical doctor and chronicler. Accompanied Holmes during the ledger review.
Inspector LestradeRegulator · 0.8Scotland Yard inspector. Represents the official regulatory inquiry.
Irene AdlerInsider · 0.65Former portfolio manager at the Reichenbach Fund. Terminated, claims whistleblower status.
Prof. James MoriartyInstitutional · 0.3CEO of Moriarty Enterprises. The subject of the investigation. Rated low due to conflict of interest.
The Times of LondonJournalist · 0.7London's paper of record. Reporting based on City sources.
The Daily TelegraphJournalist · 0.65National broadsheet. Independent investigative reporting on investor withdrawal failures.

What makes this hard — and what Arbiter does with it

Everyone disagrees. Holmes, Watson, Adler, and Lestrade all say something is wrong. Moriarty says everything is fine. Arbiter doesn't take a vote — it weighs each source's credibility and shows you every version of events that holds together.

Not all sources are equal. Holmes, a respected outside expert, carries far more weight than Moriarty, who is talking about himself. Watson agrees with Holmes — but he was in the room with Holmes, so his agreement adds less than a truly independent source would.

The claims span months. The oldest report has faded slightly by the time of judgment; the newest carries full weight. Arbiter handles this for you and shows the freshness of each claim.

Some claims come with receipts. Holmes's claims are backed by physical ledgers and court-ordered bank statements. Moriarty's rebuttal cites an audit by a firm of questionable standing — admitted, but lightly weighted.

Full investigation input

This is exactly what gets submitted to Arbiter — every source, claim, and piece of evidence, with who said it and when. It's shown in full so you can see there's nothing up the sleeve. If someone else will handle the wiring, skip ahead to the results — and note that you don't have to write this by hand: the extraction prompt builds it from your source documents, or Claude can do the whole thing conversationally.

{
  "research_question": "Is Moriarty Enterprises engaged in financial fraud?",
  "domain": "Finance",
  "dependent_refresh_factor": 0.5,
  "actors": [
    {
      "id": "holmes",
      "name": "Sherlock Holmes",
      "source_type": "Expert",
      "base_reliability": 0.92
    },
    {
      "id": "watson",
      "name": "Dr. John Watson",
      "source_type": "Journalist",
      "base_reliability": 0.75
    },
    {
      "id": "lestrade",
      "name": "Inspector Lestrade",
      "source_type": "Regulator",
      "base_reliability": 0.8
    },
    {
      "id": "adler",
      "name": "Irene Adler",
      "source_type": "Insider",
      "base_reliability": 0.65
    },
    {
      "id": "moriarty",
      "name": "Prof. James Moriarty",
      "source_type": "Institutional",
      "base_reliability": 0.3
    },
    {
      "id": "times",
      "name": "The Times of London",
      "source_type": "Journalist",
      "base_reliability": 0.7
    },
    {
      "id": "telegraph",
      "name": "The Daily Telegraph",
      "source_type": "Journalist",
      "base_reliability": 0.65
    }
  ],
  "subjects": [
    {
      "id": "moriarty-ent",
      "name": "Moriarty Enterprises Ltd",
      "subject_type": "Company"
    },
    {
      "id": "reichenbach-fund",
      "name": "Reichenbach Investment Fund",
      "subject_type": "Financial Instrument"
    }
  ],
  "claims": [
    {
      "id": "c1",
      "actor_id": "holmes",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "fabricated",
      "content": "After examining the ledgers obtained from the Diogenes Club, the reported revenue of Moriarty Enterprises bears no correlation to actual client payments. At least 40% of stated revenue traces to circular transactions between shell entities.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "assertion_time": "2026-02-15T10:00:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z",
      "corroboration_events": [
        {
          "time": "2026-02-16T14:00:00Z",
          "actor_id": "watson",
          "description": "Watson independently confirmed ledger discrepancies during joint review"
        },
        {
          "time": "2026-02-28T06:00:00Z",
          "actor_id": "times",
          "description": "The Times reported industry observers could not reconcile stated revenue with known engagements"
        }
      ]
    },
    {
      "id": "c2",
      "actor_id": "watson",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "fabricated",
      "content": "I accompanied Holmes during the ledger review. The discrepancies he identified are real, though I cannot independently verify the 40% figure. The pattern of circular billing is consistent with what I have seen in other fraud cases I have reported on.",
      "valence": "Supports",
      "claim_type": "Evaluative",
      "epistemic_status": "hypothesis",
      "assertion_time": "2026-02-16T14:00:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c3",
      "actor_id": "lestrade",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "under-investigation",
      "content": "Scotland Yard has opened a preliminary inquiry into Moriarty Enterprises' financial statements following a referral from the Serious Fraud Office. We cannot confirm or deny specific allegations at this time, but the inquiry is active.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "hypothesis",
      "assertion_time": "2026-03-01T09:00:00Z"
    },
    {
      "id": "c4",
      "actor_id": "moriarty",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "legitimate",
      "content": "Our accounts are audited annually by a reputable firm. All revenue is from legitimate consulting engagements. The so-called discrepancies reflect complex multi-party arrangements that an untrained eye might misinterpret.",
      "valence": "Refutes",
      "claim_type": "Factual",
      "assertion_time": "2026-03-05T11:00:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c5",
      "actor_id": "adler",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "insolvent",
      "content": "I was employed by Moriarty Enterprises as a portfolio manager for the Reichenbach Fund from 2024 to 2025. The fund's reported assets are overstated by at least 60%. Client redemptions are being paid from new investor deposits, not returns.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "assertion_time": "2026-01-20T08:00:00Z",
      "corroboration_events": [
        {
          "time": "2026-02-10T07:00:00Z",
          "actor_id": "telegraph",
          "description": "Telegraph independently confirmed investor withdrawal failures starting November 2025"
        },
        {
          "time": "2026-02-20T16:00:00Z",
          "actor_id": "holmes",
          "description": "Holmes obtained bank records confirming deposit-to-redemption routing"
        }
      ],
      "event_start_time": "2024-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c6",
      "actor_id": "holmes",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "insolvent",
      "content": "The Reichenbach Fund is a Ponzi scheme. Bank records show deposits from new investors being directly routed to redemption accounts. The fund has held no actual securities positions since Q2 2024.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "assertion_time": "2026-02-20T16:00:00Z",
      "event_start_time": "2024-04-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c7",
      "actor_id": "moriarty",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "solvent",
      "content": "The Reichenbach Fund returned 18% to investors in 2025 and maintains full reserves. Ms. Adler was terminated for cause and her claims are retaliatory. We welcome any audit.",
      "valence": "Refutes",
      "claim_type": "Factual",
      "assertion_time": "2026-03-05T11:30:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c8",
      "actor_id": "lestrade",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "under-investigation",
      "content": "The Financial Conduct Authority has frozen the Reichenbach Fund pending investigation. Investor withdrawals are suspended.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "supersedes_claim_id": "c3",
      "assertion_time": "2026-03-10T09:00:00Z"
    },
    {
      "id": "c9",
      "actor_id": "times",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "questionable",
      "content": "Sources within the City suggest that Moriarty Enterprises has been the subject of quiet inquiries by multiple creditors. The firm's reported consulting revenue is difficult to reconcile with the scale of its known client engagements, according to industry observers.",
      "valence": "Supports",
      "claim_type": "Evaluative",
      "epistemic_status": "conjecture",
      "assertion_time": "2026-02-28T06:00:00Z",
      "corroboration_events": [
        {
          "time": "2026-03-01T09:00:00Z",
          "actor_id": "lestrade",
          "description": "Scotland Yard confirmed an active inquiry, corroborating reports of creditor concerns"
        }
      ],
      "event_start_time": "2025-06-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c10",
      "actor_id": "telegraph",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "concerns-raised",
      "content": "The Daily Telegraph can reveal that at least three prominent investors in the Reichenbach Fund have been unable to withdraw their capital since November. Prof. Moriarty has attributed the delays to 'administrative restructuring' but has not provided a timeline for resolution.",
      "valence": "Supports",
      "claim_type": "Factual",
      "assertion_time": "2026-02-10T07:00:00Z",
      "event_start_time": "2025-11-01T00:00:00Z",
      "event_end_time": "2026-02-10T00:00:00Z"
    },
    {
      "id": "c11",
      "actor_id": "telegraph",
      "subject_id": "moriarty-ent",
      "predicate": "reputation",
      "value": "deteriorating",
      "content": "Several former associates of Prof. Moriarty have distanced themselves from the firm in recent months. The Diogenes Club has reportedly revoked his membership, an unusual step for the notoriously discreet institution.",
      "valence": "Supports",
      "claim_type": "Evaluative",
      "epistemic_status": "conjecture",
      "assertion_time": "2026-03-02T07:00:00Z"
    }
  ],
  "evidence": [
    {
      "id": "e1",
      "claim_id": "c1",
      "content": "Ledger photocopies from the Diogenes Club showing circular transactions",
      "valence": "Supports",
      "weight": 1.2
    },
    {
      "id": "e2",
      "claim_id": "c5",
      "content": "Adler's employment contract and internal fund reports",
      "valence": "Supports",
      "weight": 1
    },
    {
      "id": "e3",
      "claim_id": "c6",
      "content": "Bank statements obtained via court order showing deposit-to-redemption routing",
      "valence": "Supports",
      "weight": 1.5
    },
    {
      "id": "e4",
      "claim_id": "c4",
      "content": "Annual audit report from Milverton & Associates LLP",
      "valence": "Supports",
      "weight": 0.5
    }
  ]
}

What the engine returns

Moriarty Enterprises — revenue. The verdict: the revenue is very likely fabricated. An outside expert and an accompanying journalist both say so, a regulator confirms an active investigation, and the company's own denial carries little weight — it's the subject talking about itself. The verdict is honest about the fact that contradicting evidence exists; it just shows you why that evidence loses.

Reichenbach Fund — solvency. The verdict: very likely insolvent. A former insider gives firsthand testimony, the expert corroborates it with court-ordered bank records, and the regulator has frozen the fund. Moriarty claims 18% returns — but with low credibility and no real evidence behind it, that claim ranks dead last.

Every claim, ranked

  1. Strong — Holmes: Reichenbach Fund is a Ponzi scheme (backed by bank statements)
  2. Strong — Holmes: Revenue is fabricated (backed by ledger photocopies)
  3. Strong — Lestrade: FCA has frozen the Reichenbach Fund
  4. Strong — Adler: Fund assets overstated by 60%
  5. Strong — Lestrade: Scotland Yard inquiry is active
  6. Moderate — Watson: Circular billing pattern is consistent with fraud
  7. Moderate — The Times: Revenue difficult to reconcile with known engagements
  8. Moderate — The Telegraph: Investors unable to withdraw since November
  9. Moderate — The Telegraph: Former associates distancing, Diogenes Club membership revoked
  10. Weak — Moriarty: Milverton & Associates audit found no irregularities (low-weight evidence)
  11. Refuted — Moriarty: Revenue is legitimate
  12. Refuted — Moriarty: Fund returned 18% and maintains reserves

Both sides of the story, on the record

Arbiter finds two versions of events that internally hold together:

  • The dominant reading. Holmes, Watson, Adler, and Lestrade are right; Moriarty's denials fail. This reading is strongly supported and hangs together well.
  • The alternative reading. Moriarty's denials are true and the investigations come to nothing. This reading survives as a logical possibility — Arbiter won't pretend it doesn't exist — but the credibility behind it is a fraction of the dominant one.

This is the part you can't get from a summary: not just "fraud is likely," but here is the losing story, here is exactly who you'd have to believe for it to win, and here is why that's a bad bet. If this were your money, that's the difference between a hunch and a decision you can defend.

Try it yourself

Copy the JSON above and submit it via the console, API, or MCP tool. It starts free — no card required. Open the console.

Next: use Arbiter from Claude with no code, or connect your own tool over REST and MCP.