Part 2 of 2. Part 1 was about the questions a model simply can't answer. This one is about the larger, sneakier set, where the model hands you a perfectly plausible answer, and the problem is everything it quietly left out.

In Part 1, the failure was obvious: ask a model for the deep roster of a field and it runs dry or invents. Most real questions are not like that. Ask a model to "build me a panel" or "give me ten experts to call" and it produces a confident, reasonable-looking list. That is the dangerous case, because the list looks complete, and you have no way to see what is missing from it.

The fix is not to replace the model. It is to let the model draft freely, then run its answer through the Authority Index as a verification-and-completion pass: confirm the names are real, and surface the people the model could not see it had omitted.

The loop

  1. Claude drafts a first-pass answer from its own knowledge.
  2. Authorix match checks the drafted names: real authorities, and in which lane.
  3. Authorix index retrieves the authorities on the topic the draft missed.
  4. Claude revises into a final answer that is verified and complete.

A worked example: a panel on the future of nuclear energy

We asked a frontier model, unaided, to assemble an eight-person panel. It produced a real, credible list: Jacopo Buongiorno, Per Peterson, Kathryn Huff, Rachel Slaybaugh, Ashley Finan, Leslie Dewan, Isabelle Boemeke, Mark Nelson. Nothing invented. But look at the shape of it: every name is US-based, every name is pro-nuclear, and the mix skews to academics and advocates.

Then we ran the draft through Authorix.

Claudewith Authorix connected
You
Build me an 8-person panel on the future of nuclear energy.
draftBuongiorno, Peterson, Huff, Slaybaugh, Finan, Dewan, Boemeke, Nelson
Authorix· matchtool call
names: 8 drafted
Authorix match
All 8 names verified real. Roughly 5 technical / domain authorities, 3 advocates / communicators.
Authorix· indextool call
topic: "future of nuclear energy"
Authorix returned the authorities the draft missed
NameAffiliationFocus
Anil KakodkarFormer Chairman, Atomic Energy Commission of IndiaThorium programme
Valérie FaudonExecutive Director, French Nuclear Society (SFEN)Nuclear policy
Jacob DeWitteCo-founder & CEO, OkloAdvanced fission
Ville TulkkiVTT, FinlandSmall modular reactors
Edwin LymanUnion of Concerned ScientistsReactor safety (credible critic)
…and 200+ more across France, Japan, India, Finland, the Netherlands and beyond
revised panelHuff and Buongiorno stay as the technical anchors, but the draft was US-only, all-advocate, and missing the operators and the skeptics. A balanced panel adds Kakodkar (the global heavyweight I omitted entirely), Faudon (Europe's nuclear establishment), DeWitte (the startup builder), and Lyman (a credible safety critic). That is a panel; the draft was an echo chamber.

What we measured

Two things, on this one query.

The draft was real but narrow. Every drafted name verified as a real person, zero fabrications. But the index's bios revealed the composition the model could not: around 5 domain authorities and around 3 advocates and communicators, all from one country and one stance.

For this panelClaude's draftAfter the Authorix cross-check
Drafted names verified real8 / 88 / 8
Countries represented1 (US)many
Stances representedpro-nuclear onlypro and credible critics
Industry / startup operators~1many

One query, one run. Counts of added experts are approximate tallies.

What Claude's panel covered vs the index added
Claude's draftAuthorix added
distinct experts surfaced (one run, approximate)0510152025020Non-US authorities110Industrystartup leaders03Credible critics
The draft was real but narrow: US, pro-nuclear, academic. The index surfaced the perspectives a balanced panel needs but the model could not see were missing. Counts are approximate, from one run.

Verification plus right-sizing. The cross-check did not catch a fake, the draft had none. Its value was completion: turning a real-but-lopsided list into a balanced one, with the bios to know which seat each person fills.

Claude's 8 drafted names, checked against the index
Verified domain authorities (5) Verified advocates / communicators (3) Fabricated / unverifiable (0)
538 drafted names · 0 fabricated
Every drafted name verified real, zero fabrications. The index's bios then right-size each one, domain authority versus advocate and communicator, so the lineup can be balanced on purpose.

What this does, and does not, claim

As in Part 1, the honest line.

The index returns real people, and the ones the model missed. It does not claim a perfect ordering of who matters most, or that every result is a tight topical match.

What this does and does not claim

What it reliably fixes is the blind spot: the geographies, sectors, and dissenting voices a model's confident first draft silently omits. What we are not claiming: a perfect ordering of who matters most, or that every result is a tight topical match. Ranking and relevance precision are work in progress.

That is the whole point of the loop. The model is good at producing a fluent first answer; it is bad at knowing what it left out. The index is the opposite. Together they produce an answer that is both well-reasoned and complete, which neither does alone.

The two posts together

Part 1: the questions a model cannot answer, where the index is the only source. Part 2: the answers a model gives confidently, where the index catches the blind spots. Same underlying fix in both, ground the model in verified, real-world authority data, pointed at the two different ways a model falls short.

Draft, then cross-check

$5 in free credits. No credit card required.