retirement-answer-check

Checks an AI assistant's draft answer to a US retirement-account question before it reaches a customer, and returns SEND or REVIEW with an IRS or FINRA source for every flag.

It is a checker, not an advisor. It never writes answers and never gives financial advice.

Reference build by an AI product manager: PRD → eval plan → build → blind evals → release gate. Not affiliated with any financial firm; public IRS and FINRA sources only. Not financial or tax advice.

What it flags

Any flag → REVIEW. When a layer is unsure, it flags.

Related MCP server: gnt MCP Server

How it works

1. MCP server (check_answer, get_facts). Fast, deterministic pattern rules for numbers, rules, scope, and obvious phrasing. Both tools are read-only and annotated that way.

2. fact-judge skill. A model reads the facts table and checks every claim, including ones that aren't numbers ("yes, that's exempt", "due by December 31").

3. advice-judge skill. A model judges the advice boundary and promissory language.

Every number in facts.json was read from the cited IRS page on 2026-09-26: 2026 limits, IRA limits, RMDs, rollovers, early distributions.

Results

Thresholds were set before the first run. Two of the three case sets were written by separate agents that never saw the checker's rules or the other cases. Each held-out set was committed before it was run.

Pattern rules alone, first run on each blind set:

That fails the top-harm gate. The misses were claims that aren't numbers ("exempt", "by December 31", "up to two"), or the account type appearing only in the question. Adding patterns for each miss would just fit the test set, so the fix was a second layer.

Full system (rules + fact-judge + advice-judge), each judge run blind 3 times:

The 2 false REVIEWs were true statements the facts table doesn't cover (beneficiary RMD rules; Roth vs. traditional tax treatment). The fact judge flagged them as unknown_fact, as its spec says it should.

Limits of these results:

• 83 synthetic cases. Real traffic is messier, and a real deployment should start in shadow mode (PRD §8).

• The judges and the case writers are all Claude, so they may share blind spots.

• The advice judge wasn't run on held-out set 2, which has only fact cases, so its false-flag rate there wasn't measured.

• The facts table covers 2025 and 2026. It needs an update each November when the IRS publishes new limits. Until then, answers citing the new year go to REVIEW.

Raw outputs: evals/ (cases, first-run logs, all judge runs).

Human review queue: is the review itself working?

Every REVIEW goes to a person. But people reviewing AI output measurably miss its errors: consultants using GPT-4 were 19 percentage points less likely to be right on a task outside what it handles well, and the EU AI Act (Art. 14(4)(b)) names automation bias outright. Of 10 LLM review tools checked, 7 give no way to test whether reviewers catch errors (decision record).

review/ adds that test. It mixes known-answer checks into the queue, cases whose right verdict is already known, and they look exactly like real items:

python review/build_queue.py            # -> review/out/review.html (for the reviewer) + key.json (keep it from them)
# the reviewer opens review.html, decides each item (A / R keys), downloads their decisions
python review/score.py review-decisions-<name>.json review/out/key.json

Try it: the demo queue (source: docs/review-demo/) has 29 items, 6 of them checks, built with the default seed 7. Its key isn't committed, but anyone can rebuild it from this public repo, so for real reviews build with your own private --seed.

The page is one self-contained file with no server and no tracking. Progress is saved in the reviewer's browser. The answer key is never in the page, and a test enforces that.

Scripted reviewers on the demo queue (policies, not people; python review/score.py --policy <name> review/out/review.html review/out/key.json) show each check doing its job:

Not yet known: how real reviewers score. That needs real people and will be reported as-is. Demo caveat: the demo has few live answers, so 4 of its 11 audit samples are tests. In production the checker passes far more answers than it flags, so audit samples would be mostly real.

Use it in Claude Code

claude mcp add retirement-answer-check -- uvx --from git+https://github.com/vishalhabib99/retirement-answer-check retirement-answer-check
cp -r skills/fact-judge skills/advice-judge ~/.claude/skills/

Then: "Check this draft answer: …". Claude calls check_answer, then runs both skills. Any flag means REVIEW.

Deterministic layer from Python:

from retirement_answer_check import check
check("What's the IRA limit for 2026?", "It's $7,000.")
# {'decision': 'REVIEW', 'flags': [{'type': 'wrong_fact', 'span': '$7,000',
#   'reason': 'not a 2026 ira limit (that is the 2025 figure)', 'source': 'https://www.irs.gov/...'}]}

Run the evals: python evals/run.py evals/heldout2.jsonl evals/judge/all_layers.json

License

MIT