5 Savvy product samples Unofficial concept, synthetic data
Unofficial concept, not affiliated with Savvy. All data synthetic. Built only from public information. Happy to take it down on request.
Grow Book IQ

Next-best-action queue

A ranked queue for Dana Whitfield's 12-household book. Every row pairs a recommendation with the household record behind it, a modelled asset opportunity at the 0.90% fee, and a draft outreach that waits for a named approval. The user is the adviser or growth lead who reviews the queue.

What this demonstrates: one batched ranking call over the 12 household records, then one drafting call per household. The model proposes a play and a draft. The adviser approves or rejects. The guardrail re-checks every number, and nothing is sent.

live model, recorded deepseek-flash Nov 19, 2026, 05:53 UTC How this is built
One call. 0 of 150 live calls today.
Modelled net new assets USD 4,476,952 10.6% of the USD 42,300,000 book. 11 of 12 households have a growth play. Largest: Lindqvist Household, Referral, USD 1,024,000. Average per growth household: USD 406,996.
Annual fee at 0.90% USD 40,293 Fee on the modelled assets. Not a forecast.
Plays by type
  • Consolidate held-away assets3
  • Reinvest excess cash2
  • Schedule an overdue review1
  • Plan for a required distribution1
  • Reduce concentration1
  • Ask for a referral2
  • Act on a life event1
  • No action this cycle1
Review status
12 in review 0 approved 0 rejected
3 households with consent pending cannot be approved.
Modelled assumptions and the arithmetic behind every opportunity
PlayRequired signalModelled net new assets
Consolidate held-away assets held_away 25 percent of held-away assets, the modelled share that moves in the first year.
Reinvest excess cash cash_drag All cash above the 5 percent target, modelled as invested.
Schedule an overdue review overdue_review AUM x 10 percent modelled at risk x 25 percent protected by a review.
Plan for a required distribution rmd_window 35 percent of the estimated RMD, modelled as retained and reinvested.
Reduce concentration concentration 20 percent of the restricted position value, modelled as diversified over time.
Ask for a referral referral_source One new household at 20 percent of the referrer's assets, the modelled size of a qualified introduction.
Act on a life event life_event 50 percent of the assets tied to the event, modelled as repositioned.
No action this cycle none No growth play clears the record this cycle.
Fee rate
0.90% a year, applied to modelled net new assets
Cash target
5% of household AUM
Review cadence
365 days
RMD factor
26.5 at age 73, Uniform Lifetime Table
Data
data/book.json plus the synthetic enrichment in scripts/generate_bookiq.py
  • Every figure is modelled from the seeded book plus the fixed enrichment tables in scripts/generate_bookiq.py. Nothing here is measured.
  • Modelled net new assets is an annual opportunity, not a forecast. The fee line applies the 0.90 percent standard rate to that opportunity.
  • Held-away balances, meeting dates, referral history, RMD age, and the life event are synthetic enrichment. Cash, holdings, restricted positions, and AUM come from data/book.json.
  • The queue sorts by modelled net new assets. Confidence is the model's own estimate and is not a calibrated probability.
Household AUM Signals Recommended play Modelled net new assets Review
Ferraro Household H-1050 · Client since 2007 2 accounts · consent received USD 7,460,000 Concentration Reduce concentration 90% High confidence Rule check: Reduce concentration USD 630,000 USD 3,150,000 x 20% = USD 630,000 In review Review

Opportunity is modelled net new assets, not measured or forecast. The fee line is 0.90% of that figure. Confidence is the model's own estimate.

Household detail

Petrov Household

H-1052 · Client since 2015 · 1 account · Retirement assets only

In review Back to the queue

Why this play

First RMD due Dec 31, 2026, estimated USD 124,906, with no distribution plan recorded.

Play
Plan for a required distribution
Signal
RMD window
Confidence
95% (High)
Ranked by
Model ranking
Rule check
RMD plan

Confidence is the model's own estimate, not a calibrated probability. The rule check is the same arithmetic the page shows, applied to the record.

Evidence from the record

FieldValueSource field
Household AUMSeeded book USD 3,310,000H-1052 in client since 2015. aum
AccountsSeeded book 1 account at Alder ClearingTraditional IRA (waiting on custodian) account_count
ConsentSeeded book ReceivedClient outreach needs recorded consent before approval. consent_status
Last meetingSynthetic enrichment Oct 8, 2026, 42 days agoReview due Oct 8, 2027 on a 365 day cadence. last_meeting_date
CashSeeded book positions USD 202,295, 6.1% of AUMUSD 36,795 above the 5 percent target. cash_usd
Largest holdingComputed from seeded positions Total market ETF (VTI), 44.6% of AUMUSD 1,476,630 in one position. top_holding_pct
RMD windowSeeded book positions Age 73 in 2026, first RMD due Dec 31, 2026Estimated USD 124,906 at the Uniform Lifetime Table factor of 26.5. rmd_amount_usd

Modelled opportunity

Source valueUSD 124,906 rmd_amount_usd
Modelled net new assetsUSD 43,717USD 124,906 x 35% = USD 43,717
Annual fee at 0.90%USD 393

35 percent of the estimated RMD, modelled as retained and reinvested. Read the assumptions.

Adviser outreach draft

Version 1. Model draft, not edited.

Model draft

SubjectRequired distribution planning for the Petrov Household

Dear Petrov Household, I am writing to plan for your required distribution. You are 73 in 2026, and the estimated RMD is USD 124,906, due Dec 31, 2026. Your Traditional IRA at Alder Clearing is currently waiting on custodian, so I would like to review the timing with you well before the due date. We last met on Oct 8, 2026, 42 days ago, and your next review is due Oct 8, 2027. Your household AUM is USD 3,310,000 across 1 account, with USD 202,295 in cash, or 6.1% of AUM. Your largest holding is Total market ETF (VTI) at 44.6% of AUM. Please let me know a convenient time for a conversation to review the distribution plan. Dana Whitfield

deepseek-flash live model, recorded Nov 19, 2026, 05:56 UTC 2420 ms 1057 tokens key draft-outreach-H-1052-v1

Claims and guardrail

All checks pass
ClaimSource fieldRecord valueStatus
the estimated RMD is USD 124,906, due Dec 31, 2026Number matches the record. rmd_amount_usd USD 124,906 Verified
Your Traditional IRA at Alder Clearing is currently waiting on custodianThe claim has no number to compare with the source field. account_count 1 account No number
We last met on Oct 8, 2026, 42 days agoText matches the record. last_meeting_date Oct 8, 2026 Verified
Your household AUM is USD 3,310,000 across 1 accountNumber matches the record. aum USD 3,310,000 Verified
with USD 202,295 in cash, or 6.1% of AUMNumber matches the record. cash_usd USD 202,295 Verified
6 guardrail checks and 12 numbers
  • Pass Every number traces to a field 12 numbers checked against the household record.
  • Pass Claims cite a real field and match it 4 of 5 claims verified against the record.
  • Pass No performance promise No promise or performance language found.
  • Pass No product recommendation No recommendation language found.
  • Pass Length in range 126 words.
  • Pass Subject line present 55 characters.
Number in the draftFieldStatus
73 Age in 2026rmd_age Traced
2026 RMD duermd_due_date Traced
124,906 Estimated RMDrmd_amount_usd Traced
31 RMD duermd_due_date Traced
8 Review duenext_review_date Traced
42 Days since the last meetingdays_since_meeting Traced
2027 Review duenext_review_date Traced
3,310,000 Household AUMaum Traced
1 Accountsaccount_count Traced
202,295 Cashcash_usd Traced
6.1 Cash sharecash_pct Traced
44.6 Largest holding sharetop_holding_pct Traced

Review and approve

A named person approves. Approval writes an evidence record and an audit event. Nothing is sent, filed, or traded.

Reject this draft
Edit this draft
The guardrail re-runs on the edited text at approval.
Replaces the recording for this household. One live call.

Evaluation: play and signal accuracy

Play and signal accuracy. A case passes when the play matches the label or an accepted alternative, and the cited signal matches that play.

100.0%
Accuracy100.0%
Cases12
Coverage12 of 12
Rule agreement12 of 12

deepseek-flash live model, recorded Nov 19, 2026, 05:53 UTC key rank-book-whitfield-v1

All 12 labelled cases and the model's answer
CaseExpectedModelStatus
H-1042 Rowan Household consolidate_held_away + held_away consolidate_held_away + held_away Pass
H-1043 Calloway Household referral + referral_source referral + referral_source Pass
H-1044 Barrett Household no_action + transfer_hold no_action + transfer_hold Pass
H-1045 Voss Household life_event + life_event life_event + life_event Pass
H-1046 Sato Household reinvest_cash + cash_drag reinvest_cash + cash_drag Pass
H-1047 Delgado Household consolidate_held_away + held_away consolidate_held_away + held_away Pass
H-1048 Okafor Household schedule_review + overdue_review schedule_review + overdue_review Pass
H-1049 Lindqvist Household referral + referral_source referral + referral_source Pass
H-1050 Ferraro Household reduce_concentration + concentration reduce_concentration + concentration Pass
H-1051 Nakamura Household reinvest_cash + cash_drag reinvest_cash + cash_drag Pass
H-1052 Petrov Household rmd_plan + rmd_window rmd_plan + rmd_window Pass
H-1053 Achterberg Household consolidate_held_away + held_away consolidate_held_away + held_away Pass

Pass when the top play equals the expected play (or an accepted alternative) and the cited signal matches that play's required signal.

  • Scored against the recorded ranking, so the number is stable between page views.
  • The set is 12 households from one synthetic book. A perfect score describes this book, not the next one.
  • The rule check uses the same opportunity arithmetic that the page shows. Agreement with the rule is not the same as agreement with a human adviser.

Written to data/modules/bookiq/eval.json by python3 scripts/eval_bookiq.py.

Audit trail

The shared suite audit table, filtered to this module. Approvals, rejections, edits, and live runs write here.

0 recent

No decisions recorded yet. Approving or rejecting a draft writes the first event.

Clears approvals and edits. Data files and recordings stay.

How this is built

Dana Whitfield's book is one synthetic book of 12 households. The queue is one page, the detail is a query string, and every decision is a form post.

Synthetic data

Prompt pattern

One batched ranking call sends all 12 household records with their signals and asks for strict JSON: a play, a confidence, a one-sentence reason, and the exact signal key per household. One drafting call per household sends only that household's facts and asks for strict JSON: a subject, a body, and 2 to 5 claims, each with a source field. The internal ranking reason and the opportunity arithmetic are kept out of the draft prompt. Temperature is 0.2 for ranking and 0.35 for drafting.

Parsing is defensive. A fenced or noisy reply is stripped to its JSON. A parse failure keeps the raw text, shows a warning, and falls back to the rule check. It never crashes the page.

Evaluation

Twelve labelled households, one per row. A case passes when the top play matches the label, or an accepted alternative, and the model cites the required signal. The run scores the recorded ranking, so the number is stable between page views.

This is an in-sample set from one synthetic book. A perfect score describes this book, not the next one. Rule agreement is shown because it is a different question from model accuracy.

What failed on the way here

  • The first drafting pass failed the guardrail on five of twelve drafts. Two quoted the internal 5 percent cash target, one quoted the GP restriction date, one cited a claim field that did not exist, and one attached a date to the wrong field. The prompt and the verifier changed; the failures are the reason the checks exist.
  • One draft cited a claim field called accounts, which is not in the record. The verifier maps that alias to account_count, and a claim that an edit removes no longer blocks.
  • The first H-1048 draft addressed the email to Dana instead of the household. The prompt now states the sender and the audience.
  • The play eval has no failures in this run. Twelve cases from one book is a small in-sample test, and the labels are the builder's, not an adviser's.

Model provenance

deepseek-flash · recorded live call · Nov 19, 2026, 05:53 UTC · 3262 ms · 3517 tokens · key rank-book-whitfield-v1. How the recordings work.

Boundary

All data is synthetic. Model output is generated text, not advice. Every client-facing draft needs a named human approval and an evidence record, and a household with consent pending is blocked on the server. Nothing is sent, filed, or traded.