Skip to content
BayetoThornbury Fixed Income (demo)
Demo — fictional firm,
real engine output
Analyze your own system

Optimization Roadmap

The loop: Hypothesis → Implement → Observe → Validate → Score ↑. Every captured win — validated here or measured from a change you already made — locks in savings and unlocks the next.

Spend timeline

$1,000 USDgpt-4-turbo → claude-sonnet≈ €244,361/yr measured05-0106-0606-29

Daily provider spend from your telemetry (uncalibrated cost basis), in USD — the currency your provider bills in. The dashed marker is the measured migration; the guide lines are the average daily spend before and after it.

The annotated run-rate is engine-derived business value in EUR: USD→EUR at 0.92 (fixed reference rate, effective 2026-07-06).

Measured wins — annualized run-rate

Measured · run-ratemedium confidence · 24d

gpt-4-turbo → claude-sonnet · since 2026-06-06

Moved gpt-4-turbo→claude-sonnet ~24d ago; repriced at gpt-4-turbo rates = $22,071.51 vs $6,884.78 actual (USD) → run-rate ≈ €244,361/yr EUR (USD→EUR at 0.92 (fixed reference rate, effective 2026-07-06); medium confidence, 24d). Calibrated to the monthly spend you declared (×1.15).

€244,361
run-rate / yr

Detected from telemetry via a repricing counterfactual (your actual recent tokens priced at the old model vs the new) — a run-rate from a short window, cost-only, quality not measured.

Prediction vs measurement

Before you switched gpt-4-turbo claude-sonnet, Bayeto predicted 0.203/call. You measured 0.221/call.

Compared per call, so the score reflects the estimate and not traffic growth. Annualized for context: €206,904/yr at the pre-switch run-rate vs €244,361/yr measured after — volume moved -2%.

accuracy = 1 − |0.203 0.221| / 0.221 = 91.9% · signed error -0.0179/call (under-predicted)

Denominator: the measured per-call saving; over- and under-prediction count symmetrically (absolute error). Graded population: client-reporting, compliance-assistant, credit-memo, research-copilot · 65,408 post-switch calls · formula pvm-v1.

92%
accurate
Optimization Score75climbing to 77
Cost validated€00 cost-validated wins
Unlockable€47,1048 pursuable moves · direct bill savings / yr
Held€18,8837 held · released if you declare — of €34,566/yr withheld (the executive figure)
start 75now 75target 77
  1. Unlockable

    Finish the gpt-4-turbo → claude-sonnet migration: Meeting Summaries missed the rollout

    unlocks €40,940/yr · open hypothesis

    7577
    score would +2
  2. Unlockable

    Extend prompt caching across Research Copilot

    unlocks €2,606/yr · open hypothesis

    7777
    score would ±0
  3. Unlockable

    Extend prompt caching across Compliance Assistant

    unlocks €1,313/yr · open hypothesis

    7777
    score would ±0
  4. Unlockable

    Route small-context Portfolio Analytics traffic off claude-sonnet to GLM-5.2

    unlocks €567/yr · open hypothesis

    7777
    score would ±0
  5. Unlockable

    Extend prompt caching across Client Reporting

    unlocks €708/yr · open hypothesis

    7777
    score would ±0
  6. Unlockable

    Extend prompt caching across Credit Memo

    unlocks €629/yr · open hypothesis

    7777
    score would ±0
  7. Unlockable

    Route small-context Python Quant traffic off claude-sonnet to GLM-5.2

    unlocks €320/yr · open hypothesis

    7777
    score would ±0
  8. Unlockable

    Pin Portfolio Analytics serving to the caller’s region

    unlocks €21/yr · open hypothesis

    7777
    score would ±0
  9. Target 77 — every step above implemented. New telemetry surfaces new hypotheses; the target rises with them.

Held — not offered as wins

Declaring these surfaces would release €18,883/yr. They carry an unmeasured quality risk on a surface that is declared critical, or is not yet cleared. Declaring a surface low-stakes releases its move; declaring it critical keeps it blocked. Where a move competes with one already leading, the figure shown is what you would gain by swapping — the two are never additive.

Held · Critical surfaceresearch-copilot

Right-size Research Copilot: move low-output claude-sonnet traffic to claude-haiku

You declared this surface critical and the quality impact is unmeasured — Bayeto won't recommend cheapening it.

Declaring this surface would release €6,965/yr — the net gain over the move already leading this application's spend, which it replaces rather than adds to.

€11,930/yr
not counted as unlockable
Held · Review neededcredit-memo

Right-size Credit Memo: move low-output claude-sonnet traffic to claude-haiku

Carries an unmeasured quality risk on a surface whose stakes aren't cleared. Declare it low-stakes to release it.

Declaring this surface would release €6,084/yr — the net gain over the move already leading this application's spend, which it replaces rather than adds to.

€8,255/yr
not counted as unlockable
Held · Critical surfacecompliance-assistant

Right-size Compliance Assistant: move low-output claude-sonnet traffic to claude-haiku

You declared this surface critical and the quality impact is unmeasured — Bayeto won't recommend cheapening it.

Declaring this surface would release €3,426/yr — the net gain over the move already leading this application's spend, which it replaces rather than adds to.

€5,967/yr
not counted as unlockable
Held · Critical surfaceresearch-copilot

Compress the un-cached context Research Copilot re-sends every call

You declared this surface critical and the quality impact is unmeasured — Bayeto won't recommend cheapening it.

Declaring this surface would release €633/yr — the net gain over the move already leading this application's spend, which it replaces rather than adds to.

€5,597/yr
not counted as unlockable
Held · Review neededcredit-memo

Compress the un-cached context Credit Memo re-sends every call

Carries an unmeasured quality risk on a surface whose stakes aren't cleared. Declare it low-stakes to release it.

Declaring this surface would release €1,483/yr — the net gain over the move already leading this application's spend, which it replaces rather than adds to.

€3,655/yr
not counted as unlockable
Held · Critical surfacecompliance-assistant

Compress the un-cached context Compliance Assistant re-sends every call

You declared this surface critical and the quality impact is unmeasured — Bayeto won't recommend cheapening it.

Declaring this surface would release €291/yr — the net gain over the move already leading this application's spend, which it replaces rather than adds to.

€2,832/yr
not counted as unlockable
Held · Critical surfaceclient-reporting

Right-size Client Reporting: move low-output claude-sonnet traffic to claude-haiku

You declared this surface critical and the quality impact is unmeasured — Bayeto won't recommend cheapening it.

Clearing this releases nothing: a larger move already leads this application’s spend, and the two are mutually exclusive.

€1,457/yr
not counted as unlockable

ledger version 22c35e346df765c3 — identical on every page, export, and decision record of this workspace state · how to verify it

© 2026 Bayeto