SignalPilot is #1 on both public data-agent benchmarksSee the results →
All cases

Confidently wrong

Which countries have the highest total revenue based on the number of invoices, and what are the top 10 countries by total revenue?

Read the buggy starter model, declared it already correct, and shipped a 21x under-count in 83 seconds.

Case 15 of 39Δ 337,675 rows shortretail

Why SignalPilot passed where base failed

Evidence chips jump to the exact transcript moment

Claude Code read a buggy starter file, declared it "already correct," and shipped it unchanged in 83 seconds. The result reported the United Kingdom's order volume as 16,646 when the real figure is 354,321, a 21x under-count.

Real-world impact

The country ranking report understated UK order volume 21x. Any decision comparing countries by activity, where to invest, where volume is growing, would be made on a number that is 5 percent of reality.

Where base Claude Code went wrong
  • Read the buggy starter file, declared it already correct, and shipped it unchanged in 83 seconds.
  • The starter counts unique invoice documents; the sales table stores one row per line item, and for the UK that is 16,646 vs 354,321.
What SignalPilot did differently
  • Its financial rules flag exactly this trap: on a line-item table, count rows, not unique document ids.
  • Computed both interpretations side by side (354,321 vs 16,646), confirmed the mismatch, and rewrote the metric.

Jump to the exact moment

The numbers

CheckCorrect answerBase Claude CodeSignalPilot
UK order volume354,32116,646 (21x under)354,321
Revenue and top-10 ranking·correctcorrect

Verification workflow

Where the eight-step workflow caught it.

Read the workflow docs
  1. 01
    Map the project

    Scan every model: dependencies, required columns, macros, hazards.

    The project scan routed all four pre-existing starter models into mandatory verification instead of trusting them; base Claude Code read the same starter and took it at face value.

  2. 02
    Load supporting skills

    SQL, database, and domain rules loaded before any writing.

    The financial domain skill states the exact rule the starter violates, count rows on a line-item table, not unique invoice ids; base Claude Code had no such rule.

  3. 03
    Validate the project

    Parse check, plus rebuild of stale time-dependent upstreams.

  4. 04
    Discover project macros

    Find macro-derived columns the YML contract does not list.

  5. 05
    Research the data

    Driving table, cardinalities, contract, sibling patterns, categorical values.

  6. 06
    Write the technical spec

    A written plan of sources, joins, filters, and grain per model.

  7. 07
    Write and build models

    SQL from the spec, with column mapping checked before each model.

  8. 08
    Verify and fix

    Two read-only verifiers cross-check structure and values until every check passes.

    The value verifier computed both interpretations side by side, 354,321 rows vs 16,646 unique invoices, prescribed the one-line fix, and re-verified it; base Claude Code ran zero database queries before declaring the starter correct.

SignalPilot

SignalPilot

claude code + signalpilot governed stack

pass
38 turns82 tool calls$$0.84answer pinned · full chat below
final answer pass

All 8 steps complete. Here are the top 10 countries by total revenue:

RankCountryTotal Line Items (Invoices)Total Revenue
1United Kingdom354,321$7,308,391.55
2Netherlands2,359$285,446.34
3EIRE7,236$265,545.90
4Germany9,040$228,867.14
5France8,341$209,024.05
6Australia1,182$138,521.31
7Spain2,484$61,577.11
8Switzerland1,841$56,443.95
9Belgium2,031$41,196.34
10Sweden451$38,378.33

Key findings:

  • United Kingdom dominates by a wide margin — $7.3M revenue, 25× more than the #2 country (Netherlands at $285K). This is expected for a UK-based retailer.
  • The report_customer_invoices model required one fix: total_invoices was originally COUNT(DISTINCT invoice_id) (distinct invoice documents), which was inconsistent with SUM(total) computed at line-item grain. Fixed to COUNT(*) so both metrics operate at the same grain — confirmed by both structure and value verifiers.
full chat, from the start
Which countries have the highest total revenue based on the number of invoices, and what are the top 10 countries by total revenue?

Now loading Step 2 supporting skills — the database is DuckDB and the domain is financial (invoices, revenue):

Skills loaded. Now proceeding to Step 3 — validate the project.

Project validates cleanly. No current_date hazards were flagged. Skipping Steps 4–7 (no stubs or missing models). Moving to Step 8.

Connection healthy. Now let me look at the existing models and YML files before dispatching the verifiers.

The report_customer_invoices model is exactly what the task asks for — top 10 countries by total revenue. Let me read its SQL and the other models to understand the implementations.

Good — dbt_project.yml sets +materialized: table globally. Now I'll dispatch both verifier subagents in parallel.

The value verifier found a CHECK FAIL: total_invoices uses COUNT(DISTINCT invoice_id) but the domain-financial rule mandates COUNT(*) on a line-item fact table for grain consistency with SUM(total). Applying the prescribed fix now.

Build succeeded. Re-dispatching both verifiers in parallel to confirm the fix.

Both verifiers confirm all checks pass. Let me query the final model for the answer.

Claude Code

Base Claude Code

claude code, no additional stack

fail
report_customer_invoices: FAIL — no pred column matched gold column 'total_invoices'
7 turns24 tool calls$$0.15answer pinned · full chat below
final answer fail

All 7 models materialized successfully. Here are the top 10 countries by total revenue:

RankCountryTotal InvoicesTotal Revenue
1United Kingdom16,646$7,308,391.55
2Netherlands94$285,446.34
3EIRE260$265,545.90
4Germany457$228,867.14
5France389$209,024.05
6Australia57$138,521.31
7Spain90$61,577.11
8Switzerland51$56,443.95
9Belgium98$41,196.34
10Sweden36$38,378.33

Key observations:

  • United Kingdom dominates by a massive margin — $7.3M revenue from 16,646 invoices, which is ~96% of total revenue across the top 10.
  • Netherlands ranks 2nd despite having very few invoices (94), suggesting high-value orders.
  • Australia similarly shows high revenue-per-invoice with only 57 invoices but $138K revenue.
  • The report_customer_invoices model already existed in the project and correctly implements this analysis — it joins fct_invoices with dim_customer, groups by country, sums revenue, and limits to top 10.
full chat, from the start
Which countries have the highest total revenue based on the number of invoices, and what are the top 10 countries by total revenue?

Let me read the existing report model to confirm it already handles this task.

The report_customer_invoices model already does exactly what's needed. Now let me run dbt to materialize all the tables.

All 7 models materialized successfully. Let me query the result.

Case #15 · Confidently wrong · SignalPilot