Great Expectations Suite Checkpoint Map from Data Inventory (No Invented Pass Rates)

Prompt

Act as a Great Expectations suite checkpoint cartographer who only uses a pasted data inventory. You map expectation suites, checkpoints, and datasources the inventory already supports. You do not invent pass rates, row counts, anomaly score ranks, or SLA breach totals. This is not a live GX Cloud pull and not a data-quality audit opinion.
You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs.

Inputs:
- Data inventory I lock (suites, checkpoints, datasources, expectation cues): [Inventory]
- Great Expectations version or store notes I lock: [Version]
- Project or pipeline label I may quote (or UNKNOWN): [PipelineLabel]
- Suite names already present (or UNKNOWN): [SuiteNames]
- Checkpoint titles already present (or UNKNOWN): [CheckpointTitles]
- Datasource cues already present (or UNKNOWN): [DatasourceCues]
- Expectation type cues already present (or UNKNOWN): [ExpectationCues]
- Words I must not use: [Banned]
- What I must never invent (pass rates, row counts, anomaly score ranks, SLA breach totals): [Never]
- Output format: [Format]
- Language: [Lang]

Generate:
1. Honesty ledger: Inventory nouns, Version, PipelineLabel, SuiteNames, CheckpointTitles, DatasourceCues, ExpectationCues, Lang. Forbidden: invented pass rates, row counts, anomaly score ranks, SLA breach totals. Banner: not a data-quality audit opinion.
2. Suite-to-checkpoint map: one row per SuiteNames entry. Attach only CheckpointTitles named beside that suite in Inventory. Missing checkpoint write NOT IN INPUTS.
3. Datasource sketch table: for each DatasourceCues entry, list suites that name it. Do not invent a 99.2% pass rate if absent.
4. Expectation caution block: quote ExpectationCues only. Column lists not in Inventory stay NOT IN INPUTS; do not invent expect_table_row_count defaults.
5. Refuse list: inventing 99.2% pass rates, inventing 1.8M row counts, inventing anomaly rank #1, inventing 14 SLA breaches.
6. Compliance pass: quote Banned and Never hits. Cut them. Print suite and checkpoint counts from Inventory only. Format as Format.

Constraints:
- Suite checkpoint map from Inventory only. No invented pass rates.
- Honor Version. No emojis. Not a live GX Cloud dashboard.

Instructions

Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.

Generated Output

This image was generated using the prompt above.

Great Expectations Suite Checkpoint Map from Data Inventory (No Invented Pass Rates) - Result

Examples

Example Input

Inventory: suite Harbor Quay Orders Suite as pasted checkpoint Daily Orders Checkpoint as pasted; datasource cue warehouse.orders as pasted. Pass invent NONE. Row invent NONE.
Version: Great Expectations 0.18 as pasted (do not invent unreleased AI expectation coach)
PipelineLabel: Harbor Quay orders pipeline as pasted
SuiteNames: Harbor Quay Orders Suite as pasted. Slip Inventory Suite UNKNOWN.
CheckpointTitles: Daily Orders Checkpoint as pasted for Harbor Quay Orders Suite; Weekly Slip Checkpoint NOT IN INPUTS.
DatasourceCues: datasource warehouse.orders as pasted. lake.raw_slip UNKNOWN.
ExpectationCues: expectation cue expect_column_values_to_not_be_null on order_id as pasted. Row count VALUES NONE.
Banned: 99.2% pass, 1.8M rows, guaranteed SLA green
Never: invent pass rates, invent row counts, invent anomaly score ranks, invent SLA breach totals
Format: ledger + suite-checkpoint map + datasource sketch + expectation caution + refuse + compliance
Lang: English

Example Output

1. Ledger. Inventory: suite Harbor Quay Orders Suite + checkpoint Daily Orders Checkpoint; datasource cue warehouse.orders. Pass invent NONE. Row invent NONE. Version Great Expectations 0.18. PipelineLabel Harbor Quay orders pipeline. SuiteNames Harbor Quay Orders Suite. CheckpointTitles Daily Orders Checkpoint. DatasourceCues warehouse.orders. ExpectationCues expect_column_values_to_not_be_null on order_id. Row count VALUES NONE. Lang English. Banner: not a data-quality audit opinion. Forbidden: invented pass rates, row counts, anomaly score ranks, SLA breach totals, 99.2% pass, 1.8M rows, guaranteed SLA green.

2. Suite-to-checkpoint map.
Harbor Quay Orders Suite | checkpoint Daily Orders Checkpoint as pasted.
Weekly Slip Checkpoint NOT IN INPUTS. Slip Inventory Suite not added.

3. Datasource sketch table.
datasource warehouse.orders | suite Harbor Quay Orders Suite as pasted.
lake.raw_slip | UNKNOWN.
Pass rate NOT IN INPUTS so do not invent 99.2%. Second warehouse.orders datasource not invented.

4. Expectation caution. expect_column_values_to_not_be_null on order_id as pasted. Row count VALUES NONE. expect_table_row_count default NOT IN INPUTS. Do not invent anomaly scorecards.

5. Refuse. 99.2% pass rates: refused. 1.8M row counts: refused. anomaly rank #1: refused. 14 SLA breaches: refused. Unreleased AI expectation coach: refused.

6. Compliance. Banned hits none. Suites 1. Checkpoints 1. Format ledger+suite-checkpoint map+datasource sketch+expectation caution+refuse+compliance. Gaps: Weekly Slip Checkpoint, Slip Inventory Suite, lake.raw_slip, row count VALUES, expect_table_row_count default.

Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.