gabspereira/talk-to-data-case-study
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: simplify anonymized examples

Browse Source 
Use clean generic names instead of repeated redaction placeholders.\n\nCo-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@gabriel.pereira
2026-09-11 11:53:37 -03:00
parent 5c01a80f1a
commit 52d3e870d2
2 changed files with 24 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
cortex_governance_config.yaml
View File

@@ -22,20 +22,20 @@ cortex_policies:
# Access control: Who can query this semantic model # Access control: Who can query this semantic model
access_control: access_control:
default_role: "[REDACTED: SNOWFLAKE_ROLE]" default_role: "quotation_analytics_user"
authorized_teams: authorized_teams:
- name: "sales_team" - name: "sales_team"
snowflake_role: "[REDACTED: SALES_ROLE]" snowflake_role: "quotation_sales_user"
tables: ["sv_quotation", "sv_chatbot_quotation"] tables: ["sv_quotation", "sv_chatbot_quotation"]
max_rows_returned: 100000 max_rows_returned: 100000
- name: "operations_team" - name: "operations_team"
snowflake_role: "[REDACTED: OPS_ROLE]" snowflake_role: "quotation_operations_user"
tables: ["sv_quotation", "sv_chatbot_quotation"] tables: ["sv_quotation", "sv_chatbot_quotation"]
max_rows_returned: 500000 max_rows_returned: 500000
- name: "cortex_agent" - name: "cortex_agent"
snowflake_role: "[REDACTED: CORTEX_AGENT_ROLE]" snowflake_role: "quotation_cortex_agent"
tables: ["sv_chatbot_quotation"] tables: ["sv_chatbot_quotation"]
max_rows_returned: 1000 max_rows_returned: 1000
allowed_functions: ["semantic_search", "similarity_score"] allowed_functions: ["semantic_search", "similarity_score"]
@@ -59,7 +59,7 @@ cortex_policies:
description: "Mask actual customer names in chatbot responses" description: "Mask actual customer names in chatbot responses"
pattern: "customer_name|cliente_nome" pattern: "customer_name|cliente_nome"
action: "mask_value" action: "mask_value"
replacement: "[REDACTED: Customer Information]" replacement: "[Customer information protected]"
exception: "Sales team in authorized_teams can see unmasked values" exception: "Sales team in authorized_teams can see unmasked values"
- rule: "pii_scrubbing" - rule: "pii_scrubbing"
@@ -97,7 +97,7 @@ cortex_policies:
# Cost controls: Prevent runaway LLM usage # Cost controls: Prevent runaway LLM usage
cost_controls: cost_controls:
monthly_budget_usd: "[REDACTED: BUDGET]" monthly_budget_usd: "configured in the deployment environment"
alert_threshold_pct: 80 alert_threshold_pct: 80
per_query_max_tokens: 2000 per_query_max_tokens: 2000
max_concurrent_queries: 10 max_concurrent_queries: 10
@@ -121,9 +121,9 @@ semantic_model_lineage:
description: "How quotation data flows through transformations" description: "How quotation data flows through transformations"
stages: stages:
1_source: 1_source:
system: "[REDACTED: SAP_SYSTEM]" system: "enterprise_erp_source"
frequency: "Daily batch 05:00 UTC" frequency: "Daily batch 05:00 UTC"
tables: ["[REDACTED: SOURCE_QUOTE_TABLE]", "[REDACTED: SOURCE_DISCOUNT_TABLE]"] tables: ["source_quotes", "source_discount_conditions"]
2_staging: 2_staging:
schema: "STAGING" schema: "STAGING"
@@ -142,8 +142,8 @@ semantic_model_lineage:
5_cortex_consumption: 5_cortex_consumption:
interface_1: "Snowflake Native App (BI)" interface_1: "Snowflake Native App (BI)"
interface_2: "[REDACTED: SIEMENS_WORKSPACE]" interface_2: "internal_chatbot_workspace"
llm_model: "[REDACTED: LLM_VERSION]" llm_model: "managed_cortex_model"
prompt_template: | prompt_template: |
You are a sales support assistant. Answer quote questions using only You are a sales support assistant. Answer quote questions using only
the data provided. If discount exceeds policy, flag for human review. the data provided. If discount exceeds policy, flag for human review.

30
marts_quotes.sql
View File

@@ -9,17 +9,17 @@
with source_quotes as ( with source_quotes as (
select select
[REDACTED: quote_id column], quote_id,
[REDACTED: line_item column], line_item,
[REDACTED: customer_id column], customer_id,
[REDACTED: material_id column], material_id,
[REDACTED: quantity column], quantity,
[REDACTED: net_value column], net_value,
[REDACTED: quote_date column], quote_date,
[REDACTED: sales_person_id column], sales_person_id,
[REDACTED: source_timestamp column] source_timestamp
from [REDACTED: SOURCE_SCHEMA].[REDACTED: QUOTE_TABLE] from source_quotes
where [REDACTED: date_partition] >= dateadd(day, -1, current_date()) where quote_date >= dateadd(day, -1, current_date())
), ),
enrich_product_portfolio as ( enrich_product_portfolio as (
@@ -34,9 +34,9 @@ enrich_product_portfolio as (
sq.sales_person_id, sq.sales_person_id,
/* Product portfolio classification */ /* Product portfolio classification */
case case
when sq.material_id like '[REDACTED: pattern 1]%' then 'data-integration' when sq.material_id like 'DI-%' then 'data-integration'
when sq.material_id like '[REDACTED: pattern 2]%' then 'automation' when sq.material_id like 'AU-%' then 'automation'
when sq.material_id like '[REDACTED: pattern 3]%' then 'connectivity' when sq.material_id like 'CO-%' then 'connectivity'
else 'other' else 'other'
end as portfolio_code, end as portfolio_code,
pm.portfolio_name, pm.portfolio_name,
@@ -109,5 +109,3 @@ select
sales_person_id, sales_person_id,
current_timestamp() as dbt_loaded_at current_timestamp() as dbt_loaded_at
from governance_flags from governance_flags
-- ponytail: materialized as table for chatbot + BI queries (not incremental yet; append-only refresh if needed later)