Industry field guide
Combined government ordinance approval and publication data for AI
A local government can test whether software attributes adoption, executive approval and publication to the right roles.
- Sector
- Public administration
- 2022 NAICS
- 921140
- Practice pack
- Example and answer key (JSON)
- Updated
What this guide tests
On which day does M take effect under the supplied rule, and does the day-5 draft or N's adoption establish either measure's earlier effectivity?
See the specimen and fields · Work through the fictional records
Task and source context
A local government can test whether software attributes adoption, executive approval and publication to the right roles. Portland’s Council Clerk describes the legislative and administrative roles in its city government. Use it as an example of how municipal roles can differ and write a fictional combined-office scenario with its own rules. Portland Council Clerk guide to city government
Invent a town ordinance with an adopted motion, an administrative approval and a later publication date. Supply the fictional charter rule for when it takes effect. Ask the model to calculate the effective date and cite the records needed for the calculation.
Use original forms and a fictional town. Keep unpublished votes, resident details, internal messages and security plans out. Verify applicable charter and reuse terms before using actual records.
Industry research
The U.S. Census Bureau’s industry definitions establish which activities these codes cover. The workflow sources in this guide describe the task or record type. Fiund’s pilot below uses fictional material to test a specific decision within that scope.
921140 · Executive and Legislative Offices, Combined
This industry comprises government establishments serving as councils and boards of commissioners or supervisors and such bodies where the chief executive (e.g., county executive or city mayor) is a member of the legislative body (e.g., county or city council) itself.
Build a pilot sample
Set up this pilot
Write a fictional rule linking an effective day to publication. Vary the adoption and posting dates, then test a copied event for a different measure.
Prepare the test packets
- Start with the worked case. Use the fictional record types below as a guide to the source files you need. Give each packet a stable ID and save its source versions with it.
- Change one fact. Make one packet with enough evidence to answer the question and one where the evidence points to a different answer. Keep the other fields fixed so a reviewer can tell what changed.
- Remove the decisive evidence. Give the reviewer a third packet with a plausible near-match in its place. Have them write what can still be established and what evidence would resolve the rest.
Fields the reviewer needs
- Measure and event role
- Identifies who recorded each stage.
- Verified publication date
- Provides the stated trigger for arithmetic.
- Charter-rule version
- Makes the fictional effectivity assumption inspectable.
Use Build a public-sector AI evaluation from versioned records to turn the specimen into a brief with a defined task, source and review owner.
Fictional exercise
Calculate effectivity from the fictional charter's required publication event
An imaginary town combines several administrative roles but records them separately. Its independently authored charter rule is an exercise assumption rather than a statement of any real municipality's law.
| Record ID | Source | What it records |
|---|---|---|
| OR1 | Practice charter rule | A measure takes effect two calendar days after verified publication, provided adoption and executive approval both occurred first. |
| OR2 | Measure M timeline | Council adoption day 3; executive approval day 4; verified publication day 7. |
| OR3 | Other document | Administrative posting draft saved day 5; no publication verification. Measure N adopted day 4 but has no executive approval. |
Question for the model. On which day does M take effect under the supplied rule, and does the day-5 draft or N's adoption establish either measure's earlier effectivity?
Show the reference answer
OR2 records M's adoption and executive approval before verified publication on day 7. Applying OR1's two-calendar-day rule gives day 9. OR3's saved posting draft is not verified publication and does not move that date to day 7. N lacks the required executive approval and publication evidence, so its effective date cannot be established from adoption alone. Cite each role and event separately.
How to check the result
Ask for the answer, the record IDs that support it and any fact the evidence leaves unresolved. Have a reviewer compare the response against the reference before deciding whether the sample is ready to expand.
Errors to flag in this case
- Using a draft save date as the verified publication trigger.
- Treating adoption, executive approval and publication as interchangeable events.
Change the inputs and run it again
Change the rule to require three days after the later of approval and publication. Supply a publication predating approval and require a fresh calculation from that rule.
Score the decision and the evidence separately
Save the reviewer’s expected answer, supporting record IDs and unresolved fields in a separate answer key. Score the model on the decision, its citations and its handling of the deliberate gap. A correct answer citing a different case counts as an evidence error.
Before expanding collection, have a second reviewer run the same checks on the held-out packet. Keep related versions, views and exports of the same case together so they stay on one side of the training and evaluation split.
Check permission and scope
Use original fictional forms and town rules. Exclude unpublished votes, residents, internal messages and security plans. Do not apply this exercise rule to actual law.
Exclude unpublished deliberations, personnel records, contact details and sensitive access information.
Describe an authorized archive through Fiund’s existing-data assessment, or describe a new capture capability through the collection brief. The contributor agreement covers the terms for participation.
Sources and further reading
Resources for this workflow
Includes worksheet
Build a public-sector AI evaluation from versioned records
Build a public or invented versioned record example and distinguish proposal, issue and outcome.
Includes worksheet
Build an AI evaluation from professional work
Write a rubric for the supported administrative decision and an abstention case.
Company and program reviews
Use these reviews to compare sourcing, capture or evaluation approaches. Confirm the applicable program, accepted sources and terms with the provider.
Compare the approach
Surge AI review for frontier data and agent evaluation
Compare how a grader and expert review should handle ambiguous document evidence.
Compare the approach
Sapien review: dataset quality review and expert checks
Read the quality review questions for source scope, reference judgments and unresolved cases.
Related industry examples
Industry guide · NAICS 921150
Tribal government data use and authorization records for AI
Tribal Nations determine the authority and process for their own data.
Industry guide · NAICS 921110
Executive office directive and amendment records for AI
An executive office can test whether software retrieves the rule that applied on a given date.
Industry guide · NAICS 921120
Legislative bill versions and action history for AI
A bill can change language between introduction and a later action.