Document intake
Receive documents and preserve their identity and structure.
- Receives
- A source document and permitted use
- Produces
- Identifiable document material
AI Initiative · early concept
An explanation of the proposed document-to-reviewed-information flow, with source support and human review at its centre.
Historical proposal A present-day explanation of the original concept, not a claim of a currently available product.
The design question
The earlier concept explores using language models to help people find and interpret relevant information in documents. This reconstruction explains the responsibilities such a workflow would need; it does not turn the original proposal into a verified implementation.
The useful distinction is between finding a passage, proposing an interpretation and accepting information for a particular use. Keeping those steps inspectable would let a reader see both the source and the remaining uncertainty.
Keep sources, permission, uncertainty and the person’s ability to correct the result visible throughout.
What each part is responsible for
Receive documents and preserve their identity and structure.
Arrange passages and metadata for subsequent inspection.
Find relevant passages and propose structured information.
Examine disagreements, omissions and source support.
Provide information for an explicitly defined downstream use.
Record corrections; any model training would require a separately designed and evaluated process.
Following one piece of work
Keep source identity and the structure needed to interpret each passage. A date or obligation can mean something different when removed from its surrounding clause; text extraction alone does not resolve that meaning.
Make the requested information clear and search within material appropriate to that request. The concept should allow the system to say that supporting material is missing rather than fill an answer with plausible wording.
Provide a candidate result with the passage that supports it. Any structured extraction should remain connected to the source so the reader can inspect ambiguity, exceptions and missing context.
Let a person compare the result with the original document and record corrections or uncertainty. Several models producing the same answer does not replace this examination, and a correction log is not automatic model training.
Pass the checked information into its intended workflow while retaining its source context and limits. Any later learning or deletion process would need its own design, evaluation and account of derived information.
Illustrative example · not a benchmark result
A reviewer asks where a contract states a renewal date. A proposed result points to the relevant passage so the reviewer can confirm its meaning.
The useful result: Information that can be checked against its source before use.
This is an illustration of the concept, not evidence that the historical product was implemented or that its original guarantees were achieved.
Reading the architecture accurately
Where the design must hold up
| Boundary | Why it matters | How to examine it |
|---|---|---|
| Source-supported interpretation | Several models agreeing does not guarantee that extracted information is correct. | Check the proposed result against the original passage, including exceptions, surrounding context and unresolved ambiguity. |
| Correction versus training | A correction record does not automatically retrain a model. | Identify whether feedback is stored, used to revise a result or included in a separately designed and evaluated learning process. |
| Retention and derived records | Removing a source file does not by itself show that its derived records or learned information have been forgotten. | Follow the intended retention or removal operation across the relevant derived material before making a forgetting claim. |
| Historical availability | The retained writing is a concept proposal, not a current product or accuracy certificate. | Establish implementation, evaluation and operating behaviour separately before making a present-day capability claim. |