Submit from anywhere; structure on ingest. Accept PDF/DOCX from any vendor and extract the response into the common schema so it is rankable. Native authoring is offered as the better path, never required.
Why. This is the side being charged. Charging them and forcing a tool migration is two asks where only one is affordable. Vendors who author natively emit cleaner structure and get better outcomes, which pulls adoption without mandating it.
Symmetry this creates. Both sides now submit documents and both get extracted, which settles the RFP-shape question by implication: extraction on both ends, human confirmation on both ends. The confirmation step is load-bearing, not polish — see the extraction-confirmation ticket.
What this costs. Extraction quality varies, so the moat is a gradient rather than a wall.
## Resolution
**Submit from anywhere; structure on ingest.** Accept PDF/DOCX from any vendor and extract the response into the common schema so it is rankable. Native authoring is offered as the better path, never required.
**Why.** This is the side being charged. Charging them *and* forcing a tool migration is two asks where only one is affordable. Vendors who author natively emit cleaner structure and get better outcomes, which pulls adoption without mandating it.
**Symmetry this creates.** Both sides now submit documents and both get extracted, which settles the RFP-shape question by implication: extraction on both ends, human confirmation on both ends. The confirmation step is load-bearing, not polish — see the extraction-confirmation ticket.
**What this costs.** Extraction quality varies, so the moat is a gradient rather than a wall.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Question
The bid intake contract. Determines whether structure is mandated, extracted, or absent.
Parent: #1
Resolution
Submit from anywhere; structure on ingest. Accept PDF/DOCX from any vendor and extract the response into the common schema so it is rankable. Native authoring is offered as the better path, never required.
Why. This is the side being charged. Charging them and forcing a tool migration is two asks where only one is affordable. Vendors who author natively emit cleaner structure and get better outcomes, which pulls adoption without mandating it.
Symmetry this creates. Both sides now submit documents and both get extracted, which settles the RFP-shape question by implication: extraction on both ends, human confirmation on both ends. The confirmation step is load-bearing, not polish — see the extraction-confirmation ticket.
What this costs. Extraction quality varies, so the moat is a gradient rather than a wall.