In Analyst Evaluation projects, analysts map manager responses to a structured report template, creating a curated set of question-and-answer pairs aligned to specific evaluation criteria. AI Autofill From Mapped Responses builds directly on this foundation. Instead of drafting IC memo and Analyst Evaluation (AE) responses manually, users can now use AI to generate first-draft responses from those already-mapped Q&As, directly within the autofill workflow.
This feature is designed to reduce manual drafting effort, improve consistency across evaluations, and give teams a stronger starting point for review without introducing content from outside the mapped context.
Who This Is For
This feature is available to requestor users and analysts working within Analyst Evaluation projects who have already mapped manager responses to a template.
Prerequisites
To use AI Autofill From Mapped Responses, the following must be in place:
- An Analyst Evaluation project must exist and be in progress
- Manager responses must have been mapped to the relevant report template sections
- DV Assist must be enabled on your DiligenceVault account
If mapped responses are not yet in place, the AI mode for this feature will not have source content to generate from. Refer to the articles on Creating an Analyst Evaluation Project and Mapping Responses to a Report Template before proceeding.
How to Use AI Autofill From Mapped Responses
- Navigate to the relevant Analyst Evaluation project from your DiligenceVault dashboard.
- In the Analyst Evaluation Tab, click on the “Autofill” button and select “Responses”
- Inside the autofill modal, select the AI Mode option. From the available modes, choose Mapped Responses as the content source. This instructs the system to generate the response using only the Q&As that have been mapped within the project.
Note : Please note that currently only one content source can be selected i.e either Mapped Responses or Documents
- Initiate the autofill. The AI will process the mapped Q&As and generate a first-draft response for the selected field. The Progress of the autofill will be displayed on the progress bar and a notification message will be displayed on the right of your screen once autofill is completed.
- Review the generated response and its sources
Once generated, each response will display:
- A confidence score, indicating how well the mapped content supports the generated response
- The AI reasoning, explaining how the answer was constructed from those sources
- The mapped Q&As that were used as source material
To review source detail, click into any mapped Q&A listed in the output. A side panel will display the full context for each contributing source.
Review the draft response alongside the source information. Edit the content directly (by clicking on the text box) if needed before saving it to the project.
Note: Editing this content will remove the source attribution, as it is no longer strictly AI-generated.
Understanding Source Attribution and Confidence Scores
Every AI-generated response is accompanied by a transparent breakdown of how it was produced. This is designed to support analyst review, not replace it.
-
Confidence score (High/Limited): A relative indicator of how well the mapped content aligns with the question being answered. A lower score signals that the mapped content may only partially address the topic, and closer review is warranted before accepting the draft
-
AI reasoning: A plain-language explanation of how the AI interpreted and synthesized the sources to produce the output
-
Mapped Q&As used: The specific question-and-answer pairs drawn from the mapped content that informed the response
These details are always visible alongside the generated response and are not hidden behind additional steps.
Autofill History and Audit Trail
To see the autofill history, Click on the “Autofill” button and select “View Auto-Filled History”
Then click on “Show Detailed Settings Button”
All responses generated through this feature are saved with full metadata. The autofill history for a project records:
- The source type used (Mapped Responses)
- The contributing projects from which the mapped Q&As were drawn
This audit trail supports internal review processes and provides a clear record of how each draft was produced, which is particularly relevant for IC-level workflows where traceability matters.
After completing an autofill session, the AI Autofill Summary provides a consolidated view of:
- The content source used (Mapped Responses)
- A list of all projects that contributed to the mapped Q&As for the session
Additional Information :
- Output quality depends on mapping quality. The AI generates responses based on the structured content that has already been mapped. If mapped responses are sparse, incomplete, or cover topics only tangentially related to the question, the generated draft will reflect those limitations. The confidence score helps surface this.
- AI-generated responses are first drafts. All outputs should be reviewed by an analyst before being used in an IC memo or AE. The feature is designed to accelerate drafting, not remove the review step.
- Prompt customization is not yet available. The ability to add custom prompt instructions or use a prompt library for generation is planned for a future release. Multi-source autofill (combining mapped responses with other document sources) will also be available in a later phase.
- The side panel shows all contributing sources. If a response draws from Q&As across multiple mapped projects, each source is listed and can be expanded for full context.
Example Use Case
An analyst is working on an IC memo for a manager under evaluation. The team has already run an Analyst Evaluation project and mapped the manager's DDQ responses to the relevant template sections, covering areas like investment philosophy, risk management, and operational infrastructure.
Rather than drafting the IC memo sections from scratch, the analyst opens the autofill modal, selects the Mapped Responses AI Mode, and generates first-draft responses for each section. The AI draws from the pre-mapped Q&As, produces structured drafts with source attribution, and flags a lower confidence score on the risk management section, where the mapped content is limited.
The analyst reviews each draft, edits the risk management response with additional context from their own notes, and accepts the remaining sections. The autofill history records the session with source and project details, giving the team a clear record of how the memo draft was assembled.