Document Intake Assistant
Financial Advisory · Document Intelligence / Intake Automation
Documents read into the record and multi-step forms pre-filled, with access kept separate
An impact-investment advisory firm reviews fund managers through long onboarding and due-diligence questionnaires. Datics replaced its legacy portal with a new platform whose AI assistant reads submitted decks, notes and documents, pre-fills the multi-step forms, produces an initial score and keeps every field linked to its source.
- Status
- In production, ongoing
- Engagement
- Discovery from December 2024; build since July 2025
Document Intelligence / Intake Automation
Pre-fill & Score
Where the assistant reads submissions and fills and scores the questionnaire.
- AI pre-fill from documents
- Questionnaires and scoring
- Portfolios and landscapes
- Layered access
Role-based access across super admins, standard admins, investors and sub-client portfolios.
The starting point
The firm ran onboarding and due diligence through a legacy portal and spreadsheets. Analysts collected data from fund managers by hand and filled first-impression and evaluation matrices themselves.
What had to change
Onboarding was manual, due diligence across financial, ESG and impact criteria was fragmented, and analysts spent their time collecting data instead of judging it.
What couldn't break
Super admins, standard admins, investors and sub-client portfolios share one platform, so automation could not expose manager-only data, and the legacy portal's data had to come across intact.
Why this was hard
Extraction had to feed validated, multi-step questionnaires with scoring rules, not a free-text summary, inside a platform with layered permissions and data migrated from the old system.
What Datics changed
Datics ran a five-month discovery, then built the platform: organization onboarding (including CSV import), an AI assistant that extracts from decks, notes and transcripts to pre-fill the due-diligence questionnaire and first-impression and evaluation matrices, scoring, fund comparison landscapes, investor and sub-client portfolios, KPI dashboards and task management.
Delivered in two-week sprints after discovery, starting with authentication, role-based access and migration of the legacy database, then the questionnaires, scoring and AI pre-fill.
AI pre-fill from documents
Decks, notes and meeting transcripts read into the questionnaire.
Questionnaires and scoring
First-impression and evaluation matrices with validation and scoring rules.
Portfolios and landscapes
Investor and sub-client portfolios and fund comparison views.
Layered access
Four user types, each limited to its own data.
How it works
Connects to: Document, deck and transcript ingestion; migrated legacy portal data.
- 1
Onboard
Where organizations and funds are added, by form or CSV.
- 2
Pre-fill & Score
Where the assistant reads submissions and fills and scores the questionnaire.
- 3
Review & Compare
Where analysts validate, compare funds and manage portfolios.
Runs within: Role-based access across super admins, standard admins, investors and sub-client portfolios.
Engagement at a glance
Analysts review pre-filled, validated questionnaires instead of retyping submissions, with every field traceable to the document it came from.
- Discovery
- Five months before build
- Delivery
- Two-week sprints since July 2025
- Team
- PM, BA and four engineers
Under the hood
- Datics role
- Discovery, business analysis, product management and full-stack AI engineering.
- Integrations
- Document, deck and transcript ingestion; migrated legacy portal data.
- Deployment
- Cloud-hosted web platform.
- Production boundary
- Role-based access across super admins, standard admins, investors and sub-client portfolios.
Technology
What this unlocked
The same extraction and review pattern now powers Intakely, our admissions and credentialing document module.
Related work
Learning-agency directory
EdTech · Directory / Marketplace
A vetted, subscription directory that helps education buyers find and compare learning agencies
A members-only directory of vetted education agencies with search, filters, shortlists, moderated comments and Stripe subscriptions, built end to end in six milestones.
Leadership-development practice app
EdTech · Learning App / Mobile & Desktop
A leadership-development practice app taken from the web to iOS, Android and desktop
A daily leadership practice built on seven inner archetypes, taken from a web app to native iOS, Android, Windows, macOS and Linux apps from one codebase.
Voice Roleplay Trainer
Insurance Sales Training · Skills Practice / Voice AI
AI voice roleplay that makes skills practice measurable
Agents pick a scenario, a prospect personality and a difficulty, hold a live voice call with an AI prospect, and get a scorecard, transcript and coaching against the firm's own method.
Have a product with the same kind of constraints?
Tell us what already exists and what you want it to do. We will tell you what it takes.