Visa Support Letter Automation Platform
AI-powered platform that auto-generates and manages US investor visa support letters for immigration law firms
Service Type
Tech Stack
Key Features
Development Period
4–6 weeks
The Problem with the Old Workflow
The existing process for drafting E-2 visa support letters at immigration law offices.
Inefficiencies and risks accumulated at every step.
Open tab files
Paste into ChatGPT
Switch to Claude
Manual case search
Edit in separate tool
No version control
Open tab files
Manually search 10–20 files
Paste into ChatGPT
Low output quality, hallucinations
Switch to Claude
Manually rewrite prompts each time
Manual case search
Dig through 100+ company files
Edit in separate tool
No inline editing
No version control
Cannot track change history
100+
Companies managed
10-20
Support letters per company
3-5h
Time per letter
30+
Files per person
A Record of Iterations
Three key approaches taken before reaching the final solution.
Write E-2 visa support letter for Korean restaurant investor...
Dear USCIS Officer, I am writing to support the E-2 treaty investor visa application...
ChatGPT alone
Failed to reflect the nuances of legal documents. Frequent hallucinations. Insufficient E-2 visa domain knowledge.
Takeaway
Domain-specific prompts and references to actual approved cases are essential
30min+
Search time
Manual
Prompt repetition
Improved
Quality gains
Claude + manual prompt iteration
Quality improved, but relevant cases still had to be searched manually every time. Prompts were rewritten from scratch each session.
Takeaway
Automatic similar-case retrieval (RAG) emerged as the critical challenge
Single LLM pipeline attempt
Feeding raw OCR text directly into the LLM wasted tokens and polluted the context window. Costs spiked.
Takeaway
Evolved into a multi-LLM architecture with a Gemini summarisation layer
Because company information changes frequently, basing a new letter on a letter approved two years ago is less effective than using the most recently approved letter in the same category. What was needed was not simple RAG but a hybrid search combining category filtering and recency ranking.
Workflow Transformation
Detailed Comparison
A 1-to-1 mapping showing how each pain point in the old process was resolved
Manually searching tab files → pasting into ChatGPT / Claude
4-step wizard: select visa type → bulk upload → OCR verification → auto-generation
Manual case search (100+ companies, 10–20 letters each)
pgvector RAG: category filter + cosine similarity + recency ranking for automatic matching
Editing in a separate tool, no inline editing
Inline editor + sidebar AI suggestion cards (one-click accept / reject)
No version control, no change history
Version history + diff view + PDF / Word download
Waiting for a colleague to review quality
AI review: grammar, legal terminology, and content enhancement suggestions with boolean apply / reject
Separate manual creation of interview question sheets
Auto-generation of expected questions and model answers based on letter content
Manual entry of DS-160 information (hand-extracted from documents)
Automatic DS-160 field mapping from OCR-extracted data
4-Step Wizard
A step-by-step interface intuitive enough for non-developers. Sessions can be abandoned and resumed at any time.
Select Visa Type
Choose the visa type and sub-category: E-2 employee (new hire / transfer), E-2 investor, L-1, etc. The prompt and search scope are configured automatically based on the selected category.
Bulk Document Upload
Upload up to 7 document types at once via drag-and-drop. Upstage OCR automatically extracts text from PDF and DOC files.
Drag & Drop
Per-File OCR Verification
Review and correct the extracted text for each file. Gemini summarises key information, reducing token usage by 20–30%.
Letter Generation + Editor
Claude generates a support letter draft with the Top 3 similar cases automatically injected. Edit inline alongside AI suggestions.
Multi-LLM Pipeline
Combining each LLM's strengths to reduce cost while maximising quality.
Upstage
OCR Extraction
Gemini
OCR Summarisation
Claude
Letter Generation
OpenAI
Embedding + Suggestions
Upstage — OCR Extraction
Specialised in recognising PDF/DOC documents such as passports and income statements. High accuracy for extracting structured data from visa application documents.
Gemini — OCR Summarisation
Cost-efficiently compresses lengthy OCR text. Reduces Claude input tokens by 30%+ while preserving key information.
Claude — Letter Generation
Highest quality for legal document drafting. Enforces 8 domain-specific writing rules via system prompt.
OpenAI — Embedding + Suggestions
Cost-efficient vector generation with text-embedding-3-small. Also used for AI suggestions and interview question generation.
Results & Impact
Letter drafting time
80%Case search time
99%Manual edits
80%Version control
∞4 LLMs
Multi-LLM pipeline
80%
Drafting time reduction
RAG
Automatic similar-case retrieval
0→∞
Version control system