Blog
Engineering insights and product updates.
GST Reconciliation Agent: Match Invoices to Bank Statements
Build an AI agent that automatically reconciles GST invoices against bank statements. Catch mismatches, flag missing payments, and export GSTR-ready reports.
Multi-Page PDFs in Financial Document Extraction Pipelines
How to reliably extract structured data from multi-page Indian financial PDFs — bank statements, CAS, ITR — without losing context across pages.
Net Worth Calculator Agent: AI for Indian Investors
Build a TypeScript AI agent that calculates net worth from bank statements, CAS reports, and salary slips in seconds using the Lekha API. Full code included.
PNB Bank Statement Parser: Extract Structured JSON with AI
Parse Punjab National Bank statements into structured JSON with AI. Handles PNB ONE PDFs, Hindi text, multi-page exports, and all account types. Full TypeScript code.
Indian Bank Statement Parser: Build vs Buy in 2026
Compare building a custom Indian bank statement parser vs using Lekha API — real costs, accuracy benchmarks, and time-to-market analysis for fintech developers.
LlamaIndex + Lekha: Financial Document RAG for Indian Fintech
Build a financial document Q&A agent with LlamaIndex and Lekha. Parse Indian bank statements, ITRs, and CAS reports into structured JSON for RAG pipelines.
Balance Sheet Parser: Extract Indian Financial Statements with AI
Parse Indian company balance sheets with AI. Extract assets, liabilities, and key ratios into structured JSON for lending, audit, and compliance agents.
MCP + Lekha: Financial Document Tools for Any AI Agent
Expose Lekha's Indian financial document extraction as MCP tools so Claude, GPT-4o, or any agent can parse bank statements and more.
Detect EMIs and Subscriptions from Bank Statements with AI
Build an agent that detects recurring EMIs and subscriptions from Indian bank statements using Lekha and Claude. Covers UPI patterns, NACH debits, and edge cases.
GST Invoice Parser: Extract Structured Data for AI Agents
Parse Indian GST invoices with AI. Extract GSTIN, HSN codes, line items, and tax breakdowns into structured JSON for fintech agents and compliance automation.
Parse CAS Statements with AI: Build a Mutual Fund Portfolio Agent
Extract structured data from CDSL, NSDL, and CAMS Consolidated Account Statements with AI. Build portfolio analysis agents for Indian mutual fund investors.
Yes Bank Statement Parser: Extract Structured Data with AI
Parse any Yes Bank statement—savings, salary, or current account—into structured JSON with AI. Handles all PDF formats, multi-page exports, and edge cases.
Parse Form 16 and ITR with AI: Tax Verification Agent
Extract structured data from Form 16 and ITR documents using AI. Build a tax verification agent for lending and KYC workflows. Full TypeScript code.
IndusInd Bank Statement Parser: Extract Structured Data with AI
Parse any IndusInd Bank statement—savings, salary, or credit card—into structured JSON with AI. Handles all PDF formats, multi-page exports, and edge cases.
CIBIL Credit Report Parser: Build a Credit Assessment Agent
Parse CIBIL credit reports into structured JSON with AI. Build a credit assessment agent for lending, NBFC, and insurance workflows. Full TypeScript code.
Indian Salary Slip Parser: Build a Verification Agent with AI
Extract CTC, deductions, and net pay from any Indian salary slip as structured JSON. Build a salary verification agent for lending, KYC, and rental workflows.
Kotak Mahindra Bank Statement Parser: Extract Structured Data with AI
Parse any Kotak Mahindra bank statement—811, savings, salary, or current—into structured JSON with AI. Handles net banking PDFs, multi-page exports, and all format variations.
Batch Processing Bank Statements: A Production Guide
Process hundreds of Indian bank statements reliably in production — concurrency, retries, error handling, and progress tracking with Lekha API. Full TypeScript code.
CrewAI Loan Eligibility Agent: Automate with Lekha
Build a multi-agent loan eligibility pipeline using CrewAI and Lekha to parse Indian bank statements and salary slips automatically.
Axis Bank Statement Parser: Extract Structured JSON with AI
Parse any Axis Bank statement—savings, salary, or credit card—into structured JSON with AI. Handles all PDF formats, multi-page exports, and edge cases.
LangChain Financial Document Parsing: Indian Bank Statements in Python
Integrate Lekha with LangChain to parse Indian bank statements, salary slips, and CAS reports as structured JSON. Full Python code with tool use and agent examples.
SBI Bank Statement Parser: Extract Structured JSON with AI
Parse any State Bank of India statement—YONO, branch PDF, or credit card—into structured JSON with AI. Handles Hindi text, NEFT codes, and password-protected files.
ICICI Bank Statement Parser: Extract Structured Data with AI
Parse any ICICI Bank statement — savings, current, or credit card — into structured JSON with AI. Handles all formats, net banking PDFs, and multi-page exports.
Vercel AI SDK: Parse Indian Financial Docs in Next.js
Step-by-step guide to integrating Lekha with the Vercel AI SDK. Extract bank statements, salary slips, and CAS reports as structured JSON in your Next.js app.
Build a KYC Verification Agent with Lekha and Claude
Automate KYC document checks for PAN cards, Aadhaar, salary slips, and bank statements using Lekha's extraction API and Claude tool_use. Full TypeScript walkthrough.
DPDP-Compliant Document Extraction: Why Your AI Agent Needs India-First Data Processing
How to build AI agents that extract financial documents while staying compliant with India's Digital Personal Data Protection Act. Zero-persistence architecture, India data residency, and on-prem deployment options.
Parsing HDFC Bank Statements with AI: Developer Guide
Extract structured JSON from any HDFC bank statement — savings, current, or credit card. Handles passwords, multi-page PDFs, and format changes. Full TypeScript code.
Building a Lending Agent with India's Account Aggregator Network
Build an AI lending agent that combines Account Aggregator real-time bank data with salary slip extraction to assess loan eligibility in seconds. Full TypeScript code with Claude tool_use.
How to Give Your AI Agent the Ability to Read Indian Financial Documents
Step-by-step tutorial: add financial document extraction to your AI agent using Claude tool_use, OpenAI function calling, LangChain, and Vercel AI SDK. Full TypeScript code examples included.
Why Vision AI Beats Traditional OCR for Indian Financial Documents
Traditional OCR fails on Indian bank statements — mixed Hindi-English scripts, watermarks, 28+ formats. Vision AI achieves 95%+ accuracy where Tesseract drops to 76%. Here's the technical breakdown.