For buy-side researchers & quants

Practical LLM workflows for quants.

Ship research faster with compliance-safe patterns for earnings, filings, and backtests. No fluff—just what works.

Educational use only. Not investment or legal advice.

# Extract earnings key metrics
company = "NVDA"
period = "Q1 2024"
extract_earnings_brief({
"company": company,
"period": period,
"focus": ["revenue", "guidance", "commentary"],
"format": "structured_brief"
})
Earnings → Brief
10-K → CSV
Backtest → Tests
Prompt Logs
RAG Eval
Audit Trail
Earnings → Brief
10-K → CSV
Backtest → Tests
Prompt Logs
RAG Eval
Audit Trail

Model evaluation for finance

Measure what matters—latency, accuracy, cost.

Latency
94ms
Accuracy
96%
Cost
$0.07

Claude Code workflows

Earnings digests and 10-K extractions that work.

def extract_earnings(filing):
structured = parse_10k(filing)
return {
'revenue': structured.revenue,
'guidance': structured.guidance
}

Compliance-safe implementation

Logging and audit trails your risk team will approve.

Schema validation
Audit logging
Data lineage
Model cards

Works with your stack

Python, SQL, and notebooks—no breaking changes.

Python
SQL
Jupyter
Pandas

From 10-K to CSV

Before/after table extraction

# Before (PDF Table)
Quarter | Revenue | Growth
Q1 2024 | $60.9B | +262%
# After (Clean CSV)
quarter,revenue_billions,growth_yoy
Q1_2024,60.9,2.62

Trusted by practitioners across the investment lifecycle

Buy-side PM
Risk Management
Systematic Trading
Quant Research
Compliance Officers
Data Engineering

Workflow Gallery

Production-ready templates that save hours of development time

Available

Earnings Call → Analyst Brief

Audio
NLP
Structured Output

Convert earnings calls into structured analyst briefs with key metrics and insights.

Outcome:
Structured brief with KPIs, commentary, and risk factors in minutes.
View workflow
New
Available

10-K Tables → Clean CSV

PDF
Tables
Data Cleaning

Extract and clean financial tables from 10-K filings into usable CSV format.

Outcome:
Clean, validated CSV with proper headers and data types.
View workflow
Coming Soon

Backtest Builder with Tests

Python
Risk
Validation

Generate backtesting code with built-in validation and compliance checks.

Outcome:
Production-ready backtest with risk validation and reporting.
View workflow
Coming Soon

Model Output Compliance Check

Audit
Policy
Validation

Validate model outputs against regulatory requirements and internal policies.

Outcome:
Compliance report with flagged issues and remediation steps.
View workflow
Available

Earnings Transcript Analysis

Sentiment
Topics
Entities

Extract sentiment, key topics, and quantitative mentions from earnings transcripts.

Outcome:
Sentiment scores, topic clusters, and numerical entity extraction.
View workflow
Coming Soon

Regulatory Filing Monitor

Monitoring
Alerts
Categories

Monitor and categorize regulatory filings with automated alert system.

Outcome:
Categorized filings with relevance scores and alert triggers.
View workflow

Release Cadence

Consistent delivery of tools, templates, and insights to keep you ahead

Weekly Workflow Drop

Hands-on workflow with inputs, outputs, and checks

Weekly

Model Eval Notes

Sampling harness + regression snapshots

Bi-weekly

Compliance Template

Logs, model card snippet, SOP redlines

Monthly

Live Build Session

From 10-K to usable tables in minutes

Live

All content delivered directly to your inbox and available in the workflow gallery

Research & Analysis

Quantitative insights, model benchmarks, and systematic approaches to AI-driven finance

Strategy

Earnings Sentiment Signal Extraction

Quantitative framework for extracting sentiment alpha from earnings calls using transformer models and sector-specific lexicons.

12 min read
Dec 2024
Read analysis
Analysis

10-K Financial Table Automation

Production system for parsing SEC filings into structured datasets with 99.2% accuracy using multimodal LLMs.

8 min read
Dec 2024
Read analysis
AI Models

Options Flow Pattern Recognition

AI-powered detection of unusual options activity patterns with sub-second latency for systematic strategies.

15 min read
Nov 2024
Read analysis
Advanced
Coming Soon

Dynamic Risk Factor Monitoring

Real-time portfolio risk assessment using LLM-derived factor models with regulatory compliance frameworks.

10 min read
Jan 2025
Notify when available
Tutorial
Coming Soon

Market Regime Classification Models

Ensemble approach combining traditional econometrics with LLM-based news sentiment for regime detection.

18 min read
Jan 2025
Notify when available
Research
Coming Soon

Credit Risk Signal Processing

Alternative data fusion for corporate credit assessment using earnings transcripts, SEC filings, and news sentiment.

14 min read
Feb 2025
Notify when available

What your risk team cares about

Built-in compliance features that address regulatory requirements and internal policies from day one

Sample SOP Template

# Standard Operating Procedure: LLM Model Usage
## 1. Input Validation
- Verify data sources and lineage
- Check for PII/sensitive information
- Validate against approved schema
## 2. Model Execution
- Log all prompts and responses
- Track token usage and costs
- Monitor for bias indicators
## 3. Output Review
- Human review of critical outputs
- Automated compliance checks
- Version control for model cards
## 4. Audit Trail
- Maintain complete execution logs
- Store model metadata and versions
- Document reviewer actions

Be first to the workflows

Short, useful emails. No spam.