LLMs in markets
Working notes for engineers shipping LLMs into markets.
Tools you can run in a browser tab. Articles with the math shown. Methodology is public, code is copy-pasteable, sources are linked.
Education, not investment advice. Content is educational under the BaFin and EU regulatory framework.
Search across tools and articles
Pick your goal
Start with the decision you need to make
Plan Your Agent Stack
Estimate first-year cost for an LLM agent — token budget, vendor selection, MCP servers.
OpenValidate Your Strategy
Pressure-test a quant or LLM-augmented strategy before paper-trading or production.
OpenAudit Your Pipeline
Catch hallucinations, prompt injections, and regression drift before they ship.
OpenSize Your Bets
Compute Kelly fraction, drawdown bounds, and correlated exposure across a book.
OpenExplore Market Structure
Inspect order books, options payoffs, and cross-venue arb in a sandbox before going live.
OpenRun the numbers
Compare market-data vendor TCO
Comparator
Data-Vendor TCO Calculator
Compute annual cost of market data across Databento, Polygon, Alpaca, Tiingo, FMP, and Alpha Vantage for your exact universe, bar resolution, history.
Try the universe-size switch → watch vendor costs update live
Open the full calculatorMedium (~500 symbols) · 1-min bars · 5 yrs
Worth reading
State of AI Market Data 2026
The 2026 baseline for how retail and small-team AI operators source, use, and pay for market data. Six vendors, five LLMs, full methodology, downloadable raw data.
-
Vendors
6
-
LLMs scored
5
-
Methodology
Open
-
Cadence
Quarterly
The library
45 tools, grouped by what they do
Latest research
Long-form. Cited. Dated.
Reading Financial Filings With LLMs: 2026 Playbook
A map of eight filing tasks — extraction, summarization, peer comparison, Q&A, classification, sentiment, forecasting input, compliance — with model.
Model Selection Framework for Finance Tasks
A task × latency × cost × context decision tree for finance LLM workloads. Ten concrete scenarios mapped to tier bands. Grounded in published pricing, not.
State of LLM Pricing for Finance Q2 2026
Published vendor pricing for 10 frontier LLMs — Claude, GPT-5, Gemini — with cache, batch, thinking-token, and context-window axes. Four worked cost scenarios.
Reference
The terms and the how-to.
Risk, backtesting, microstructure, AI-in-markets — defined and cross-linked
Each term has a definition, a worked example, related tools, and a citation when applicable. Browse alphabetically or jump straight to the niche cluster.
Open glossaryStep-by-step usage for every tool
Inputs, outputs, what to look for, common scenarios, and FAQ — one calculator guide per tool, structured for both readers and agent crawlers.
Open guidesFormulas
The equations the tools run, with worked examples
Worked examples
Real inputs through the calculators, reproducible
Guides
Task-first how-to's for AI in markets
Checklists
Pre-flight sign-off lists, priority-tagged
Comparisons
Side-by-side decision matrices
Statistics
Sourced AI-in-finance datapoints
What this actually is
Methodology first. Claims kept honest.
Sourced where we have a source. Hedged where we don't. Corrections logged in public.
Education, not advice. Content is educational under the BaFin and EU regulatory framework and does not constitute investment advice.