QuantData Subscribe
Menu

Setting up your AI agent

Quant Data is built to be used through an AI agent. You ask a question in English; the agent makes the HTTP call, reads the JSON, and reports it back with the caveats attached. This page is the practical walkthrough, whatever agent you use.

The whole integration is one HTTP header. No SDK, no OAuth, no callback URL, no webhook. If your tool can send X-API-Key with a GET request, it is supported. A free key gives both endpoints 10 successful calls per UTC day. No paid plan is offered on the site.

On this page:

Step 0 — Read the free pages first

A good part of this site needs no key, no account and no card, so you can look before deciding whether any of it is worth paying for:

One anonymous first look is available per source per UTC day, followed by a free key delivered by email for 10 successful calls per UTC day across both endpoints. No paid plan is offered on the site.

Step 1 — Get a key

Start free. Submit an email address through the homepage or the API below. There is no login, password or card. A successful 202 response confirms delivery started, but never contains the raw qd_ key; check that inbox for it. Product updates are a separate choice and marketing_opt_in stays false unless the email owner explicitly asks for them. A true value only records a pending request; the recipient must reply SUBSCRIBE to the delivery email before any marketing updates begin. 

curl -s -X POST https://api.quantdata.uk/v1/access/free-key \
  -H "Content-Type: application/json" \
  -d '{"email":"you@example.com","marketing_opt_in":false,"source":"agent-setup"}'

Get free API key

The free key gives 10 successful calls per UTC day, shared across Brooks, Weis, Max Pain and Gamma. Keys bought earlier keep working under the terms shown at purchase.

Your agent can request the free key itself. It can POST an email address you provide and tell you to check that inbox. When the daily free allowance is used up, the API returns the reset time and a sentence for the agent to relay to you.

Step 2 — Put the key where the agent can find it

For anything with a shell, an environment variable. Never paste a key into a SKILL.md, a prompt file, or anything you might commit. 

# ~/.zshrc on macOS, ~/.bashrc on most Linux
export QUANTDATA_API_KEY="qd_your_key_here"

Open a new terminal (or source the file), then confirm it works:

curl -s -H "X-API-Key: $QUANTDATA_API_KEY" \
  https://api.quantdata.uk/v1/brooks/SPY

You should get JSON back with an events array — an empty array is a valid read; it means no event has fired in the window yet. If you get a 401, the key is not reaching the request — see troubleshooting below.

Not sure whether the problem is the key or the network? Call the API with no header at all and print only the status code. A 200 consumes the source's 1 anonymous first-look response for the UTC day; 429 means it has already been used. The response action then points to the free-key request. 

curl -s -o /dev/null -w "%{http_code}\n" \
  https://api.quantdata.uk/v1/brooks/SPY

For an agent with no shell — Claude Desktop, a Custom GPT, an n8n node — use that platform's own secret store instead. The rule is the same: keys belong in a secret store, never in a file you might share.

Step 3 — Install a Skill, or paste the prompt

Two paths. They do the same thing; pick whichever your tool supports.

Claude Code

Copy the skill folders into your skills directory and start a new session.

mkdir -p ~/.claude/skills
cp -R quantdata-daily-bias ~/.claude/skills/
cp -R quantdata-weis-wave  ~/.claude/skills/

Personal skills at ~/.claude/skills/ are available in every project. Put them in .claude/skills/ inside a repository instead if you want them shared with everyone working on it. The key comes from the environment automatically. Verify with: "which Quant Data skills do you have?"

Claude Desktop and the Claude apps

Same SKILL.md files, installed through the app's own skills interface. Because there is no shell, put your key wherever the app keeps connector or integration secrets. If you would rather not manage a Skill at all, paste the system prompt into a Project's custom instructions — it works identically and it is scoped to that Project.

Cursor, Windsurf, Cline, GitHub Copilot

All of these read a rules or instructions file from your repository — the exact filename differs by tool and by version, so check the current docs for yours. Paste the prompt block into it. Keep the key in your shell environment and have the agent read $QUANTDATA_API_KEY rather than writing it into the rules file, which will end up in version control.

ChatGPT and Custom GPTs

Two pieces, and people usually forget the second one.

  1. Paste the prompt block into Instructions. That teaches the model what the endpoints mean and how to report them.
  2. Add an Action by importing https://api.quantdata.uk/openapi.json, then set authentication type to API Key with custom header name X-API-Key. Without the Action the GPT knows about the API but cannot reach it — and a model that cannot reach an API will sometimes produce plausible-looking numbers anyway. That is the failure mode to watch for.

Gemini CLI and other terminal agents

Put the prompt block in whatever context or system-instruction file the tool loads at startup. The key is already in your environment from step 2, and terminal agents can generally shell out to curl, so no further wiring is needed.

n8n, Dify, Coze, CrewAI, AutoGen, LangChain

Two nodes. An HTTP Request node calling https://api.quantdata.uk/v1/brooks/SPY with a header credential named X-API-Key, feeding into an Agent or LLM node whose system message is the prompt block. For framework code — CrewAI backstory, AutoGen system message, LangChain SystemMessage — the prompt block is the string, and the request is an ordinary HTTP call with one header.

Anything else that can send a header

That is the entire requirement. Two dozen lines of Python with no dependencies beyond the standard library will do it. If your platform is not named above, it is almost certainly supported — the API has no client library because it does not need one.

The prompt block

This is the paste-ready canonical version — the same block printed on the Skills page and the API reference, covering both endpoints, the symbol rules and the reporting rules. The homepage carries shorter prompts for specific workflows instead. Replace the key placeholder with wherever your platform keeps secrets.

Step 4 — Ask a question

You never invoke a Skill by name. Ask normally, and the agent matches your question against what it has installed.

"Has NVDA broken out of its range?" "Did the ES=F breakout follow through?" "Is the pullback in ES=F on low volume?" "Any Weis events on QQQ today?" "Where is max pain for SPY this Friday?" "What does the volume structure of AMD show?" "Is it true that 80% of breakouts fail?"

Step 5 — Read the answer critically

This is the step nobody writes down, and it is the one that decides whether any of this is worth having. An AI agent will happily produce a confident, fluent, completely fabricated market reading. Here is how to tell the difference.

A good answer contains

Red flags

When in doubt, ask it to show you the raw JSON, or run the curl from step 2 and compare. Verifying twice in your first week is worth more than any amount of prompt tuning.

The full version of this critical-reading skill is its own page. If you only skim one thing there, make it the checklist at the end.

Troubleshooting

StatusWhat it meansFix
400 window=gap or window=asia (Brooks), or session=asia (Weis), sent for something that is not a 24-hour instrument Drop the parameter, or use a futures (=F) or spot-FX (=X) symbol. Stocks and ETFs trade the US day session only. Weis still needs exchange volume, so use CME currency futures rather than spot FX there.
401 Unrecognised X-API-Key, or an anonymous request that cannot be counted Is the variable visible to the agent's process? Exporting in a shell profile does not affect an app that was already running — restart it. Does the key start with qd_, with no stray quotes or trailing newline? Is the header name exactly X-API-Key, not Authorization or a Bearer token? The body carries retryable: false; do not retry in a loop.
429 FREE_QUOTA_EXHAUSTED for anonymous or free-key access Read access_kind. For anonymous, relay the request_free_api_key action. For evaluation_key, report quota_resets_at and relay message_for_your_human to the person. Do not keep retrying.
402 Subscription lapsed, or the anti-abuse usage cap was reached A billing state, not a transient error — retryable: false, so your agent should stop calling. The response body carries the free pages and a sentence written for your agent to relay to you. It applies only to keys bought earlier; if you hit the anti-abuse cap unexpectedly, something in your setup is probably looping.
403 Key is valid but does not cover that endpoint Only legacy keys see this. The current plan is one tier covering everything; keys bought under the old per-product pricing keep their original price and their original scope. Also retryable: false. Email quantdata@quantdata.uk — existing subscribers are moved across by hand rather than paying twice.
404 The symbol did not resolve Read the message — it names a likely correct ticker. Indices and commodities need an ETF or futures symbol, never a name: S&P 500 is SPY or ES=F, gold is GLD or GC=F. Failed lookups are not billed.
404 insufficient sessions Not enough recent history — usually a very thin instrument, or a long market holiday. Try a more liquid symbol.
200 Weis response with an error field insufficient bars means fewer than 120 bars of history; no volume data means the source returned prices without volume, and wave analysis is impossible without volume. Neither is fixable by retrying.
5xx An upstream market-data source failed Retry once after a pause, then report it. Never let an agent fabricate a reading.

Two problems that are not error codes

  • You asked about gold and got a company. GOLD is a real ticker — a US-listed equity, Gold.com, Inc. The API returns a symbol_note warning about exactly this; make sure your agent is relaying it. For the metal, use GC=F for futures or GLD for futures.
  • Your agent answers without calling anything. Fluent, plausible, entirely invented. Check the response mentions a session date and a bar count. If your agent has an Action or tool that is misconfigured, it may silently fall back to answering from memory rather than reporting the failure.

Next

The three Skills, in detail Reading probabilities honestly Day types Access

Get free API key Browse the free pages

Free daily notes by email

One email per publishing day: what the paid research publishers said, ticker by ticker. Free; unsubscribing deletes the address.

Free. One email per publishing day, the same text as the web version. Submitting the form subscribes this address straight away and sends a welcome note carrying the unsubscribe link, so an address entered by mistake can be removed with one click. Unsubscribing deletes your address.How the address is handled.

Educational analytics and developer tooling. Nothing here is investment advice or a recommendation to buy or sell anything.