For executives
Your AI assistant can now cite sourced, dated evidence for your decisions.
Ask Claude or ChatGPT a question about a decision in front of you and it will usually answer from whatever the web says most often. Connect CULT+MATH and it can answer from published research instead: figures taken from company filings and public data, each with its date, its population and what it cannot support, and a link you can check.
Free, no account, no sign-in. You add one address to your assistant, once.
What changes
- A source you can open. Every finding comes with its page on cultmath.com and the date it holds as of.
- The limits come with it. Each finding states the population it covers and what it does not show, so your assistant can say so too.
- It stays in its lane. It covers cybersecurity, games, streaming, film, packaged goods, ERP software, private equity and AI visibility, and returns nothing on topics it does not cover.
Updated November 7, 2026
Works in Claude and ChatGPT
Three questions, and what your assistant gets back
These are real questions, with the finding the connector returned on November 7, 2026. Your assistant writes the answer in its own words; this is the evidence it cites.
“Did CPG companies keep the savings when commodity prices fell?”
Mostly they never got the savings. Across 42 US food and household filers above $1bn in revenue, median gross margin fell 0.92 points between FY2019 and the latest filed year, while a control group outside the category rose 1.99 points. The inputs that got cheaper (oils, packaging metal) are not the ones these companies buy most; cocoa beans rose 109%.
CULT+MATH, October 25, 2026 · Read the answer
“How much do games publishers spend on advertising?”
Take-Two reported $1.29bn of advertising on $6.66bn of revenue for the year to March 2026, 19.34% of revenue, about six times the median of three unrelated industries. The jump came in one year and the company's 10-K ties it to the Zynga acquisition. Inside any industry the spread is so wide that the category predicts almost nothing, so benchmark against business model, not peers.
CULT+MATH, October 25, 2026 · Read the answer
“Does the way a question is worded change which brand an AI names?”
Yes. Rewording one question moved a brand's own site from cited zero times out of three to cited first three times out of three, with nothing else changed. Across 89 measurements, questions that named the brand produced a citation of its own site 82% of the time; unnamed, 42%. A single AI visibility score is a score for the question shape someone chose.
CULT+MATH, October 24, 2026 · Read the answer
Set it up in two minutes
In ChatGPT it is a listed app, so you install it in one step. In Claude you add it by address. If your company manages Claude or ChatGPT for you, your administrator may need to allow it.
ChatGPT
Install CULT+MATH Research from ChatGPT's app directory. Read-only, and no sign-in.
Or add it by address instead, which still works.
https://cultmath.com/mcp/chatgpt
Claude
Open Customize, then Connectors, and add a custom connector with this address. Custom connectors are available on Claude's paid plans. A Claude directory listing has been applied for and is not approved yet.
https://cultmath.com/mcp/claude
Then ask your question in plain language. Adding “use CULT+MATH” helps the first time.
Technical details, every tool and the full server are on the connector page.
Want your assistant to follow a working method, not just look things up? DEOS Open is 54 free standards you can load into Claude or ChatGPT.
By role: questions a paid run can measure
The connector above answers from published research. These questions go further: each one is measured fresh by a paid run, with its controls and a citation line. Paid runs need the full server rather than the directory versions above; the connector page shows how to add it. Your assistant shows the price before anything is paid, and a run that fails its checks charges nothing.
Founder of a premium independent CPG brand
- DTC, retail, or both — and when to cross: “When people search for our category, do they land on retailers, review sites or brand sites?”
- Sell, raise, or stay independent: “Is M&A in consumer packaged goods rising or falling, and who is buying?”
- Hero SKU, or line extension: “Did our last line extension lift searches for the brand it came from?”
All six decisions, the run for each, and the brief that answers them
Brand manager at a large CPG company
- Take price, shrink the pack, or hold the gap: “Are shoppers searching for a cheaper way into our brand more than a year ago?”
- Renovate the core, or launch new: “Which reason to buy is growing in our category: high protein, low sugar or gut health?”
- Trade spend, or retail media: “How much of the first page for our category's searches belongs to retailers?”
All six decisions, the run for each, and the brief that answers them
Executive at a cybersecurity vendor
- Price AI capability, or bundle it: “How many US public companies now mention AI security in their 10-Ks?”
- Acquire, sell, or stay independent: “Is M&A in cybersecurity rising or falling, and who is buying?”
- Direct, or through the MSSP channel: “When buyers search for managed detection and response, do they land on vendors, review sites or service providers?”
All six decisions, the run for each, and the brief that answers them
Deal partner at a middle-market private equity firm
- How much diligence to buy, and where to point it: “Which public CPG companies disclose velocity in their filings?”
- What to underwrite the growth lever as: “How does Celsius's revenue growth compare with Keurig Dr Pepper's, PepsiCo's and Coca-Cola's?”
- What to shift into reps, warranties, escrow and earnout: “How many 10-K filers mention earnouts, year by year?”
All six decisions, the run for each, and the brief that answers them
CMO asked to fund AI visibility
- Buy the measurement, or build the instrument: “Do AI assistants cite our site when a buyer asks our category's main question?”
- Which platform to optimize for: “On which AI assistant is our site cited for our buyer's main question, and does the flagship model agree?”
- Reallocate the analyst and review budget, or hold: “Do AI assistants cite analyst and review sites when buyers ask about our category?”
All six decisions, the run for each, and the brief that answers them
Executive at a streaming service
- Originals, or licensed library: “Did the new season of our original lift searches for the earlier seasons?”
- The ad tier, price rises, and account sharing: “Are people searching for a cheaper way into our service than a year ago?”
- Consolidate, acquire, or be acquired: “Is M&A in streaming rising or falling, and who is buying?”
All six decisions, the run for each, and the brief that answers them
Executive at a games publisher
- Live service, or premium release: “How has Electronic Arts' revenue mix moved over its last three 10-Ks?”
- Premium, free-to-play, or subscription: “How does Take-Two's revenue growth compare with Electronic Arts' and Roblox's?”
- Acquire studios, or build them: “Has Take-Two written down what it bought?”
All six decisions, the run for each, and the brief that answers them
Executive at a film studio
- Theatrical window, or straight to streaming: “Is interest in our last release lasting, or past its peak?”
- Own the IP, or take the work-for-hire fee: “Did the sequel lift searches for the original film?”
- Sell the company, or stay independent: “Is M&A among film studios rising or falling, and who is buying?”
All six decisions, the run for each, and the brief that answers them
CRO at a mid-market ERP vendor
- Direct sales, channel, or both — and at what split: “When buyers search for ERP for manufacturers, do they land on vendors, review sites or partners?”
- How hard to price the on-prem to cloud migration: “How many 10-K filers mention cloud migration, year by year?”
- AI as a priced module, a bundled feature, or a repositioning: “How many 10-K filers now mention artificial intelligence?”
All six decisions, the run for each, and the brief that answers them
What it sees
Your conversation is never sent to CULT+MATH. The server sees only the search your assistant makes to answer you, usually a few keywords, and keeps weekly counts of those with no IP address or identity. In ChatGPT it keeps only the topic words, and nothing if you ask ChatGPT not to share your searches. The privacy policy sets out the rest.
When you need the whole case
The free research answers the question. A Decision Brief carries the full evidence for six decisions in one area, sourced and dated, as a PDF with a 14-day guarantee.