The roast. The number. The pivot.
An honest answer to whether a three month build should exist, argued by four agents at once, with the cost of winning a single customer put on the table beside it.
Chapters
-
0:00Old friends, and an MBA in sustainability -
3:09The wish: roast the idea, and the business model I do not have -
7:24Local models, and what you actually give up -
14:30Before the app: what happens if you just ask? -
21:32A small furniture company in Hungary, and a report from nothing -
25:18If anybody can ask for it, it is not an advantage -
26:35His own answer: the only moat is speed -
33:17No markdown reports on this show -
34:19Four agents, one for each thing worth arguing about -
38:05Can the build actually hold client data? -
38:47Is anybody searching for this at all? -
44:51A form built in a minute, to see how far a stranger gets -
52:54"I have no clue what question you are asking me" -
55:25A real company, picked off a search, filled in from public records -
56:43What an AI expert is usually selling -
1:02:51The roast comes back: pivot needed -
1:04:33So how would anybody find it? -
1:06:19The code review: a demo, and a key every visitor can read -
1:09:50Which people do you want to work with? -
1:18:21Roasting the roast: you never costed the marketing -
1:29:48The business case, and a market that was never the problem -
1:32:222,500 dollars a customer, and two and a half years to earn it back -
1:33:49The question nobody else would have asked -
1:39:09"The advertising part, I completely missed out" -
1:45:06125 cells written into EFRAG's official template -
1:55:18Sell the help, not the app -
1:56:50What the next session is for
The session
He came on to be argued with. Three months and about seventy thousand lines of prompting had produced Frontier, which takes the Excel sheet a small European company is handed when a bank asks for its sustainability report and turns it into ordinary conversations, one topic at a time, in the company’s own language. The wish was not to finish it. It was to find out whether it should exist.
So the session ran two experiments side by side. Four agents pulled the thing apart, one each on the idea, the code, the easier route and the demand. And in another terminal, the same report got filled in for a real Hungarian manufacturer with two prompts and no application at all, ending with 125 values written straight into the official template by a script it wrote for the job.
The verdict that mattered was not about the software. Asked, on the second attempt and only after being told it had skipped the question, what it costs to find one paying customer, it came back with about 2,500 dollars on German search ads against a subscription that takes two and a half years to earn that back. His own words, at 1:39: “The advertising part, I completely missed out, honestly.” The thing he left with was a different offer, which is to sell the prompting rather than the app.
What did Denes build? What Denes said afterwards
Mate is a great host who makes you feel comfortable from the start. I was genuinely surprised by how focused and engaged he was throughout our session. What really stands out is his rare mix of solid technical and business skills — he understands the tech, but also thinks about real client needs, finding customers and what actually works in the market. Really enjoyed the conversation!
Prompty
