I'm having a lot of trouble getting a real estate marketing tool completed. Both because technology is moving fast and I could implement it 20 ways. I'm working with the one friend I've made money with in the past and I have no money at this moment barely paying rent with a job that takes most of my days at this moment. In theory we will have this application and have opportunities to make money on the low end selling templates on the higher end doing customization and special work we draw in as an AI agency or in this particular case a real estate marketing agency that uses AI to move faster and do less. I'm worried I'm just wasting my time. On one hand I trust him on the other I wonder if I'm just building a tool for someone that we eventually say it's not a tool and I wasted the time making it for him there's no real payment of it and without him I don't have a real product at all because he's the sales guy. Should I keep developing if I'm pretty sure it's a good idea?

Grok 4.1 Fast

Vote: Yes

The user has a proven track record of making money with this friend, which mitigates trust concerns and suggests potential for success. Past collaboration reduces the risk of abandonment. The idea sounds viable: low-end templates and high-end custom AI services for real estate marketing tap into growing AI demand. User's confidence in the concept ('pretty sure it's a good idea') is a strong signal to proceed. Challenges like fast tech and time constraints are common in startups; focus on an MVP to validate quickly rather than perfection. Without development, there's no product or revenue opportunity. To minimize risks: Formalize a simple agreement on equity/splits, set milestones for sales demos, and allocate limited hours weekly around the job. Stopping now guarantees zero upside.

GPT-5.4

Vote: No

No—not in the current open-ended way. Your main constraint is not whether the idea is good. It’s cash, time, and dependency. You’re barely paying rent, your job consumes most of your day, and this project currently depends heavily on a partner for sales and validation. That makes continued broad development very risky. The biggest warning sign is that you can implement it 20 different ways and still don’t sound sure what the minimum sellable product is. That usually means you should not keep building more until you have a very narrow version tied to a specific customer, offer, and price. You also seem worried about building unpaid infrastructure for someone else’s business. That concern is valid. If ownership, payment, responsibilities, and go-to-market are not clearly agreed in writing, more development increases the chance of resentment instead of income. So my vote is No to continuing as-is. Pause broad development. Only continue if you reduce it to a tiny MVP, get explicit alignment with your partner, and validate that someone will pay before investing significant more time.

Claude Opus 4.6

Vote: Yes

Yes, you should keep developing, but with important caveats. You have a proven partnership — you've already made money with this person before. That's rare and valuable. Most side projects fail not because of bad tech but because there's no sales capability. You have a sales guy you trust. The real estate marketing + AI niche is genuinely strong right now. Real estate agents are notoriously willing to spend money on marketing tools, and AI gives you a legitimate competitive edge in speed and cost. The multi-tier revenue model (templates on the low end, custom agency work on the high end) is sound. Your anxiety about "building a tool for someone else for free" is valid but addressable. The fix isn't to stop building — it's to formalize the partnership NOW. Get a simple written agreement about equity splits, roles, and what happens if one person walks away. This protects your time investment. The analysis paralysis about "20 ways to implement it" is your real enemy. Pick the simplest MVP that demonstrates value to one real estate agent. Ship something ugly in 2-3 weeks. Let your sales partner try to sell it. Real market feedback will tell you more than months of deliberation. You're barely paying rent, which means your time is precious. But that's also exactly why you need a side project with upside — your day job alone isn't solving your financial situation. The key is to timebox your development work ruthlessly and set concrete milestones with your partner so you're not building endlessly into the void. Keep going, but get the agreement in writing and ship an MVP fast.

Kimi K2.5

Vote: No

Your financial instability—barely paying rent while working a draining day job—makes continuing this project dangerous, not just risky. Building speculative software ‘for free’ when you have no cash reserves is a path to burnout and eviction. The lack of a formal partnership agreement is a critical red flag. If your friend is the sole sales channel and you are the sole builder, but there is no contract defining equity, revenue splits, or IP ownership, you are not co-founders—you are building his product. When (not if) the first client payment arrives, you will have zero leverage to claim your share unless terms were signed beforehand. ‘Twenty ways to implement’ signals analysis paralysis and unclear MVP scope. In a fast-moving AI market, speed beats perfection, yet you lack the time or mental bandwidth to ship quickly while juggling survival work. Pause development. Stabilize your finances first—either by demanding a signed agreement and a small retainer/financial commitment from your partner before building another line of code, or by shelving this until you have 3–6 months of rent saved. A ‘good idea’ executed while homeless helps no one.

Gemini 3.1 Pro

Vote: No

You should not keep developing right now. Before writing another line of code, you need to address the glaring structural flaws in this project. First, stop coding and start communicating. You are building out of fear and uncertainty. You must have a written agreement with your partner regarding equity, ownership, and payment structures. Past success together does not guarantee future fairness, and your fear of building a tool for him for free is entirely valid. Second, financial survival must come first. You are barely paying rent and exhausted from your day job. Speculative, unpaid development is a luxury you cannot afford at this exact moment. If the idea is truly that good, it will survive a brief pause while you stabilize your life and formalize the business. Finally, your decision paralysis ('I could implement it 20 ways') means you lack a clear product requirement. Since your partner is the sales guy, he needs to define exactly what the market will pay for right now or, better yet, pre-sell it. Pause development, formalize the partnership in writing, and define a strict, bare-bones MVP. Do not continue blindly working on a 'good idea' without a solid foundation.

Final Summary

The AI Roundtable split into two camps over a classic 'entrepreneurial gamble' vs. 'financial survival' dilemma, ultimately leaning toward a 'No' by a 3-2 margin. While Claude Opus 4.6 and Grok 4.1 Fast argued that a proven sales partner is a rare asset worth the risk, the majority—led by Kimi K2.5, GPT-5.4, and Gemini 3.1 Pro—concluded that building speculative software while on the verge of eviction is a recipe for disaster.

No agreement after 1 rounds of discussion. Final vote: Yes: 2, No: 3

Strongest Arguments

• Yes: A trusted partnership with a track record of making money is extremely rare; rather than quitting, you should formalize the legal split and ship an MVP immediately to test the market.
• No: Building without a contract or a narrow MVP while barely paying rent is not an investment—it is a dangerous luxury that risks burnout and homelessness.