resonaX

Right now, we validate twin responses in a few ways:

Ground truth comparison: When users upload CRM notes, Gong call transcripts, or win/loss data, we benchmark the twin’s language and objections against what real prospects actually said.

Confidence scoring: If a twin sounds overly confident but doesn’t have enough supporting data (e.g., limited context or sparse history), the system flags it with a lower reliability score rather than pretending it’s certain.

Iterative calibration: Each feedback cycle — whether a message worked or not — helps fine-tune the twin so its “voice” and reasoning evolve over time.

The end goal is that twins shouldn’t pretend to know — they should learn continuously from every interaction and new data point.

Thanks — that’s exactly the problem we’re trying to solve. Traditional personas go stale fast, and most survey data is self-reported, not behavioral.

On hallucinations and bias: We handle it in three ways right now —

Grounding in real data: Each twin is built using structured + unstructured data (LinkedIn profiles, CRM notes, messaging, etc.), so the LLM has contextual grounding rather than free-form guessing.

Feedback calibration: Every time users compare twin feedback with real user insights (e.g., call transcripts or campaign results), that feedback loop fine-tunes how the twin weighs language patterns and priorities.

Cross-model validation: We run prompts through multiple models and look for consensus — if the outputs diverge too much, the system flags it for review rather than showing one “confident” but wrong answer.

It’s still early, but the goal is to make twins that drift with real customer data — not just sit frozen like static personas.

A quick clarification and some context on how the “AI twin” actually works.

- Each twin isn’t just a generic chatbot. - It’s grounded in real behavioural data + psychology frameworks (like MBTI and DISC) that are matched with customer roles and communication patterns.

For example:

If your real customers tend to be data-driven “analyst” types, the twin reasons and responds that way.

If they’re more visionary “driver” types, the twin reacts to emotion and ROI triggers.

So instead of random AI answers, you’re getting responses that mirror how your actual buyers think and decide — built from your CRM, LinkedIn, and conversation data.

I’m particularly curious how others here would:

Combine multiple buyer types into a “composite twin” (like 10 VP Marketing profiles)

Add validation loops that make the twin’s reasoning evolve with more data

Integrate open-source behavioral models rather than proprietary ones

Appreciate all feedback — especially from those who’ve worked on LLM fine-tuning, agent memory, or customer simulation before.

thanks bix6. - Video point is totally taken, it was my first time recording a demo so I guess went a bit longish but will try to shorten. - great idea about defaults like 20M ARR SaaS CMO, SaaS Founder etc. Just that by putting a linkedin profile it becomes hyper-personalised. - if a profile is private, we use publicly available data + behavioral patterns from similar personas in our database. - Right now users compare responses to their actual customer conversations. I'm seeing 65-70% alignment on messaging preferences. But you're right - having human advisors validate the AI responses could be a premium feature.

I would love it if you could create a digital twin by just a linkedin profile of even someone yo know or yours and tell me how accurate you think responses are. Would mean the world to me ;)

Thanks for your feedback tene80i. - yes the accuracy is upto 70% as of now from what little testing we have done. It is able to give these responses based on the personality analysis that resonaX does based on the online behaviour of the person. If the user uploads any conversations with the target/prospect customer like any DMs exchanges, email or just anything the accuracy increases.

- thanks a tonne for your ideas on positioning and the copy, I will tighten it further.

- Quick question - did you get a chance to try creating a twin yourself? I'm curious about your experience with the actual responses and whether they felt accurate/useful from a CRO standpoint.

- Also, when you mention "identifying issues different user types might find with a page" - that's exactly what I'm seeing users do. They'll create twins of different customer segments and ask the same question to see how responses vary. So its like a quick A/B testing hypothesis.