Sounak Bhattacharya

"Expressive voices in seconds" — what does expressive mean here specifically? Emotion range, character accents, speaking style? The difference between a voice that sounds "playful" and one that actually commits to a character is pretty significant.

The competitor data piece is the most interesting part to me. How does Emotix know which competitors are relevant to an idea it's never seen before? Is that user-defined, or does the system infer it? Because getting that mapping wrong would skew the whole validation.

Always-on agent with access to email, calendar, CRM, sequences, AND workstation simultaneously — that's a lot of surface area. When something goes wrong (wrong prospect gets a sequence, meeting booked at the wrong time), how does accountability work? Is there a full audit trail of what the agent decided and why, or do you only find out after the damage is done?

Cryptographic verification of agent actions is the interesting piece here. What exactly is being signed — the prompt, the tool call, the output, all of the above? And when you say 'verify,' is that post-hoc audit trail or can you actually halt an action mid-execution if it fails a policy check?

Curious what "asking questions" looks like in practice. If a prospect asks something outside the scripted demo flow — like a specific pricing edge case or an integration question — does the AI handle it or gracefully hand off? That's where these tools usually break down.

The secrets-by-name-without-seeing-values architecture is the most interesting part here. How does that work exactly when Claude is orchestrating a deployment — does the MCP server do a local substitution at runtime, or are the values never in the process environment that the LLM context can reach? The threat model matters a lot depending on the answer.

Curious how the conversational widget works in practice. Is it proactively prompting users mid-session based on behavior triggers, or is it more of a passive "leave feedback here" button? The difference matters a lot for response rates — passive widgets get ignored, triggered ones get gamed.

The prescription lens support is the obvious unlock here — most people who actually need glasses all day have been blocked from smart eyewear because of this. But how does the prescription integration work practically? Do you go through a licensed optician, upload your Rx somewhere, or is Meta partnering with specific lens providers?