Just Now Possible

What do you do when off-the-shelf moderation scores aren't good enough—and the alternative is paying human contractors to spend their days reviewing traumatizing content at scale?

In this episode of Just Now Possible, Teresa Torres talks with Nikki Marinsek (Data Scientist), Brian McCaffrey (Software Engineer), and Dan Means (Machine Learning Engineer) from Musubi, an AI-native trust and safety toolkit for content platforms. Musubi builds custom-trained ML models and LLM-powered moderation tools that adapt to each platform's unique policies—from dating apps to social networks to AI inference endpoints.

They walk through the full journey: training the first prototype on tabular data, discovering their AI was sometimes catching things human moderators missed, and building a policy optimizer that uses agentic flows to help teams iterate on their moderation policies without needing a data scientist in the room.

You'll hear how they balance latency, accuracy, and cost for clients handling hundreds of millions of actions per month, why pushing eval tools directly to customers is their core product strategy, and what's next as they build flexible agentic orchestration for non-technical trust and safety teams.

What does it take to build an AI customer support agent that actually knows when it can't help — and says so?

In this episode of Just Now Possible, Teresa Torres talks with Jamie Hall (Co-founder & CTO), Xharmagne Carandang (Product Engineer), and Rona Wang (Product Engineer) of Lorikeet, a startup building AI customer support concierge agents for businesses in regulated industries. Lorikeet's vision: an agent that responds like the best customer support you've ever had — one that knows you, gets things fixed, and hands off gracefully when it's out of its depth.

The team spent months exploring the wrong ideas — reflection tools, information dashboards — before a healthcare startup pulled them toward the real problem: just help us clear the inbox. Their earliest prototype was a command-line script delivering results via CSV. Today, Lorikeet runs two agents: a Concierge that handles customer tickets end-to-end, and a Coach that helps customers configure, test, and continuously improve it.

You'll hear how they built customer-configurable guardrails (and why a cannabis company's support tickets broke their first approach), designed a "resolution in the loop" pattern for human-AI collaboration, and are now flipping the configuration workflow so customers define what good looks like before they ever write a standard operating procedure.

Only 10% of the plastic we manufacture gets recycled. We've been trying to solve this for a hundred years using the same mechanical and chemical tools that created the problem. What if biology—specifically, engineered enzymes—is the missing piece?

In this episode of Just Now Possible, Teresa Torres talks with Arzu Sandıkçı (co-founder and CEO) and Mert Topcu (co-founder) of Rhea's Factory, a startup using engineered enzymes and AI to achieve what mechanical recycling can't: breaking plastic all the way back to its original molecular building blocks.

Arzu brings a background in molecular biology and enzyme engineering. Mert brings 20 years in tech, including a decade at Google as a product manager. Together, they've built an AI platform that uses protein language models, multi-step agentic pipelines, and proprietary wet lab data to design novel enzymes that deconstruct plastic polymers into their original monomers—selectively, at low temperatures, and at industrial scale.

You'll hear how they evolved from a human-orchestrated pipeline to an agentic AI scientist, why they sometimes *want* the model to hallucinate, and what it means to explore an enzyme design space that makes everything nature has ever evolved look like a tiny dot.

What does it take to build an AI that can take a food order over WhatsApp — correctly, every time, fast enough that customers can't tell it's not a person? That's the core challenge Santi Marchiori and Juan Haedo set out to solve at AITropos, a company building AI employees for the hospitality industry.

In this episode of Just Now Possible, Teresa Torres talks with Santi Marchiori (CEO) and Juan Haedo (CTO) of AITropos about how they built an AI order-taking agent that handles the full flow — menu recommendations, modifiers, delivery zones, payment links, and status updates — entirely inside WhatsApp. They went through three product iterations to get there: first a hardware device for waiters, then a waiter-facing app, and finally a customer-facing conversational agent powered by a tools-based architecture designed for speed and reliability.

You'll hear how they solved the core technical challenge of translating non-deterministic human conversation into structured POS-compatible order data, why they chose tools over MCP for agent architecture, how they pre-inject product context to cut latency before the agent ever makes a tool call, and why they test with thousands of agent-simulated customer conversations overnight before deploying to any real venue.

How do you turn a rambling stream of consciousness into a clean task list — while the person is still talking? That's the core challenge Doist solved with Ramble, a voice-to-task feature inside Todoist that uses live audio AI to capture tasks in real time, no transcription step required.

In this episode of Just Now Possible, Teresa Torres talks with Ernesto Garcia (Front-end Product Engineer), Thomas Jost (Backend Software Engineer), and Hugo Fauquenoi (Product Manager) from Doist about how they built Ramble — Todoist's first pure AI feature. What started as a two-to-three month AI exploration phase became one of the most technically deliberate features they've shipped: a Gemini-powered pipeline that makes tool calls while the user is still speaking, surfacing tasks on screen in real time without any text output from the model.

You'll hear how they designed around the "brain dump" behavior they found in user research, why they chose direct context injection over RAG for project and label matching, the surprising complexity of date handling in a live audio pipeline, and how they built a multi-language eval system using real employee recordings across 35 countries. It's a detailed look at the discipline of keeping AI features simple, constrained, and genuinely useful.