AI R&D lab for agents in the real world

We run fast, practical experiments on AI agents in production environments — then open the most promising ones to collaborators, contributors, and future teammates.

Based in Seattle, we've run experiments in healthcare, education, finance, and energy — we're looking for people who want to push agents beyond demo-ware.

Experiment feed

Multi-agent incident responder for Stripe + Slack

Running

Let AI agents triage and respond to Stripe and Slack events in real time, without cron jobs or polling.

Timeline: Feb–Mar 2026

Owners: Frank M., Dev Team

WebhooksClaudeOpenAIAWS

What we've tried

Version 1 handles webhooks reliably; we’re now testing how far we can push agents on call routing and summarization.

How you can help

We’re especially interested in AI engineers and PMs who’ve shipped real-time workflows.

Collaborate on this experiment

AI-assisted clinical note summarization

Designing

Summarize lengthy patient visit notes into structured, provider-ready formats using LLM pipelines.

Timeline: Mar–Apr 2026

Owners: Frank M.

ClaudeFHIRAWS Lambda

What we've tried

Early prompt engineering showed promising results on de-identified notes; now scoping a structured evaluation framework.

How you can help

Looking for clinicians or health-tech engineers familiar with EHR integrations.

Collaborate on this experiment

Energy grid anomaly detection dashboard

Shipped

Build a real-time dashboard that flags anomalous meter readings using lightweight ML models.

Timeline: Nov 2025–Jan 2026

Owners: Dev Team

PythonScikit-learnNext.jsAWS

What we've tried

Shipped v1 with isolation-forest models; accuracy exceeded baseline by 18% on test utility data.

How you can help

This experiment has shipped. Review the write-up or reach out if you want to extend it.

Conversational onboarding flow for intern applicants

Designing

Replace static forms with a guided AI chat that collects applicant info and answers FAQs.

Timeline: Mar–May 2026

Owners: Frank M.

ClaudeNext.jsSendGrid

What we've tried

Prototyped a basic chat widget; exploring how to balance structured data capture with open-ended conversation.

How you can help

We need UX researchers and front-end engineers to co-design the conversation flow.

Collaborate on this experiment

Ways to work with us

Join a live experiment

Pick an experiment tagged “Open to collaborators” and tell us how you'd like to contribute.

See open experiments

Explore roles

If you're looking for something longer-term, check our current roles and send a short note.

View roles

Propose a new experiment

Have a thorny AI agents problem in your product or research? Pitch an experiment and we'll see if it fits our roadmap.

Pitch an experiment
© 2026 Last Myle LLC.