What we're building.

This summer, Flashlight 3D has been building three seemingly different systems: a whole-genome analysis pipeline, a medical-record consolidation platform, and Chippy, our internal AI agent. Building them side by side has revealed that they share the same basic problem: there is too much information to use effectively in its original form.

A whole-genome VCF can contain millions of variants. A medical history can span years of PDFs, lab reports, handwritten notes, and records from different health systems. Inside a company, decisions become scattered across meetings, documents, emails, and conversations. Our approach across all three has increasingly followed the same pattern:

Raw information → structured data → relevant information → useful output

Most of the processing in our systems is handled deterministically. We use defined pipelines to extract, organize, filter, and validate information before an LLM becomes involved.

For Medical Records, that means processing records from different sources and formats — including scanned and handwritten documents — and consolidating them into a structured longitudinal report. Built using AWS infrastructure, the pipeline is approaching prototype completion while the team continues validating its output and developing the UI. Sathvik Guntha is leading the project, joined by Angel Mencia and Andrew Pham.

For Genomics, the challenge is different in scale but similar in structure. A VCF begins with millions of variants that must be annotated, filtered, and evaluated against available scientific evidence before they become useful to a person. Peter Wang is currently leading the validation phase, with particular attention being given to individual variants and the evidence supporting their interpretation.

Eventually, this work will become part of the Medical Records experience: a dedicated genomics section where a user can provide their VCF and access the resulting analysis alongside their broader health history. We encountered the same information problem inside Flashlight. We built Chippy so our team could ask questions across company knowledge — finding an idea buried in old meeting notes, recovering the context behind a decision, or navigating a growing collection of internal information. Angel Mencia led much of that work. Chippy reinforced an important lesson: giving an AI more information does not automatically make it more useful. Finding and structuring the right information first matters just as much as the model interpreting it. That lesson now influences how we think about our health-data products.

Our goal is to create an interface where a person's longitudinal medical history and genomic information can be organized in one place, with reports that can be reviewed and shared with qualified healthcare professionals. The individual pipelines are different. The architecture underneath them is becoming increasingly similar:

Organize the information first. Surface what matters. Then use AI to help people understand it.

Alongside the product development, Nirel Indurkar has been building Flashlight's website, branding, and public presence, while founder Jonathan Price continues to lead the team as the Summer 2026 program approaches its conclusion.

We're still building, validating, and learning, and we'll continue sharing that process as the products develop.

It sits on our meeting transcripts, our documents, and our decisions. It tracks what we're working on, what we've already figured out, and what's supposed to happen next. When someone needs to know why we filtered a variant class the way we did in July, or what we decided about a data-handling question three meetings ago, they ask Chippy instead of scrolling through hundreds of notes.

For a company this size, that's already worth it. Institutional memory doesn't usually survive a startup's first year: decisions get made, contexts get lost, and six months later nobody can reconstruct the reasoning behind something everyone is now building on.

The focus of our energy is not technical anymore. It is on ensuring that Chippy is offering assistance that is uniquely valuable.

Right now, it's a company brain. It could be a research assistant, an onboarding system, a project manager that actually knows the project. Each of those is a different aspect of the product, and we'd rather find out which one is useful by living with it than by guessing on a whiteboard. Intern Angel Mencia has been working diligently to develop the AI agent at a technical level. He is joined by intern Nirel Indurkar, leading the AI Alignment process to ensure that all of Chippy's policies and instructions are valid and data is protected. Angel performs the complex work of thoughtfully implementing these policies into the Chippy system. Intern Sathvik Guntha has been working on the skills of Chippy, making sure that Chippy knows how to do the specific jobs we actually ask of it.

There's also a longer thread here: Chippy is a system that takes a large pile of unstructured information about an entity and makes it answerable, with sources attached. That's the same problem as a person's medical records. It's the same problem as a genome. We're working on solving it.

A person's medical history is rarely in one place. It accumulates across primary care offices, specialists, hospitals, imaging centers, and labs, each maintaining its own record in its own system, none of which reliably talks to the others. The result is that the patient is the only one with a complete picture, and they hold it in memory rather than in a file.

Our intern Sathvik Guntha leads this project, joined by intern Andrew Pham. They have been methodologically tracking how data travels from input to the final product. Medical records were never designed to be read by anything other than a human being with the time to read them.

Our team is ensuring that all results are verifiably accurate during this stage of product development.

It's filtered, annotated, and cross-referenced against ClinVar, ClinGen, OMIM, Orphanet, and the ACMG actionable gene list. Sathvik Guntha led the initial sprint and developed the pipeline integrating these various trusted databases.

Assisted by Peter Wang, Nirel Indurkar, and Max Arola, this phase took a few weeks. Proving it's right will take longer, and it should.

A whole genome carries millions of variants. Almost all of them are noise, and the entire value of a report like this is the small number that aren't. So this month, Peter Wang and Dru Johnson are in validation, running known samples through the pipeline and checking the output against expected results, variant by variant.

“I started Flashlight 3D to pull together my passions and experience: data science, mentoring young developers, education and workforce development, health and life science, saving lives.” —Jonathan Price (Founder & CEO)

They'll help prototype the Genomic Sequencing Pipeline, an AI-assisted genomic information tool currently in development. Pictured from left to right: (bottom row) Peter Wang, Nirel Indurkar, Dru Johnson; (top row) Sathvik Guntha, Max Arola, Angel Mencia, Jonathan Price.

Beginning July 20, the cohort will contribute across genomic data processing, sequence annotation, artificial intelligence, application development, user experience, and responsible product design.

The internship program gives participants hands-on experience developing early-stage medical-informatics technology while contributing to product evaluation, documentation, privacy, safety, and communication.