← @bgSponge

Startup Fellowship 002: Balto Energy | DevCon 6

Summary

Frank Chen of Balto Energy uses Palantir Foundry to build physics-based digital twins and contractor knowledge graphs to scale home electrification and increase EBITDA from 3.5x to over 8x.

  1. Ontologies drive compounding business value.

    Balto uses Foundry to capture decision traces and tacit knowledge from contractors, turning workflows into versioned system improvements.

    Every workflow ships two artifacts, the result, and the version improvement to the system

  2. Digital twins enable energy underwriting.

    Balto models 250 parameters through thousands of simulations per home to match equipment, weather, and usage patterns.

    we're in thousands of simulations per home to goal seek with building physics in mind

  3. AI automation accelerates operational speed.

    Marketing campaigns that previously took 11 weeks now launch in less than a day using highly customized context.

    a generic marketing campaign took 11 weeks to launch. Today, a campaign launches in less than a day

  4. Knowledge graphs prevent talent attrition.

    By capturing contractor judgment and decision traces into an ontology, Balto ensures expertise remains within the company.

    We build loops under santassent knowledge that lives in people's heads so it doesn't walk out the door

  5. Agentic loops resolve modeling errors.

    When a simulation misbehaves, an agent traverses the graph and building science literature to propose a diagnosis for human review.

    an agent walks a graph, pulls from the building science literature and proposes a diagnosis

Read the original ↗Save to your Sponge

Summarized with Sponge. Quotes are the author’s own words.

More from @bg

All readings →