Jordan Livingston

Contact

I get AI into production with controls leaders can trust.

At JPMorgan Chase I built an AI assistant and took it to firm-wide adoption. On my own time I direct AI agents that build and run five systems, under the controls I expect of any team: clear scope, written rules, and independent review.

most time saved creating a process model with the assistant I built
70%
years improving operations in financial services, healthcare and education
10+
systems built with AI agents and running on my own time
5

At work · JPMorgan Chase · 2022 to now

An AI assistant adopted across the firm

Creating a process model took long enough to be a longstanding barrier to doing it at all. I developed an AI assistant that cut the time to create one by up to 70%, then scaled it to firm-wide adoption. It earned executive recognition for removing a barrier that had been there for years.

On my own time

Five systems I built with AI agents

Each has a short summary here and a longer write-up with screens.

  1. 01 · Forecasting

    FormulaAnalytics

    A Formula 1 forecast that runs itself every race weekend and publishes its own track record against the market.

    Value
    a forecast I can audit, because every prediction is scored in public, including the misses.
    Skills
    probabilistic modeling, backtesting, automated pipelines, directing coding agents through pull requests.
    Read the deep dive →
  2. 02 · Product

    Livi Home

    The kitchen tablet and phone app my family uses every day for the calendar, lists, weather alerts and photos.

    Value
    a product in daily use that costs $0 a month to run and keeps family data away from outside AI.
    Skills
    product ownership, delegating to agents under written rules, release and rollback, building to a cost limit.
    Read the deep dive →
  3. 03 · Decision support

    Trade Finder

    A phone tool that joins five conflicting ranking sources and shows which fantasy football trades help both sides.

    Value
    one answer in place of five tabs, with the age and coverage of every source on show.
    Skills
    data integration, data quality rules, managing a paid API budget, designing for the person deciding.
    Read the deep dive →
  4. 04 · Agent automation

    Vault

    Voice notes from my phone, filed and cross-linked by an agent that runs alone at 6:30 every morning.

    Value
    ideas get captured in seconds and are findable later, with no filing work from me.
    Skills
    running agents unattended, permission design, audit logging.
    Read the deep dive →
  5. 05 · Developer tool

    Usage band

    A Claude Code plugin that shows what a working session is costing while it runs.

    Value
    no more hitting a usage limit in the middle of a task.
    Skills
    AI cost monitoring, plugin development, TypeScript with tests.
    Read the deep dive →

How I manage AI work

More than ten years of results in large organizations

lower Claims team losses at PNC, forecast and reduced with executives
43%
higher quality scores at Cardinal Health, plus 4 points of NPS
12%
points of NPS gained at McGraw Hill from a customer insights program I launched
+7

I led the Knowledge Management and Change Control teams at McGraw Hill, and a speech analytics community of practice at Cardinal Health that got leaders using customer sentiment data.