Skip to content
Judd Gurtman

I check what a number is actually counting before I trust it.

I study Information Analysis at the University of Michigan. This year I've built a full-stack AI fitness app, a research agent that cites every sentence, and the assistant on this site, and I publish what broke and the measured numbers behind every claim.

Or ask Judd Bot about my work →

Studying
Information Analysis, Michigan '27
Building
A fleet of AI agents run by one orchestrator
Last role
Data Analytics Intern, TrueSource
Looking for
Full-time data and AI roles from 2027, open to relocating

Selected work

All work →
Aug to Sept 2026Python · FastAPI · Claude API · installable web app

Coach

A full-stack AI fitness app. You talk to it like a trainer and it acts: an agent logs workouts, meals and weigh-ins through 7 tools and writes each day's session from the weights you actually lifted. Under it: a FastAPI backend, a phone app you can install, and a simulator that runs a fake user through ten days to test every change.

Coach tab: the test user reports a workout and the coach logs it with the log_workout toolWorkout tab: today's session, with bench press set at 165 lb because the last logged session was 160Journey tab: level 4, XP and daily quests computed from the logs

Read the case study → Code ↗

Tools the agent can call
7
Offline tests
37
Scorecard, run 1 → 3 of the last 5 runs
7 → 13 of 13
Cost of a 10-day test run, run 1 → run 16
$2.07 → $1.35
Sept 2026Python · Claude API · web search

Research agent

Ask it a hard question. It splits the question into smaller ones, researches them in parallel, checks every claim against the exact quote it came from, and writes a brief where every sentence cites a source.

Read the case study → Code ↗

Weakly supported claims, saved replay
66% → 54%
Sentences with a citation, tuned run
45 / 46
Invented sources, every saved run
0
Cost per question, first → tuned run
$1.68 → $1.25
Sept 2026Python · MCP · orchestration

Agent fleet

One orchestrator runs my other agents as tools through an MCP server. Anything that spends money has a cap and waits for a person to approve it, and a stuck job gets shut down so it stops costing money.

Read the case study → Code ↗

Agents connected so far
2
Search cap per question
4 × 3
Sept 2026JavaScript · Cloudflare Workers · Claude API

Judd Bot

The assistant on this site. Ask it about my work by voice or text: it answers only from a public list of facts, cites a source for every answer, takes you to any page you ask for, and says it doesn't know rather than guess. Code checks every answer before a visitor sees it.

Try it → Code ↗

Eval questions passed, run of Oct 4
100 / 100
Questions per visitor per minute
6

Experience

More →
Data Analytics Intern, TrueSourceSummer 2026 Audited 29 KPIs across 4 dashboards and documented 7 inconsistencies. The analytics team added disclaimers to the live dashboards. Assistant varsity lacrosse coach, Aspen High SchoolSpring 2026 Also a volunteer youth flag football coach since 2024.
A research agent that cites every sentenceSept 2026 What broke, starting with zero evidence on the first run, and why the fix I planned was aimed at the wrong cause. How the research agent works, and whySept 2026 The six-step pipeline, four layers against made-up answers, and a cost ledger that found where the money went.