Headshot of Baxter Harrington

Hi,

My name is Baxter Harrington and I am studying Mechanical Engineering and Human Computer Interaction at WashU as part of the class of 2028. I'm especially interested in how AI is moving into our physical world. 

Here's my recent work.

This page has three projects — Project 01: LeRobot SO-101 Robotic Arm, Project 02: Konica Minolta Internship, and Project 03: University Rover Challenge (just starting) — followed by a Contact card with email, LinkedIn and GitHub, and a Resume card linking to his resume (PDF).

Project 01: LeRobot SO-101 Robotic Arm

Project Phase 1: LeRobot Open Source Policy Training

Task: Pick up a 1.5in cube and place it in an open top box. A given policy has a successful episode if it grasps the block and places it into the box on the first try. Regrips were not possible in testing, because I removed the block immediately after a failed attempt.

I trained 2 Action Chunking Transformer (ACT) policies, each off of 50 episodes of demonstration using LeRobot Hugging Face toolset.

Policy 1 has a success rate of 32% over 50 trials. It experiences significant issues with depth perception due to the camera mount location. This issue was observed through the common failure mode of the arm grasping directly behind the block.

Policy 2 (V3) uses a new camera mount that provides a better overhead view of the workspace. This new view both minimizes the need for depth perception and also puts more of the workspace into frame, allowing for a larger array of actions. The success rate of this policy is 68% over 40 trials.

Next Steps:

Training a PPO policy (Stable-Baselines3) on a custom Gymnasium environment wrapping a MuJoCo simulation of the SO-101. Redesigning the SO-101 workspace for new sim-to-real transfer processes.


Project 02: Konica Minolta Internship - Experience Design with Agentforce

Naming key for this project: “Step 01–03” are the three phases of the design process. “Business Unit 1, 2, 3” (also written BU 1, BU 2, BU 3) are three anonymized Konica Minolta business units; their real names are not given. “Jobs 1–4” are the four jobs shared by all three business units. “A1–A4” are the IDs of the four proposed Salesforce Agentforce agents, one per shared job. “Figure 2.1” and “Figure 2.2” are the first and second figures of Project 02.

  1. Step 01

    Discovery: I conducted discovery interviews following the Jobs-to-be-Done framework

  2. Step 02

    Prototyping: I used this knowledge of workflows and painpoints to develop agent concepts, built cheaply in Claude Design

  3. Step 03

    Validation: I went back to the same interview participants for feedback on the prototypes

Discovery

I conducted four 1 hour discovery interviews with individuals across three business units. The interviews held a conversational format using the Jobs-to-be-Done framework to understand current workflows and pain points. The goal for this project was to design around how our sales reps actually work, not how we assumed they would use the new Agentforce platform.

Figure 2.1 Jobs identified through interviews : a three-circle Venn diagram of the jobs each business unit does, and which jobs they share.

Figure 2.1 contents, region by region:

  • Business Unit 1 only: Call quota; Agreement recon; Renewal timing.
  • Business Unit 2 only: Onboarding; Coaching; SLA tracking; Templated emails.
  • Business Unit 3 only: Prospecting; Lead routing; Version currency; Partner quoting; Scoping.
  • Shared by Business Units 1 and 2 (not 3): Billing relay; Lease expiry.
  • Shared by Business Units 1 and 3 (not 2): Forecasting; Upsell ID.
  • Shared by Business Units 2 and 3 (not 1): CSM coordination; Adoption.
  • Shared by all three business units (center): Job 1, Account prep; Job 2, Worklist construction; Job 3, Cross-functional troubleshooting; Job 4, Document synthesis.

Full design story for Project 02 (Konica Minolta internship). On screen this part is collapsed behind the “Full design story” toggle; its text is included here in full.

Designing & prototyping

The first step of the design was to gather and analyze the data collected through interviews. This yielded an extensive list of jobs and their scope across the three business units. Organizing these jobs into a Venn-Diagram yielded Figure 2.1, shown above.

To maximize the value proposition, I focused on creating solutions for the jobs shared across all three business units: account prep, worklist construction, cross-functional troubleshooting, and document synthesis. I mapped these shared jobs onto Agentforce solutions that could both increase efficiency and in some cases improve output quality.

Figure 2.2: each of the four jobs shared by all three business units (Jobs 1–4), with its current time cost, mapped to the proposed Agentforce agent (A1–A4) that addresses it.
  • Job 1. Account prep
    Today: 45–90 min per meeting, assembled from 3+ systems
    is addressed by agent
    A1 · Account Intelligence
    One brief, three role-customized views
  • Job 2. Worklist construction
    Today: 1–2 hrs every Monday morning, one report at a time
    is addressed by agent
    A2 · Proactive Worklist
    Ranked, cross-checked, pushed not pulled
  • Job 3. Cross-functional troubleshooting
    Today: 15–50 min per billing issue, with no authority to fix it
    is addressed by agent
    A3 · Workflow Orchestration
    Triage, route, guard, escalate
  • Job 4. Document synthesis
    Today: 5–15 decks a week, system data retyped by hand
    is addressed by agent
    A4 · Artifact Synthesis
    Drafts only, behind a QA gate

A1: in focus (agent A1, Account Intelligence)

After identifying the agents to be designed, I honed in on agent A1: Account Intelligence. This agent will provide an account summary right on the salesforce account landing page, pulling the specific metrics that the end users voiced in discovery in order to give them the view that will provide them with the most value. The discovery interviews laid bare that an agent of this nature would save each sales rep upwards of 20 minutes before each account contact point, saving up to 4 hours of prep time per person every week.

In addition to these efficiency gains, this agent will evaluate every account against the same criteria, removing the variability that occurs when analysis quality depends on a sales rep's time, attention, or experience.

As part of creating an optimized account brief view, additional agents will pull service history from a customer's devices, and data from other systems outside of salesforce.

A1 subagents (the five sub-agents that make up agent A1, Account Intelligence)

  • BU 1 Account Brief (account brief view for Business Unit 1)
  • BU 2 Account Brief (account brief view for Business Unit 2)
  • BU 3 Account Brief (account brief view for Business Unit 3)
  • Service History Q&A
  • Cross-System Answers

UX rules identified

Push, don’t pull: individuals made it clear that the most impactful and useful tools are the ones that get automatically pushed to their dashboards.

One agent, three views: each of the BUs requested different views into the same core data points, so a single agent with individualized sub-agents should be utilized, as they will all be grounded in the same data

Prototyping

Using Claude Design I was able to create elaborate prototypes in HTML for the end users to get an accurate understanding of what the user experience will be of the shipped agent. This efficient prototyping process allowed me to create the individualized view for each of the business units.

Validation sessions

Returned to the same interview participants with the HTML prototypes for 30 minute feedback sessions on design utility. These sessions resulted in further design criteria for the next iteration of prototypes.

Project 03: University Rover Challenge - Science Team Lead

Challenge Rulebook

Current State:

Onboarding new members. Check back soon for updates.