Vol. 02 · The Index

Brent Espineda.

AI Learning Engineer & Learning Experience Designer · learning science, supercharged with AI

I design learning experiences, and build the AI systems that let them scale.

Trained as an Educator and School Counselor. Learned to build with AI at Amazon, shipping tools that replaced manual workflows. Now at EdPlus, directing Claude and Codex to build the learning tooling that lets the entire ASU Online Course Catalog scale.

“Learning is the pinnacle of human existence.”

Brent Michael Espineda

Frame the problem before the model

Stakeholder discovery, scope, build, iterate, launch, evaluate, refine. AI infused in every stage. The workflow is the product.

Translate impact into evidence

Benchmarks, workflows, and analytic numbers all tied to the systems that produced them.

Currently

EdPlus at ASU

Learning Experience Designer / Instructional Designer

ID for the MS in Applied Statistics & Data Science. Hand-selected contributor to the Juris Doctor program team and a cross-functional AI taskforce (AI, UX, ID leadership).

Looking for

Learning teams that treat AI as core craft: building course-quality, authoring, and knowledge tooling, not just specifying it. Comfortable being the most technical person in a learning team, or the most learning-science-aware person in a technical one.

What I build for you.

Pick the format your content needs. I work end to end, from your subject-matter experts to a finished course in your LMS.

Custom Courses

  • Full eLearning builds in Rise & Storyline
  • Existing content rebuilt and modernized
  • SCORM / xAPI delivery to your LMS

Branching Scenarios

  • Decision-based, consequence-driven practice
  • Soft-skills, compliance, onboarding
  • Adaptive logic that responds to the learner

Microlearning

  • Short, single-outcome modules
  • Job aids and reinforcement
  • Series built for retention

Course Design

  • Needs analysis and learning objectives
  • Storyboarding and assessment design
  • SME partnership on dense material

AI Simulations *

  • AI-driven branching scenarios
  • Live LLM roleplay for real practice
  • Pass-criteria checks, not click-through

Consulting

  • Learning alignment
  • Accessibility audits (WCAG 2.1 AA)
  • Existing-course review and fixes
  • AI workflow setup for your team

* AI Simulations: the client is fully responsible for covering AI usage costs. Please contact me for more information.

What you get.

Real builds you can click through, not screenshots.

Live · AI Branching Simulation

De-Escalation Training

Your people learn a hard conversation by having one, usually a real one that goes sideways. This gives them the rep first. The learner talks with an AI character who pushes back like a real skeptic, and they pass only once they handle it right. The scenario reacts to their choices, so it never feels scripted. Built in Articulate Storyline with a live AI behind it.

Live · Branching Scenario

Handling Difficult Conversations

Managers learn difficult conversations the hard way, on a real person. This is the practice round. Ten endings, each earned by the path the learner takes, so they feel the weight of a call instead of being handed the right one. Articulate Storyline. One month later, 87% of managers reported more confidence and 100% said the method helped them learn.

Live · Microlearning

AI Fundamentals: Prompt Engineering

People aren't short on AI hype, they're short on where to start. This module takes a complete beginner from the vocabulary to writing prompts that actually work. One clear outcome, nothing padded, the way microlearning should be. Articulate Rise. Post-survey, 80% strongly agreed they understood AI better and felt more confident using it.

Need to see range? Earlier K-12 / SEL and financial-literacy builds, children through adult learners, live in Built.

How I work.

You own the content, I own the learning. I won't pretend to be your subject-matter expert, and I'm not a content pumping machine. Quality over quantity, every time.

Sound design first

Backward design, Bloom's, UDL. I get the analysis right before building. A fast build on a weak foundation is just a polished course that doesn't teach.

Suggestions, not orders

I don't tell you what to do. I make recommendations and explain the reasoning, and I review your material for learning impact and alignment, not to check your facts.

AI as craft

I use tools like Claude and GPT for the grunt work, drafting, structuring, quality checks, so more of my time goes to design. WCAG 2.1 AA is baked in, not bolted on.

How we'll work

We start with a kickoff to lock objectives, outcomes, and audience. From there I set a regular check-in cadence, share suggestions early with the reasoning behind them, and flag needs or delays before they become problems. We're a team, and you stay in the loop the whole way.

Rate & start

From $50/hr. Fixed-price quotes on defined projects. Tell me what you're trying to teach and who needs to learn it, and I'll come back with format, scope, and cost, straight.

[email protected]

The receipts.

Some shipped, some validated at scale, some tested at the per-unit benchmark; aggregates labelled as estimates. Numbers tie to the system that produced them.

5h → 40s

per-course audit time

Batch course-evaluation pipeline: Python + Claude/Codex. Validated at scale on a dev LMS against 1,000 real course builds. Throughput 5,541 courses/hr (~133K/day). Zero failures across 71,000 deterministic evaluations. 100% data readiness using an adaptive rate-limiter.

3-4 wks → 2-3 days

to build a course

AI-assisted course build: 110-140 person-hrs → 16-24, curriculum supplied. Validated end-to-end.

6h → 10min

per-course edit time

Same workflow, edit mode.

$50K/yr est.

labor saved at Amazon

Project TIES: shipped and ran in production for 5 months.

+56%

survey participation lift

Amazon: 44.49% → 69.17% after the TIES rollout.

+30%

performance / efficiency

SOP-GPT + LearnOps, measured via PartyRock analytics.

The work, verbatim.

Five roles. Each entry is the system, the stack, and the measured or tested result.

EdPlus at ASU

Nov 2025 - Present

Learning Experience Designer / Instructional Designer

Scope: building internal AI tooling for a 5,000+ course operation serving the entire ASU Online Course Catalog. Hand-selected contributor to the Juris Doctor program team and a cross-functional AI taskforce (AI, UX, ID leadership). ID for the MS in Applied Statistics & Data Science.

Batch Course Evaluation SystemPython + Claude + Codex on Railway; async workers, job queues, batching, retry logic

Per-course audit time 5 hours → 40 seconds. Validated at scale on a dev LMS against 1,000 real course builds: 5,541 courses/hr (~133K/day) end-to-end throughput, zero failures across 71,000 deterministic evaluations, 100% data readiness on a 500-course representative run. Adaptive rate-limiter self-throttles against Canvas; cannot DoS the API. Grades against WCAG 2.1 AA + ID rubrics.

AI Course BuilderClaude-assisted authoring workflow with embedded WCAG + ID-standards checks

Total per-course build time, curriculum supplied: 110-140 person-hours / 3-4 weeks → 16-24 person-hours / 2-3 days. Per-course edit time 6 hours → 10 minutes. Validated end-to-end.

Audit-to-Remediation PipelineDetection, remediation queues, verification checks joined into one workflow

Closes the loop between detection and fix: audit findings flow into remediation queues with verification on the way out. Per-course review-fix-verify cycle reduced ~70% in tested workflow.

Amazon

Dec 2024 - Nov 2025

Learning Trainer

Project TIESPython + Slack webhooks + Asana + Amazon Quick Suite

Shipped and ran in production for 5 months. Survey participation +56% (44.49% → 69.17%). 80+ hours/quarter/teammate of manual data collection eliminated. ~$50K/yr labor savings (estimated from time × loaded rate). Identified 20% of SOPs as out-of-date on first run.

AI-Integrated Learning SimulationsArticulate Storyline with AI-driven branching

Built branching simulations with live-AI roleplay, giving managers a safe place to practice difficult conversations before having them live.

Facilitation & DeliveryClassroom and virtual training

5/5 facilitator feedback. Trained 300+ associates with on-time delivery on all L&D submissions.

Amazon

Jul 2024 - Dec 2024

Logistics Specialist

6,500+ escalation cases at a 3% defect rate.

Mechanic On-The-Go

Dec 2022 - Apr 2024

Co-Owner

Operations and financial tracking for a retail automotive service.

CNMI Public School System

Jul 2023 - Apr 2024

School Counselor

Won a 20% budget increase via a data-driven grant proposal.

Things I’ve built.

Six systems and four live demos. Tools first; demos you can open below.

AI Tool

SOP-GPT

+30% performance on complex processes (PartyRock analytics).

AI Tool

LearnOps

+30% workflow efficiency for L&D (PartyRock analytics).

EdPlus

Batch Course Evaluation Pipeline

Per-course audit 5h → 40s. Validated at scale on a dev LMS: 1,000 real courses, 5,541/hr, zero failures across 71,000 evaluations.

EdPlus

AI-Assisted Course Build

Per-course build 110-140 person-hrs → 16-24 (3-4 wks → 2-3 days). Validated end-to-end.

EdPlus

Audit-to-Remediation Pipeline

Detection → remediation queue → verification, joined into one workflow. ~70% cycle reduction in tested workflow.

Portfolio

bremiclxd.dev

Recruiter-mode AI chat: JD-fit, comp-band, objection-handling modes. Cloudflare Workers + Anthropic API, prompt-cached.

Case Study · Amazon

Project TIES

Python + Slack webhooks + Asana + Amazon Quick Suite. Shipped and ran in production for 5 months. +56% survey participation; 80+ hours/quarter/teammate of manual collection eliminated; ~$50K/yr labor savings (estimated). 20% of SOPs flagged out-of-date on first run.

Live Demo · AI Simulation

The Trainer Experience Series

Companies rolled out AI and their people pushed back, but trainers had no safe place to practice handling it. So I built one. The learner talks to an AI employee who's skeptical of AI at work, and a Python script checks off four de-escalation criteria as they earn them, passing only when all four are met. Articulate Storyline + Google Gemini, with cognitive load theory keeping the context and checklist on a separate button so attention stays on the conversation.

Live Demo · Branching Scenario

Handling Difficult Conversations

New and experienced managers froze in one-on-ones with their direct reports. I gave them the reps: a branching scenario with ten endings where every choice changes where they land, so the consequence is felt and not just told. Articulate Storyline. One month out, 87% of managers said they felt more confident in these conversations, and 100% said the practice method helped them learn.

Live Demo · Microlearning

AI Fundamentals: Prompt Engineering

My needs analysis turned up “AI fatigue”: people overwhelmed by AI's pace and unsure how to use it past a basic prompt. So I scoped one tight module that takes a beginner from AI terms to functional prompt engineering. One outcome, no filler. Articulate Rise. Post-survey, 80% strongly agreed they understood how AI works and felt more confident using it at work.

Earlier public-education work: K-12 SEL and financial literacy, plus one lesson rebuilt for adult L&D. Proof of audience range, from children to professionals.

Public Ed · SEL

Feeling Stuck in the Cold

Designing for educators, not just students. A mini professional-development session for fellow district counselors, who taught stress response as fight-or-flight only. It names the overlooked freeze response, shows how to spot it, and equips counselors with coping strategies and reflection activities to carry into their own SEL lessons. Counselors left able to identify a freeze response and called the training memorable and immediately usable.

Public Ed · Financial Literacy

Do You Really Want to Be a Millionaire?

Behavior change over information. A persuasive financial-literacy workshop for college students. It opens with a tongue-in-cheek “getting rich is easy,” then turns it, teaching four behavioral-economics traps through a live match activity and reframing the goal from wealth to well-being. A self-contained session that treats money as a behavioral question, not a math one.

Public Ed → Adult L&D

Time is Gold

Same content, any audience. A K-12 time-management seminar rebuilt as a facilitated adult workshop. Same evidence-based skills (prioritization, SMART goals, Pomodoro, boundaries) now anchored by six hands-on moments: a time-perception hook, an Eisenhower sort, a live Pomodoro sprint, a “say no” role-play, a personal time audit, and a commitment exit ticket. It moves learners from knowing the techniques to rehearsing them.

Public Ed · SEL

Give Me Some Respect

Foundational SEL for young learners. An elementary lesson on respect and disrespect: the golden rule, concrete examples, and what respect looks, sounds, and feels like, with discussion prompts and a “respect or disrespect?” sorting activity. Age-appropriate behavior modeling for young learners.

What I reach for.

Learning and development up front, the technical toolkit that delivers it right behind. Both load-bearing.

Learning & Development

  • Backward Design
  • Bloom’s Taxonomy
  • UDL
  • HPI/BEM
  • Assessment architecture
  • WCAG 2.1 AA

AI Systems

  • Production RAG
  • Prompt engineering
  • Batch evaluation pipelines
  • Agent orchestration
  • Prompt caching
  • Model failover
  • Refusal-safety hardening

Product

  • Stakeholder discovery
  • Problem framing
  • Scope definition
  • Prioritization

Process

  • SOP development
  • Cross-functional partnership
  • Training operations
  • Faculty partnership

Engineering

  • Python
  • Claude / Codex / OpenAI APIs
  • AWS
  • Cloudflare Workers + Pages
  • Railway
  • SQL / Postgres
  • Canvas LMS API
  • Git

Analytics

  • PowerBI
  • Dashboard design
  • ROI quantification
  • Airtable

Where the rigor came from.

Education and certifications.

Degrees

MS, Organizational Performance & Workplace Learning

Boise State University · Coursework

BS, Education

Northern Marianas College · Summa Cum Laude

AA, Education

Northern Marianas College · Magna Cum Laude

Certifications

Applied AI Foundations - Pilot

OpenAI · 2026

Data Analyst Professional

IBM

Workflow Specialist

Asana