Reddy · AI Implementation

7+ enterprise clients. Hundreds of simulations.
AI training built for the people who need to practice, not just learn.

As part-time Director of Learning at Reddy, I helped build the systems that turn business logic into realistic practice environments — giving call center agents the experience of fifty AI conversations in dozens of scenarios before their first real call.

7+enterprise clients I built simulations for

3.5xROI on Reddy's program (per Reddy)

+50%improvement in agent ramp speed

+61%increase in CSAT scores

The ask

Build AI training that drives real behavior change for enterprise call center agents — at scale, across clients with totally different call drivers, scripts, and tools.

The move

Half learning scientist, half forward-deployed engineer. Designed deterministic pipelines that turn business logic into game-like simulations, with humans in the loop at the right moments.

The outcome

Hundreds of simulations shipped across 7+ enterprise clients. 110 commits, 400,000+ lines of code, all in 20 hrs/week over 1.5 years. The pipeline became foundation Reddy now automates further.

How we got there

Experiential learning used to be expensive. AI made it possible at scale.

Five years ago, building a custom training simulation for one call scenario at one company was practically impossible. With intelligent systems that combine AI and human insights into what makes great customer service, you can now build dozens of simulations with only 20 hours a week.

What changed isn't just smarter models. It's smarter use of them — deterministic pipelines, well-organized data, and human operators who understand both the technology and the learning science behind it.

My role bridged two worlds. At the strategic level, I worked with the founders on learning theory, LMS architecture, and making sure simulations drove real behavioral change. At the tactical level, I was writing code, building data pipelines, and deploying simulations directly to enterprise clients — embedded with client teams as a forward-deployed engineer who understood both the platform's capabilities and the pedagogical goals.

The pipeline

Six steps from raw business logic to working simulation.

Neither the human nor the AI can do this alone. The AI can't understand why a particular escalation path matters to a particular customer segment. The human can't hand-build 45 scenario variations. The pipeline works because each step plays to the right strengths.

Data

SOPs, call recordings, knowledge bases, scorecards — every client's source material is different. The first job is ingesting raw business logic and turning it into structured data that downstream systems can actually work with.

Organized patterns

Extract the decision trees, compliance rules, and conversation flows from the structured data. This is where the shape of the simulation starts to emerge — what scenarios matter, what branches exist, what a good outcome looks like.

Human review

A human who understands the business logic, the customer experience, and the learner's reality reviews the patterns before anything gets built. AI is good at finding structure. Humans are good at knowing which structure matters.

Transformation to code

AI generates functional HTML that recreates the learner's actual workspace — their CRM, their scripts, their tools — populated with AI customers who behave like real customers. Each simulation is closer to a custom video game than a training module.

Human review again

Another human pass. Does the AI customer behave realistically? Are the scenarios logically sound? Does the evaluation rubric capture what actually matters for this call driver? Simulations that train the wrong behavior are worse than no training at all.

Final craft

The last step is artistry — tuning feedback quality, adjusting difficulty curves, refining the AI evaluator with datasets of both positive and negative examples. This is where platform expertise and learning science meet. The final product couldn't exist without either the human or the AI.

This reflects how I worked during my time at Reddy in 2024–2025. Since then, the team has automated significantly more of this pipeline — their AI now handles the vast majority of the heavy lifting and they're putting powerful tools directly in their customers' hands. What I built was part of the foundation that made that possible.

Clients I worked with directly:

Morgan & Morgan Fortune 500 Retail Globe Food Delivery App Affiliated Monitoring ISG Harte Hanks

7+ enterprise clients. Hundreds of simulations. AI training built for the people who need to practice, not just learn.