Eric Pendleton

Communication · Learning & systems · Practical AI

Complexity into clarity. Clarity into action.

Welcome. I work in technical communication and learning development, and I designed and built the site and apps you'll find here.

Explore the case studies, try an app, or ask FitCheck about my experience. For your next meeting or podcast, try LiveCue: it explains unfamiliar terms as they come up.

There's also a little background, a few photos, and a short film at the bottom that explains almost nothing about my professional qualifications. Enjoy.

FitCheck

Have a role or a question?

Ask about my experience, or paste a role or project description. FitCheck explains where my background fits and where it may not, and points you to relevant work samples.

About me Contact LinkedIn ↗

01Apps & systems

Four recent builds. Three are public. Go poke at them.

I built these products, wrote the specifications, designed every detail, and directed all technical development.

My apps are free to use and don't collect any personal data, so give them a spin! LiveCue is really useful. The flight simulation is fun and the views of the ship in space are spectacular. I keep working on them so let me know what you think!

LiveCue

Chrome or EdgeLaptop or phoneAudio not stored

Live transcription that explains unfamiliar names, acronyms and terms as they come up. No pretending you know what pari passu means.

Try it ↗

The demo needs no key. Live use takes your own Gemini key, kept in your browser.

The Enterprise-D at warp 9 inside its blue warp bubble, course confirmed for the Badlands, the missions panel open on the right.

The ship under its shields at the end of a warp jump, a Borg cube above it and a planet with a second ship behind.

The saucer up close, U.S.S. Enterprise NCC-1701-D, turning in combat with a Jem'Hadar attack ship in front of a ringed planet.

The saucer in combat, torpedoes in flight, a Borg cube at the left and a second Federation ship behind.

The ship seen from below against a purple nebula, shields raised, the tactical panel open.

The saucer from above inside its shield bubble, beside a Borg cube in the Badlands.

The transporter beam reaching down to a planet: four survivors dematerializing, 36 percent, with the Badlands navigation panel open.

The night side of the saucer during a rescue: six survivors beamed aboard from a derelict, a planet below.

The saucer filling the frame as the ship brakes on arrival, the nacelles glowing behind it.

Enterprise-D Flight Deck

Any browserLaptop or phoneBuild 119

A starship flight and tactical simulator. Fly the ship yourself, or let the crew take the helm, Captain.

Try it ↗

Unofficial fan project, not affiliated with Paramount.

Meridian, the interactive project briefing: a fictional campus whose funding routes are clearer, with the capital picture of senior facility, sponsor capital, public incentives and site control.

Infrastructure Project Briefing Interactive demo

Complex projects throw off meetings, documents, decisions, changing assumptions and open questions.

I designed an AI-assisted workflow that turns recordings and source documents into one coherent project briefing, which I execute, check, and publish internally to my partners each week.

Fictionalized demonstration based on a real, ongoing project.

Explore the demo ↗

Le Hub Active deployment · Personal operating system

I was tired of hunting for emails, texts, receipts, AI chats, scans and spreadsheets across my laptop, my iPhone, iCloud and Downloads, then copying and pasting it all again just to bring an AI up to speed. That's friction. I hate friction.

So I built Le Hub: one canonical record of my active projects, priorities and decisions that every AI I work with reads and writes under the same rules. It gives my AI collaborators shared context, so I spend less time finding things and explaining the same background again.

It isn't an app, at least not yet. What runs today is the working system underneath: one shared record, common rules, and the connections to Gmail and Drive. That's the heart of the beast. The app that will sit on top is what I'm building in my free time, along with a standalone FitCheck. Both are works in progress.

02Garside's Ice Cream, Saco, Maine

The ice cream stand that became a business laboratory

Garside's Ice Cream in Saco, Maine: a small white stand with a blue script sign and a line of customers at the serving windows on a sunny day.

Eric in an apron at Garside's, making ice cream: fresh ice cream pours from the freezer's spout into a pan he holds under it.

An older photo of Garside's: the stand under its red and black sign, Cones, Sundaes, Frappes, with cars of the time parked in front and customers at the windows.

The front of Garside's: the white stand under its blue script sign, flavor menus in the windows, flower boxes and a red-topped bin at each end.

Two Garside's staff in front of the stand, smiling, each holding out an ice cream cone.

Garside's at night: the lit stand under its older sign, with a crowd of customers at the windows.

Garside's from the side on a sunny day, a few customers lined up at the windows.

OperationsProduct developmentHiringTrainingEmployee manualPricingVendor negotiationsMarket research

My family owned Garside's, which has made its own ice cream on Ferry Road since 1956, for decades. I developed the recipes, trained the employees, managed operations, set the prices and did just about everything else, including mowing the lawn.

When customer traffic began declining, I wanted to understand why. So I made the business the subject of my master's research: customer surveys, interviews, focus groups, vendor pricing, historical sales and weather data. The findings challenged some obvious explanations and exposed problems we could actually fix.

The resulting plan focused on consistency, product variety, customer retention and training. One immediate change, renegotiating our dairy pricing, cut a key ingredient from $26 to $16 a bag and saved more than $7,000 a season. It was a practical lesson in separating what a business can control from what it can't.

I didn't just sling ice cream. But I absolutely slung ice cream.

The early years were growth. When my family bought the stand, the summer I finished high school, it had a loyal following, thirteen flavors and unpredictable hours. We set regular hours, upgraded the cream and expanded the flavors; revenue rose 800% over the next two seasons. I wrote about a hundred recipes, starting with Mint Chocolate Chip the first summer, and thirteen flavors became forty. Much of it I did on weekends from Boston. We sold the stand in 2018.

The decline came much later. The stand records every order, every day, in a notebook, and by the 2000s decades of those records showed customer traffic falling. The market around us was changing, too: tourism along the Maine coast had softened, the country was counting cholesterol, and fast-food chains were selling inexpensive sundaes.

To understand what was driving the decline and where we could make a difference, I made Garside's the subject of my master's capstone: two surveys, 314 respondents; fourteen customer interviews and focus groups; a vendor-pricing review; state weather data; and a season observing the business at the serving windows. A third survey followed in 2017.

The historical data didn't support weather as the principal explanation: four of the best ice cream summers in the record produced no bump. Customers didn't point to the economy either: 87% said it hadn't changed how often they came.
Customers didn't point to the product: 95% rated Garside's equal to or better than Häagen-Dazs and Ben & Jerry's, and 58% said better.
The research pointed to four likely causes. Three belonged to the market: Maine's tourism slump after 2001, a public eating less ice cream for its arteries, and a cheaper sundae at the drive-through. The fourth was ours: hours trimmed at both ends, and running out of basics like sugar cones. Once a customer is lost, getting them back is the hard part.
So the plan worked on what we controlled: consistency and promotion. Fifteen points, most of them cheap: new flavors every week (62% asked for them), a flavor contest (winner: Mosquito Ripple), weekday specials, gift certificates, the old hours restored, and a rewritten training manual.
The first move paid before the paper was finished. We asked the dairy for volume pricing. The base mix went from $26 a bag to $16 overnight, saving over $7,000 a season.

The Scoop

Employee manual · 10 pages · PDF · 0.9 MB

A good operating plan isn't worth much if the next employee doesn't know how to carry it out. Point five of the plan: I rewrote our employee manual to make procedures, expectations and customer-service standards clear from day one, from opening and closing checklists to the "arc" scooping technique and what to do about a Grumpster. It became the foundation for each season's training. Training meant showing them the work, letting them practice, and checking that they could carry it out. This is the 2015 edition.

View ↗ Download

03Learning & performance

Before we build the training, what's getting in the way?

Before building a course, I look at what people need to do, what gets in their way, and what improvement would look like.

A customer-service manager asks for a course: "Onboarding is taking too long." Here is what three new hires said. Select what you're hearing; more than one can be true.

These sound similar, but they call for different responses. Practice might help with one; easier access to information or clearer authority might help with another.

Behind the approach

Learning for Competence, white paper, February 2018, sole author. The performance model and the three rings. It already argued against deviation rates as a measure of training; the rest of this panel is how I'd put it today.
Training Needs Analysis worksheet, 2019. Starts from the business outcome and asks which competencies are trainable at all.
Training Development Guide, 2019. Demonstration, supervised practice, and a signed final assessment.

04Work samples

Different audiences. Different ways in.

West Side Kitchen, Paris

Whiteboard explainer · YouTube

The same whiteboard format I used in regulated e-learning, turned on a friend's sandwich café in Paris's 17th, 25 years in business. One idea, told plainly. Friendly sandwiches. Delivered.

Watch on YouTube ↗

Selected Work Samples

14 pages · PDF · 2 MB · August 2026

Eight samples from twenty years inside corporate L&D, plus the early AI record. Each opens on its own page:

View ↗ Download

First page of the finance writing samples

Finance Emails and Blog Articles

4 pages · PDF · 0.8 MB · 2023

Four client pieces written for Pendleton Financing, my commercial-lending brokerage: why lenders want an LLC as the borrower, adaptive reuse, getting started in long-term rentals, and 1031 exchanges. Plain English for people about to sign something.

View ↗ Download

What the star ratings didn't tell us

Text analysis · Research communication · Chart design · 2017

While training manager at Luminoso, I analyzed 13,465 passenger reviews across 19 airlines to understand what travelers valued, and what went wrong. I sourced the data, conducted the analysis, wrote the story and designed the ranking chart. Inc. later covered the study and reproduced the chart.

5 Steps to Unlocking the Value in Unstructured Big Data

Article · Quirk's Media · 2017

Five practical things to do with the text nobody reads: survey comments, call transcripts, support tickets, social posts. Written for marketing researchers at a point when "text analytics" was a vendor promise more than a practice. Still holds up: the lessons are business strategy and operating habits, not the tools.

Read at Quirk's ↗

Pride at Work: Make It Worth Showing Up For

Editorial writing · Workplace inclusion · Adapted from a 2023 client draft

Practical ideas for celebrating Pride at work, from paying queer artists to making support easier to find. A client piece for Grindr through Graphite, tightened here for the portfolio.

05How I work with AI

AI made me dramatically faster. It also gave me more places to lose the thread.

During a LiveCue test, the app lost the end of a transcript. Another AI had reviewed the code and missed the problem. Here's how I tracked it down and checked the repair: choose one of the four habits I work by to see that step.

Case · LiveCue · September 30, 2026

The 56 words that disappeared.

In a session I ran to test LiveCue, a long passage appeared as live text. When I pressed Stop, the speech service's final transcript came back shorter, with earlier wording changed, and the app threw away the last 56 words it had already shown. The repair keeps them, marked as unconfirmed.

01 · Spec before build

Start with the problem, the audience and a clear definition of success. The specification can evolve, but the purpose shouldn't get lost.

The rule: never discard words the listener has already seen. Keep the speech service's final text exactly as delivered, and show anything it dropped separately, marked unconfirmed, because a live draft is not proof of accuracy.

Reenactment · sample wording

On screen while talking

Thanks, everyone. Before we wrap, the launch moves to the fourteenth. The venue holds three hundred, and invitations go out Friday. Replies are due by the first.

Final text from the speech service

Thanks, everybody. Before we wrap, the launch moves to the fourteenth.

Saved transcript

Thanks, everybody. Before we wrap, the launch moves to the fourteenth.

The last two sentences, already shown on screen, are gone.

unconfirmed draft · provider final omitted later draft textThe venue holds three hundred, and invitations go out Friday. Replies are due by the first.

Evidence and limits

From the LiveCue repair report of September 30, 2026, on a desktop Chrome session of release candidate 5. Last live draft: 1,323 characters. Final from the speech service: 877 characters, with earlier wording changed. The distinct ending it omitted: 267 characters, 56 words. After the repair, replaying the recorded sequence kept all 267 in the visible transcript and the export.

Not established: that recognition is complete or accurate, that every provider path behaves the same, or a fresh live test. The kept words are what the service sent as provisional text; their accuracy is not confirmed. The October 21 check confirms the safeguard's code is in the deployed release, not its behavior in a new session. The wording in the reenactment is invented.

AI can rewrite 500 pages in an afternoon. Checking page 340 is still a person’s job.

06About

A little background

I help people get up to speed, make sense of complicated information, and get things done. I develop training, write guidance people can use on the job, and build tools that make everyday work easier.

I like figuring things out: why a process takes so long, where people get stuck, what would make something work better. Then I make something useful: a learning program, a clearer explanation, an app. The satisfaction comes when someone can spend less time wrestling with the work and more time getting sh*t done. Or playing.

Places I've called home

The technology is new. The judgment behind it isn't.

NowI'm a partner and executive producer at Lunchbox Labs, an animation studio with a feature in production. My work spans development, production and the business side of getting a film made: preparing materials, working through decisions and helping move the project forward.

Through Lunchbox Labs, one of Gaia Eco Developments' founding owners, I also help explain the venture's projects and plans: investor communications and executive briefings on the projects, the funding strategy and what needs to happen next.

BeforeMy first job after Colby was at L.L.Bean in Maine. Teaching followed at Proctor Academy, which sent me back to France to run its term-abroad program, then graduate study and teaching at Washington University in St. Louis.

After six years in academic teaching, I moved into business, working in corporate communications and company-wide English training at bioMérieux in Lyon.

Back in the US, I worked across pharmaceuticals, banking, technology and government. At Takeda, Alexion, Shire and Citizens Bank, my projects included an enterprise train-the-trainer program, training and role-based qualification for regulated pharmaceutical work, and a knowledge system to help lending professionals navigate an internal credit-risk platform used by thousands of active daily users: loan officers, credit analysts and lending managers.

Along the way

Born in Waterville, and raised in Saco, Maine. Only child. My father taught history and directed athletics at Deering High School in Portland.

The summer I finished high school, my family bought Garside's, a seasonal ice cream stand on the Saco River. I made the ice cream, wrote the recipes, hired and trained the crews, painted the building and mowed the grass. I kept doing that on weekends from Boston for years, to help my mother. She passed and I sold it in 2018.

Thornton Academy, Phillips Exeter, then Colby, where I studied French and sang tenor with the Colby 8.