Skip to case study
WorkshopProduct development case study

CONCEIVED & DIRECTED BY BEN KLAIBER

MaxiMail

A communication workspace,
designed around the work.

AI-assisted writing, rich-media Snippets, and an attachment workspace for bookmarking, conversion, and OCR. The product decisions and engineering work behind MaxiMail, conceived and directed by Ben Klaiber.

Ben Klaiber Principal Workflow & Experience Architect, MMWB Inc.

MaxiMail overview visual with its communication tools, organization features, and application presented on a laptop.
MaxiMail · Product overview with demonstration content
Project
Independent product development
Leadership
Product, workflow, UX & engineering direction
Core platform
Electron · React / Next.js · SQLite · macOS
Evidence snapshot
October 2026 · Active development

01 / PRODUCT STRATEGY

Design the work around
the message.

A client response may need a reusable explanation, a visual, information trapped in a scan, and a different tone for its audience. Those needs shaped MaxiMail.

I approached email as a collection of connected work problems. People build their own libraries of responses, download attachments into temporary folders, open separate tools to convert images or extract text, and search old conversations to reconstruct a relationship. Each detour interrupts the task that prompted it.

MaxiMail brings those activities into the communication environment. Rich-media Snippets retain reusable knowledge. Attachment Workspace makes received material easier to collect, transform, and reuse. Relationship and attention views organize the surrounding context. The AI tools address specific writing decisions rather than reducing everything to a generic rewrite.

My product strategy was to connect these capabilities into useful sequences: find material, adapt it, combine it with reusable content, and communicate with the audience in mind. That required workflow architecture, not simply a larger feature list.

02 / COMMUNICATION DESIGN

Assistance for intent,
expression, and audience.

I separated five communication needs into distinct tools. The result gives writers more specific control than a single AI button asked to do everything.

Elevate

Shape the communication around its intended outcome. Elevate works with context and the writer’s original intent, helping develop the message rather than merely changing its tone.

Intent & impact

Polish

Refine clarity and expression with selectable writing styles, a preview, and further revision. This separates editorial finishing from the more substantial communication decisions handled by Elevate.

Editorial control

Culture Mode

Bring cultural expectations into the writing process. The assistance addresses how a message may be received by its audience, adding a dimension that a generic “make this professional” instruction misses.

Audience awareness

QuickFact

Work through factual questions within the communication workflow. Research assistance stays close to the claim or explanation being developed, without requiring a separate conversation disconnected from the draft.

In-context fact assistance

Subject Suggestions

Develop subject lines from the message’s context. Subject framing becomes a focused editorial decision, distinct from rewriting the body.

Contextual framing

Native intelligence: eligible features use Apple Intelligence-first routing. Availability and processing paths depend on the feature and device. [1]

SNIPPETS / REUSABLE RICH CONTENT

Reusable responses.
Including the visuals.

Snippets combine formatted text, images, GIFs, built-in variables, and shortcuts. A reusable response can carry its explanation and visual material together, with variable elements adapted for the communication.

Text, images & GIFs
Retain a complete piece of communication, including visual instructions or expressive media, instead of rebuilding it from separate assets.
Built-in variables
Personalize reusable content without maintaining a different static version for every variation.
Shortcut insertion
Bring the prepared material into the current draft at the point it is needed.

The product decision: treat repeated communication as a reusable resource. An onboarding explanation, support walkthrough, or project follow-up can combine consistent wording with visual context and variable content.

VISUAL COMMUNICATION

Find the visual.
Refine it where you’re writing.

Pexels photography and GIPHY GIFs share a searchable picker. Inline image tools then handle sizing, editing, rotation, and optimization. I designed this as part of composing a richer response, alongside Snippets and stationery.

03 / WORKFLOW ARCHITECTURE

Attention organized around
people and priorities.

Mail volume is a poor proxy for importance. MaxiMail combines relationship context, tunable Smart Views, and sender-level actions so the user can shape what stays in focus.

MaxiMail workspace showing Discussion Groups, Attention Views, Smart Views and relationship context with demonstration messages.
Discussion Groups, Relationship Views, Attention Views, and task-specific Smart Views provide different ways into the same communication context.

Smart Views with adjustable priorities

AI-enriched categories connect mail to activities such as applications, contracts, appointments, and travel. Importance and recency thresholds let the user tune category relevance instead of accepting a fixed classification as the final answer.

Relationship-centered navigation

Focus on Sender, Relationship Views, and Discussion Groups make a person or ongoing discussion the organizing context. This supports following a relationship across messages rather than repeatedly reconstructing it through search.

Keep Only Recent & sender actions

Apply retention and cleanup decisions at the sender level. Keep Only Recent is designed for communication whose older versions lose usefulness, while bulk sender actions reduce repeated, message-by-message handling.

ATTACHMENT WORKSPACE

Collect, convert,
extract, and reuse.

An attachment can be a reference, a reusable asset, or information trapped in an image. I designed the workspace to support those different jobs.

Bookmark valuable files, organize them into groups, convert images, and extract text through one-click OCR. The attachment becomes material to work with, not just a file to download and deal with elsewhere.

MaxiMail Attachment Workspace with Bookmarked files, a Design Projects group, cross-account filters, and a document workspace.
Bookmarks and project groups give important attachments a reusable home across the communication workflow.
Collect

A cross-account reference library.

Search attachments across connected accounts, bookmark high-value files, and organize related material into named groups. The collection can follow a project rather than whichever inbox received each file. The Bookmarked area and Design Projects group shown here illustrate that approach.

Convert

Prepare images for their next use.

Convert a supported image to another format inside the workspace instead of downloading it, opening a separate converter, exporting, and bringing it back. File preparation stays beside file discovery and reuse.

Extract

One-click OCR, with output you can format.

Extract text from a scan or image in one click, then format the output for its next use. Source material can contribute to a reply or document without a separate OCR utility and manual retyping.

WHY THESE FEATURES BELONG TOGETHER

A project update can draw on a bookmarked reference, text extracted from a scan, a converted image, and a rich-media Snippet. These are connected tasks. Designing them together reduces the need to assemble the workflow across unrelated utilities.

Example workflow · The tools can also be used independently. [3]

FROM CONCEPT TO ARCHITECTURE

One desktop product.
Several specialist systems.

Rich composition, file transformation, contextual views, and multi-provider synchronization need different services. The architectural work is connecting them without fragmenting the experience.

Interaction layer

React / Next.js renderer

AI-assisted writing, rich-media composition, attention views, and the file workspace.

Desktop services

Electron + native macOS

Local SQLite, native media and document integrations, protected credentials, and coordinated state.

Provider adapters

Gmail · Graph · IMAP/SMTP

Provider-specific synchronization and operations behind the shared application experience.

Shared state, specialized views. Relationship, attention, and mailbox views depend on a common ordered state model. Centralizing that responsibility limits competing interpretations of the same account while letting each view support a different workflow.

Native capabilities where they add value. macOS integrations support document and media work, notifications, Contacts, and Calendar. The local architecture also requires deliberate boundaries between privileged services, external content, stored credentials, and temporary files.

Simplified architecture based on the development record. The Electron application and broader SwiftUI exploration are separate workstreams. [1, 2]

04 / DIRECTING AI-ASSISTED DEVELOPMENT

Product ownership through
the difficult engineering.

AI accelerated code production. I supplied the workflow model, made implementation tradeoffs, diagnosed architectural weaknesses, and directed corrections when the result diverged from the product intent.

  1. 01

    Model the work

    Connect writing, reusable content, file transformation, and attention management before specifying isolated controls.

  2. 02

    Direct bounded changes

    Give coding agents defined responsibilities within the existing services, adapters, and state ownership.

  3. 03

    Trace the bottleneck

    Inspect interaction behavior and use targeted measurements to distinguish rendering, data preparation, and provider work.

  4. 04

    Revise the architecture

    Reduce redundant work, extract safe module boundaries, and retain measured gains without accepting unrelated regressions.

HUMAN DIRECTION / AI IMPLEMENTATION

Direction, implementation,
and technical judgment.

The work combined product leadership with hands-on evaluation of a complex desktop application.

My responsibilities

Conception, workflow and interaction design, requirements, priorities, implementation planning, and the choice of technical approach.

Reviewing builds, tracing unexpected behavior, directing corrective engineering, and making acceptance or rollback decisions.

AI-assisted implementation

Coding tools generated and revised code, implemented scoped changes, and supported tests and diagnostic work under that direction.

The development challenge was coordinating those contributions across a stateful renderer, local services, and provider adapters while preserving clear ownership of behavior.

SELECTED TECHNICAL EVIDENCE

Stop loading full messages to prepare a list.

A 1,000-message test exposed an avoidable data cost: list preparation was loading large saved message bodies. Using stored previews reduced both preparation time and data volume, while retaining body recovery for missing previews.

List preparation time

~2.7 s68 ms

Before → after, fixed synthetic test

Data loaded for that list

~106 MB0.92 MB

Data loaded, not total application memory

Controlled source benchmark, September 2026. These figures measure the fixed list-preparation test, not installed-app startup, total memory use, or live provider latency. [2]

ARCHITECTURAL DECOMPOSITION

Reduce coupling without a wholesale rewrite.

Seventy independent declarations moved into eight focused modules. A typed mailbox-row boundary followed, while stateful mailbox decisions remained in MailApp.

The sequencing mattered: separate presentation first, preserve established state ownership, and validate the installed result before attempting another extraction.

PROVIDER-SPECIFIC DIAGNOSIS

Resolve a provider mapping, not an apparent send failure.

In a 30-cell delivery matrix, two messages appeared missing. They were in AOL Spam; exposing AOL’s provider-owned Bulk / Junk mailbox completed the test.

The finding located the fault in folder visibility rather than delivery. All 30 tested cells then passed the rich-message contract, including inline imagery and attachments.

PERFORMANCE TRADEOFFS

Evaluate the gain and its cost.

Changes that worsened Reader memory or conversation caching were reverted. Improvements that held up were retained and remeasured from the better baseline.

This was iterative engineering direction: distinguish useful optimization from complexity that moves the bottleneck or increases resource use elsewhere.

Further engineering: incremental sync, native security, and staged content delivery

Incremental sync instead of full rewrites

A controlled Gmail History update against 20,000 saved rows went from rewriting all rows in roughly 70–73 ms to updating only the zero, one, or three changed rows in roughly 4–7 ms. Identity and sync-cursor protections were retained.

Desktop and local-data boundaries

Hardening addressed privileged IPC, permissions, external-browser isolation, temporary attachment lifetimes, account-scoped caches, and private database files. Credentials are protected; ordinary SQLite relies on filesystem and platform disk protection rather than database-level encryption.

Decouple cached restoration from catalog discovery

Known Yahoo and AOL mailboxes began restoring saved messages before a fixed 30 ms folder-catalog barrier. Unknown mailboxes and provider work retained their verification step. This changed the dependency order rather than skipping provider checks.

Stage content around its dependencies

In a controlled Graph test, text delivery changed from 88 ms and three requests to 21 ms and two requests, with inline images following through the existing path. Image-only messages retained their image dependency.

05 / RESULTS & CURRENT STATE

An advanced workflow product,
with documented engineering progress.

The work brings communication intelligence, reusable rich content, file transformation, and attention management into one desktop application. Development and release verification remain active.

Implemented workflows

Five targeted AI communication tools; Snippets with images, GIFs, variables, and shortcuts; integrated media search and image tools; attachment bookmarking, groups, conversion, and one-click OCR; relationship and attention views; Smart Views; and Keep Only Recent.

Measured technical improvements

Controlled list-preparation and synchronization benchmarks, a six-provider navigation matrix, 30 checked delivery cells, and signed app-only structural-validation checkpoints. Measurements retain their documented test scope.

Native exploration

Broader SwiftUI macOS/iOS development is a separate workstream. It is not presented as completed feature parity with the Electron application.

Continuing verification

The atlas flags offline reconciliation, Stationery 2.0, updater distribution, and release packaging for status reconciliation. Historical development notes do not by themselves establish the current completion state of those items.

Selected checkpoints

  1. Provider delivery, navigation, reliability, and app-only security progress documented.

  2. Controlled structural extraction and installed visual acceptance recorded.

  3. Performance hotfix ledger separates synthetic gains from remaining installed checks.

  4. Feature atlas consolidates implemented capabilities and verification items.

Sources, status, and measurement notes

[1] MaxiMail Feature Atlas, 20 October 2026. The 79-feature catalog and analytical brief establish the feature set and its status distinctions. The atlas combines creator confirmation and project documentation; “Verify / roadmap” is not a declaration that an item is missing.

[2] Documented engineering history. Architecture, performance numbers, provider tests, and structural-extraction milestones draw on the project’s engineering documentation. Source tests, installed-app checks, and production-release evidence are distinct. The benchmark figures are controlled source results, not whole-application or competitor comparisons.

[3] Product capabilities and application imagery. Advanced bookmarking, image conversion, OCR with formattable output, and rich-media Snippets reflect creator-confirmed functionality. The composer views show Pexels search, GIPHY search, and inline image tools. Overview and workspace imagery uses demonstration content.

Exact Snippets token names, conversion format lists, OCR output formats, and unsupported automation have not been inferred. Example workflows illustrate how the documented capabilities relate; they are not new benchmark or automation claims.

WHAT THE WORK DEMONSTRATES

The product work is in
connecting the capabilities.

MaxiMail brings together editorial judgment, reusable knowledge, visual communication, document work, and attention management. The value lies in how those capabilities support a complete task, not in treating each tool as an isolated feature.

My role was to establish that product logic and carry it through implementation: define the interactions, direct AI-assisted development, diagnose the difficult parts, and make architectural corrections without losing the user’s original purpose.

MaxiMail product image

Open full-resolution image