Bonkers by Foyer
Bonkers by Foyer is a creative production system I helped rebuild from v2 to v3, adding reusable templates, multi-model fallback handling, and faster repeat workflows.
Overview
Bonkers is a creative production system that moves beyond one-off image generation to reusable workflows. Users discover styles, start from templates, refine outputs, and access their history in one place.
Bonkers is a creative production system that moves beyond one-off image generation to reusable workflows. Users discover styles, start from templates, refine outputs, and access their history in one place.
I led the v2 to v3 rebuild, focusing on template-first workflows, image-to-image capabilities, multi-model routing (Flux, Recraft, Ideogram), and performance optimization for repeat usage.
How It Was Built
The main technical choices behind the product, from system design to the parts that make it work day to day.
- Redesigned the generation pipeline around reusable templates with structured inputs, parameterized defaults, and version control.
- Implemented multi-model routing with automatic fallback (Flux → Recraft → Ideogram), parallel execution for latency reduction, and circuit-breaker patterns for failed providers.
- Redesigned the generation pipeline around reusable templates with structured inputs, parameterized defaults, and version control.
- Implemented multi-model routing with automatic fallback (Flux → Recraft → Ideogram), parallel execution for latency reduction, and circuit-breaker patterns for failed providers.
- Extended beyond text-to-image to support image-to-image transformations, style-preserving variants, and iterative refinement workflows.
- Built Templates as a first-class product surface with authoring tools, template discovery, and one-click instantiation rather than treating them as saved prompts.
Impact
- The v3 rebuild made the product easier to use again and again, which helped daily active usage grow by 50%.
- Fallback handling and parallel runs cut service failures by 60% and improved response times by 30%, so the product felt more dependable.
- The v3 rebuild made the product easier to use again and again, which helped daily active usage grow by 50%.
- Fallback handling and parallel runs cut service failures by 60% and improved response times by 30%, so the product felt more dependable.
- Templates drove 10K+ generated images in the first month because they made it easier to get to a useful starting point quickly.
Highlights
- Shifted from one-shot generation to template-driven repeatable workflows.
- Achieved 60% reduction in service failures through multi-model fallback and parallel execution.
- Shifted from one-shot generation to template-driven repeatable workflows.
- Achieved 60% reduction in service failures through multi-model fallback and parallel execution.
- Templates drove 10K+ generations in first month by lowering the barrier to useful outputs.
Tech Stack
More Projects
Additional work across AI products, developer tooling, and full-stack systems.
Next.js 16
Edward
An AI coding workspace where developers can describe apps in plain language, generate production-ready code, inspect and edit files in real-time, run projects in isolated Docker environments, publish live previews, and sync everything directly to GitHub without leaving the product.
Next.js
Agentic chat
AI workspace that uses memory, documents, tools, and vision to give grounded answers.
AWS (ECS, ECR, S3)
DeployNinja
GitHub-native deployment platform for automated builds, live logs, and repeatable releases.