Brandon Gell

An internal AI editorial tool project failed because the builder focused on technical implementation rather than identifying the actual workflow problem, ultimately leading to adopting Claude Teams as a simpler, more reliable solution.

“Head of Every Studio who provided feedback that individual projects made no sense and advocated for a single source of truth.”

“Created and maintains OpenClaw agent Zosia; piloted Plus One hosted OpenClaw for team productivity.”

“Coauthor discussing organizational lessons from implementing Plus One OpenClaw agents in workplace.”

“Ran P&L analysis through Claude models to identify data errors and test task verification capabilities.”

Thinking about AI product development through board game mechanics—specifically worker placement, area control, and victory conditions—helps overcome creative blocks when building with large language models.

“Built an AI CFO tool to help steer the company.”

Software in 2026 will treat AI agents as first-class citizens across three levels: operating user interfaces like humans, accessing hidden backend code capabilities, and making direct code modifications that only developers can do today.

“Shared predictions for 2026 on AI podcast about how software will be built and the future of autonomous AI agents.”

A software developer rebuilt the Sparkle file organization app from Electron to Swift using AI in 14 days, demonstrating how AI-assisted development is changing the speed and efficiency of software engineering.

“Helped build Sparkle v1 and described the product's vision for automatic file organization.”

Claude Haiku 4.5 delivers nearly Sonnet 4.5-level performance at 3x cheaper pricing, making it an optimal choice for developers building agentic applications.

“Warned that Every would go out of business if they didn't switch from expensive Sonnet 4 to GPT-5-mini for cost reasons.”

Kairos, an AI-powered reading companion, enables fundamentally new ways to read by integrating AI directly into the reading experience, allowing readers to actively probe and discuss texts rather than passively consume them.

“Introduced the Kairos AI reading tool experiment from Every Studio.”

Monologue, an AI voice dictation app, achieved product-market fit with thousands of users during beta by building community before launch, contrary to traditional app development approaches.

“Discusses with Dan Shipper and Naveen Naidu about how Naveen built Monologue and its journey to product-market fit.”