Building AI-Native Code Platform With Java for Java

Jul 3, 2025

Jonathan Ellis, the creator of Brokk, an AI tool for writing code, dives deep into AI's role in enhancing programmer productivity. He discusses the evolution of coding practices, comparing the productivity of younger versus older programmers. The conversation reveals the unique features of Brokk, including context sculpting for improved AI interactions and its open-source nature. Ellis also highlights challenges within large codebases and the use of AI for code reviews and technical debt management, showcasing a shift in mindset among developers.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

ANECDOTE

AI Compensates for Aging Programmer

Jonathan Ellis shares how AI compensates for his reduced energy and slower learning as he ages.
He highlights the synergy between experienced programmers and AI to enhance coding productivity.

ADVICE

Read Code Fast to Guide AI

Read code quickly and critically to judge AI-generated code quality.
Accept or reject AI outputs continuously for effective AI-assisted coding.

INSIGHT

Sculpting AI Context in Brock

Brock enables sculpting the AI's context to improve its problem-solving accuracy.
It surfaces all AI context to users to fix incorrect assumptions, avoiding black-box models.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

An airhacks.fm conversation with Jonathan Ellis (@spyced) about:

brokk AI tool for code generation named after Norse god of the forge, AI as complement to experienced programmers' skillsets, age and productivity in programming, transition from JVector to working on Cassandra codebase, challenges with AI in large codebases with extensive context, building tools for historical Java codebases, comparison of productivity between younger and older programmers, brute force coding vs experienced approach, reading code quickly as a senior skill, AI generating nested if-else statements vs better structures, context sculpting in Brokk, open source nature of Brokk, no black boxes philosophy, surfacing AI context to users, automatic context pulling with manual override options, importing dependencies and decompiling JARs for context, syntax tree based summarization, Maven and Gradle dependency handling, unique Java-specific features, multiple AI model support simultaneously, Claude vs Gemini Pro performance differences, Git history as context source, capturing commits and diffs for regression analysis, migration analysis between commits, AI code review and technical debt cleanup, style for code style guidelines, using modern Java features like var and Streams, Error Prone and NullAway integration for code quality, comparison with Cursor's primitive features, branching conversation history, 80% time in Brokk vs 20% in IntelliJ workflow, sketching package structures for AI guidance, data structures guiding algorithms, Git browser by file and commit, unified diff as context, reflection moving away from due to tooling opacity, Jackson serialization refactoring with DTOs, enterprise features like session sync and sharing, unified API key management, rate limit advantages, parallel file processing with upgrade agent, LiteLLM integration for custom models, pricing model based on credits not requests, $20/month subscription with credits, free tier models like Grok 3 Mini and DeepSeek V3, architect mode for autonomous code generation, code button for smaller problems with compile-test loop, ask button for planning complex implementations, senior vs junior programmer AI effectiveness, self-editing capability achieved early in development, no vector search usage despite JVector background

Jonathan Ellis on twitter: @spyced