The NxtFruit blog
Notes from
the build.
Insights on AI development, technology choices and business outcomes, from the engineers who do the work.
AI Development
AI Context Reduction: What a 98% Cut Costs You
A tool claiming 98% less context use made us re-examine our own retrieval. Here's how context reduction actually works — and the one axis where their approach beats ours.
· 6 min read
AI Development
Meta’s Muse Code and Muse Spark 1.2: Meta Graded Its Own Benchmark
Meta entered the AI coding wars with Muse Code and Muse Spark 1.2. We went looking for the independently verified benchmarks, found none, and worked out what the harness-coupled headline score really means before touching our routing.
· 5 min read
AI Development
AI Slop Design: Why Every AI Landing Page Looks the Same
Every AI-generated landing page converges on the same skeleton. Evaluating an anti-slop skill exposed the fixed template hiding in our own pipeline — and the archetype fix that ended it.
· 5 min read
AI Development
What Are Claws? The Always-On Layer Above AI Agents
Karpathy's "Claws" describes an always-on layer above LLM agents. We already run one — here's what the idea gets right, and the feature we refused to ship.
· 6 min read
AI Development
When AI Coding Agents Skip Their Own Tests
A viral engineering essay reminded us how easily an AI coding agent can "pass" a test by skipping it. We audited our own platform, found the gap, and fixed it.
· 7 min read
AI Development
Agentic Workflow Platform vs. Autonomous Code Generation
Dify is a strong agentic workflow platform — but it solves a different problem than autonomous code generation. Here's how we evaluated both and how to choose.
· 5 min read
AI Development
AI Coding Token Costs: Why Cutting Tokens Can Cost You Quality
Token-reduction tools promise 60–90% fewer tokens on AI coding, but cutting tokens isn't the same as saving money. Here's why signal per token — not raw token count — is the metric that actually protects quality.
· 7 min read
AI Development
Can AI-Generated Code Leak Your Secrets? The Fail-Open Gap We Found
Our AI development platform once pushed a live API key - despite having a secret scanner. The fail-open gap we found, and the fail-closed fix any AI pipeline can copy.
· 7 min read
AI Development
Multi-Agent AI: How Super-Agent Systems Actually Work
Multi-agent AI systems split work across a lead and sub-agents with isolated context. We build software this way — here's how super-agent harnesses really work and where the design choices matter.
· 5 min read