Three weekend Claude Code projects: personal benchmarks, mini-SaaS, AI asset library
EXM7777 · x · 2026-10-21
EXM7777 shares three weekend projects to level up with Claude Code: (1) build your own benchmarking toolkit — prompts + systems + messy real projects, run each new model through your actual work and know within 15 minutes if it's worth switching; (2) build an embarrassingly simple mini-SaaS for each repetitive task, hosted for $2/month just for yourself; (3) create an AI assets library of prompts, context files, MCPs and repos, sorted for instant retrieval. 'These feel like side projects but it's actually the start of a decent infrastructure.'
More from coding & agent
- Research agent Épi sets 120 records, narrows n-queens constant interval 84x — dair_ai · 2026-10-21
- Compaction hooks in practice: keep last n messages verbatim, summarize the rest for full agent continuity — MoonL88537 · 2026-10-21
- The blank prompt box hides real operational burden: context, workflow and supervision fall on users — _AustinCalvert_ · 2026-10-21
- DeepMind paper: self-evolving agents forget as they learn — fastest learner GEPA also breaks old tasks most — rohanpaul_ai · 2026-10-21
- arXiv: Are Self-Evolving Agents Continual Learners? Plasticity comes at the cost of stability — rohanpaul_ai · 2026-10-21
- PM OS vs Team OS vs Company OS: how to layer your AI setup and which to build first — aakashgupta · 2026-10-21