Practice · 2023–now · AI Present
AI will rewrite the codebase
Big-bang rewrite, now with a chatbot — then with agents. Same failure mode; prettier slides.
AI rewrites fail for the same reasons manual ones do: unknown edge cases, missing tests, and political ownership of legacy modules. LLMs accelerate typing, not accountability. Strangler migrations still win; autopilot and agentic-migration slides still lie.
Cost of the fad
Exec decks promised autonomous migrations "by next quarter," then rebranded as "agentic modernization." Teams that skipped tests, ownership, and incremental strangler patterns bought expensive demos and fragile diffs.
Case studies
Patterns
Context
Demos consolidate; evals remain
AI pair programming changed how code is typed faster than how it is reviewed. Agent frameworks and standalone vector stores sorted into demos versus durable plumbing; mid-market RAG folded back into Postgres. The permanent layer is familiar: evals that gate deploys, model routing for cost, tool protocols instead of plugin snowflakes, and humans who own production. Autopilot rewrites and vibe-shipped auth middleware are still big-bang migrations with better slides — and a longer on-call.
Compare with
Related
Practice · 1995–now
Big-bang rewrite
Replace the working system instead of strangling it. A perennial money pit with new branding each decade.
$ "We'll freeze features and rewrite in the hot language." Multi-year projects shipped late, incomplete, or not at all — while competitors iterated on the ugly system that made money.
Framework · 2023–now
LLM app frameworks
LangChain-class glue gave way to vendor SDKs and thin wrappers. The durable pieces are boring: evals, retrieval, and product UX.
Practice · 2021–now
AI pair programming
Autocomplete that understands the file — now table stakes. Generation outran review capacity; ownership is the bottleneck.
Practice · 2024–now
Vibe coding
Accept AI output on feel, skip the diff, hope tests exist. Fast demos; CVEs and nobody owns the middleware.
$ Ship-to-prod without reading the diff became a flex until incidents revealed nobody knew which prompt wrote the auth middleware. Review debt arrived in one weekend demo.
Framework · 2023–2025
Multi-agent orchestration hype
LangGraph, CrewAI, AutoGPT cosplay — agents delegating to agents for tasks one function call could do. Hype peaked; backlash stuck.
$ Autonomous agent swarms burned API budgets on coordination loops that a single prompt and a cron job would have handled. Debugging "which agent lied" became the new on-call sport.