AI replaces engineering

Big-bang rewrite, now with a chatbot — then with agents. Same failure mode; prettier slides.

$ 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.

Autocomplete that understands the file — now table stakes. Generation outran review capacity; ownership is the bottleneck.

LangChain-class glue gave way to vendor SDKs and thin wrappers. The durable pieces are boring: evals, retrieval, and product UX.

Drag-and-drop apps for the enterprise backlog. Useful for internal tools; fantasy as a full replacement for engineering — a pitch later absorbed by AI demos.

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.

Give the model a goal and a credit card. Viral in 2023; quietly shelved when the loop never stopped spending.

$ Open-ended agent loops burned API credits chasing goals nobody specified well enough to finish. Demo videos outpaced production deployments by orders of magnitude.

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.

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.

Craft the magic string until the model behaves. Job title of 2023; table-stakes skill of 2026.

Chains, tools, memory, and agents as a framework — LangChain-class glue sold as architecture. By 2026: LangChain-fatigue and thinner SDKs.

$ Teams adopted chain/agent frameworks before they had a single reliable tool call. Abstraction layers multiplied while prompt quality stayed flat.

Slap an LLM on the homepage and call it AI-native — "we have an app now," 2010 edition.

$ Homepage chat boxes billed as AI-native platforms while the roadmap stayed FAQ search with a spinner. Acquisition decks outpaced retention.

Prod data into consumer chat because the approved tool is slow. GDPR with better autocomplete.

$ Employees routed tickets, logs, and customer PII through consumer chat before InfoSec finished procurement. Compliance scramble followed the demos.

Coverage theater with a chat box. Tests that mirror the bug and never catch it.

$ LLMs wrote tests that boosted coverage and asserted nothing. Green CI, false confidence — eval theater's cousin in the test suite.

LLM evals as slideware — metrics that look scientific and never gate a deploy. The foil to real eval pipelines in CI.

$ Dashboards of vibe-check scores that never blocked a release. Green charts for leadership; prod still hallucinated.

Copilot ships PRs faster than teams can review. Generation outran ownership and security review — the real 2026 invoice.