Practice · 2023–2024 · AI Present
AutoGPT-class autonomous agents
Give the model a goal and a credit card. Viral in 2023; quietly shelved when the loop never stopped spending.
AutoGPT-class agents failed because open-ended autonomy without evals, budgets, or tool reliability produces expensive wanderlust. Narrow copilots stuck; fully autonomous rewrite/ops agents did not. The fad sold headcount replacement; the residue is constrained tool-use with a human in the loop.
Cost of the fad
Open-ended agent loops burned API credits chasing goals nobody specified well enough to finish. Demo videos outpaced production deployments by orders of magnitude.
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
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.
Practice · 2023–now
AI will rewrite the codebase
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.
Practice · 2023–now
Agent ops / LLM observability
Tracing, cost caps, and prompt versioning for production LLM features — mostly constrained tool loops, not autonomous agents. Datadog for tokens.
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.