Framework · 2023–2025 · AI Present
Multi-agent orchestration hype
LangGraph, CrewAI, AutoGPT cosplay — agents delegating to agents for tasks one function call could do. Hype peaked; backlash stuck.
Multi-agent frameworks failed as defaults because non-determinism compounds with every hop and observability lagged behind demo videos. They stuck in research and narrow automation where human oversight remains in the loop. By mid-2026 the framework layer faded; the costly fad was autonomous headcount replacement on slide seventeen.
Cost of the fad
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.
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
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 · 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.
Framework · 2023–now
LLM orchestration frameworks
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.