Practice · 2024–now · AI Present
AI stack consolidation
Seventeen LLM wrappers to three vendors, one observability bill, and orchestration repos becoming MCP clients. Hype cycle entering boring procurement.
How AI stack consolidation mutated
AI stack consolidation mutated because enterprises cannot maintain a new framework every quarter and model APIs commoditized. The fad layer — bespoke chains per team — is dying; the stuck layer — evals, guardrails, data pipelines, and a vendor harness — is becoming table stakes. Winners look like platforms; losers look like last year's YC batch.
Compare with
Related
Framework · 2023–now
LLM app frameworks
LangChain-class glue mutated into MCP clients and thin wrappers around vendor APIs. The durable pieces are still boring: evals, retrieval, and product UX.
Practice · 2023–now
LLM eval pipelines
Regression tests for nondeterministic models that actually fail the build. The unglamorous CI that separates demos from products.
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.
Platform · 2025–now
Vendor agent APIs
The Codex/Claude loop as a product SKU — durable sessions, compaction, subagents, and a sandbox you do not own.
$ Teams replaced a weekend of LangGraph glue with a managed session API, then discovered residency, recovery, and kill switches all live on the vendor side of the harness.