Agent APIs Are Becoming Runtime Contracts
For the last year, if you were building anything serious with agents, you spent most of your time building everything that was not the…
Tag
AI Infrastructure
posts
9
Vector Databases: Choose the Failure Mode, Not the Benchmark
You are choosing a vector database, so you open the comparison charts. Most of them have one, and it tends to show the publisher…
Coding Agents Are Runtimes. Evaluate Them Like One
Most teams still evaluate coding agents with one question. Can it write the code? That question made sense when the product was autocomplete. You…
Model Escalation Is a Tool Call
On June 10, 2026, OpenRouter announced Advisor, a server-side tool that lets one model consult another model mid-generation. The obvious reading is cost optimization.…
The Agent That Finishes Is the One to Worry About
Most agent failures are easy to recognize. The tool call fails. The browser times out. The code does not compile. The agent loops. The…
Reranking and the Recall You Throw Away
You added a reranker because retrieval quality was not good enough. The relevant passage kept landing at rank eight when it should have been…
Chunking Is Where RAG Silently Fails
You have tuned everything. A better embedding model, a reranker, hybrid search. Retrieval quality is still not what it should be, and you cannot…
Embedding Drift: Why Changing Your Model Re-Indexes Everything
You upgrade your embedding model. The new one benchmarks better, so you point your pipeline at it, ship it, and within a day retrieval…
The Hidden Architecture Behind Dense Vector Search (and Why It’s Hard to Scale)
Most people think dense vector search works like this: embed your documents store the vectors run cosine similarity Done. This is the biggest misunderstanding…