Learn how to build faster, cheaper and smarter agents
Hands-on tutorials, examples, benchmarks, talks and more
Boost performance & reduce cost by self-hosting specialized AI models
Introducing SIE, a multi-model inference cluster for search and document processing workloads, released under Apache 2.0.
A hijacked AI agent still has valid credentials. Check its behavior instead.
Ten model calls per contract review, zero external APIs
PDF-to-Markdown is easy to demo and hard to trust. Here's how to test it.
Trace one restated figure through three SEC filings without losing the source
$182,552 claimed, 15 cubic yards covered: an AI pipeline reads a real FEMA appeal
38°F, 103°F, 253°F: reconstructing the East Palestine bearing failure from the NTSB report
"A red leather handbag": one query, six images built to fool it
Change your NER labels at request time. Retrain nothing.
One month late, payment recouped: reproducing a CMS finding with five models
Test your reranker on documents where wrong answers have consequences
Which price label belongs to the empty shelf gap? Geometry answers, OCR proves it.
Your RAG pipeline can't read a wiring diagram. This one can.
llm-d vs Dynamo vs SIE: Multi-Model Serving Compared
SIE vs TEI (Text Embedding Inference): Benchmarks, Cost, Setup
SIE vs vLLM: Which Should You Deploy for Multi-Model Workloads?
vLLM vs SGLang vs SIE for Production Search Pipelines
Should You Self-Host Inference?
A Practical Guide for Choosing Models for Your AI Agents
Top 6 Open-Source Alternatives to Hosted OCR APIs (Azure Document Intelligence, AWS Textract)
Best OpenAI Embeddings Alternatives You Can Run in Your Own Cloud
How to serve private document tools to any LLM with the SIE MCP server
5 AI Agents You Can Build in 5 Minutes
SIE vs hosted embedding APIs: ~97% of the quality at ~1/12th the cost
One GPU, Four Retrieval Modes: How to Serve Hybrid Search Without Four Separate Deployments
Self-hosted search inference with SIE
Self-hosted document processing for AI agents, with SIE
Why Are My Token Costs Going Up? How Open Source Inference Keeps Them Down
How to Cut Token Usage and Costs in AI Search and Agents (Without Throwing More GPUs at It)
How to make AI agent infrastructure portable across AWS, GCP, Azure, and customer clouds
Building production inference: routing, batching, model configs, and LoRA in one cluster
Hundreds of models, one deployment: how to kill the server-per-model sprawl
How to choose an inference layer for agents: vLLM, SGLang, TEI, Triton, KServe, and SIE
What is the best alternative to OpenAI and Anthropic APIs for running agent workloads?
How to Route Different AI Agent Tasks to the Right Model
My agent is dumb: how to route each task to the right model (and make it smarter)
Building agents: run embeddings, reranking, and extraction from one inference stack
What small open source models can handle real AI agent tasks?
Building an Agentic NLQ System for Real Estate Search
Improving RAG with RAPTOR
Evaluating Retrieval Augmented Generation using RAGAS
An evaluation of Retrieval Chunking Methods for Inference Systems
Semantic Chunking
A Practical Guide for Choosing a Vector Database
Optimizing RAG with Hybrid Search & Reranking
Vector Embeddings in the Browser