cgft - rlft on your data

outperform frontier models on dimensions that matters. rlft custom models on your proprietary data.

castform - the training platform for the ai engineer train models that rival the frontier, at open source cost post-train, evaluate, and ship task-specific models start training book demo import data define tools & rewards monitor training beat the frontier rag corpus agent traces show code from benchmax . rag . qa_generation . pipeline import Pipeline from benchmax . rag . qa_generation . pipeline_config import PipelineConfig , PlatformConfig from benchmax . rag . corpus . postgres . source import PostgresChunkSource # supports turbopuffer, pinecone, chroma, postgres source = PostgresChunkSou

saved by

• Karthik Suresh

related reading

• A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
• Patterns for Building LLM-based Systems & Productseugeneyan.com
• Langfuselangfuse.com
• Why We Built Our Own Background Agentbuilders.ramp.com
• AI Engineering from Scratchaiengineeringfromscratch.com
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• LangChain: the open agent platform to own your intelligencelangchain.com
• Inference Platform: Deploy AI models in production | Basetenbaseten.co
• GitHub - deepset-ai/haystack: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.github.com
• Expert Data for Frontier AI - AfterQueryafterquery.com
• Llama 2 · Hugging Facehuggingface.co
• Contextcontext.ai