Welcome to the Daft blog
Join us as we explore innovative ways to handle multimodal datasets, optimize performance, and simplify your data workflows.
Eventual Raises $30M to Build the Future of Data
Knowledge curation (not search) is the AI big data problem
The next context engineering breakthrough looks a lot less like Google (Information Retrieval) and a lot more like Wikipedia (Knowledge Curation).
How We Use AI Coding Agents
Our engineering team's best practices for working with AI coding agents.
How Sourcetable Built the World's First AI Spreadsheet with Daft
Sourcetable CTO Andy Grosser discusses their data infrastructure choices and why reliability and scale drove their architecture decisions.
Why I Joined Eventual
Sam Stokes on his decision to join Eventual
Processing 99% of U.S. Caselaw for Under $1 in the Common Pile
How Teraflop AI processed 7 million court documents and 40 million pages spanning 365 years of U.S. caselaw for under a dollar using Daft.
Multimodal Structured Outputs: Evaluating VLM Image Understanding at Scale
Leveraging ablation for contrastive image understanding evaluation in Daft
Prompting with DataFrames: Massively Parallel LLM Generation is Here
Structure and scale LLM inference with prompt. A new function for Daft dataframes.
Agentic systems are just query engines for unstructured data
A systems engineer’s view of the new AI stack
Fall 2025 Review: Daft Open Source Updates
Highlights from new AI Functions, updated UDFs, and daft.File upgrades.
Cutting LLM Batch Inference Time in Half: Dynamic Prefix Bucketing at Scale
A new inference backend that maximizes batch inference throughput.
Simplifying Voice AI Analytics with Daft: Transcription, Summaries, and Embeddings at Scale
How Daft simplifies voice AI analytics pipelines for meeting summaries, subtitle translations, and more.
Using PyTorch DataLoaders to Streamline Multimodal Data
Learn how PyTorch's DataLoader streamlines deep learning pipelines by efficiently loading and shuffling data in batches.
