Tag
The author argues that the reliability of AI agents comes from deterministic code, not the LLM, and shares five key practices for building trustworthy agents on messy real-world data.
Perplexity Brain is a memory system that builds a persistent context graph across tasks, projects, decisions, files, and sources, enabling agents to start with relevant context instead of from scratch, improving answer correctness and reducing task costs.
Jedify raised $24M in Series A funding to develop a context graph platform that connects enterprise knowledge sources (databases, Slack, etc.) so AI agents can better understand business-specific data and permissions.
Glean reaches $300M ARR, a three-fold increase in 15 months, as it leverages its context graph to help enterprises cut AI costs. The company faces growing competition from tech giants like Google and Microsoft, but emphasizes its deep understanding of customers' business needs as a differentiator.