Tag
A personal account of five key lessons from building an AI consulting company, covering practical advice and insights for entrepreneurs in the AI space.
A CEO shares practical lessons from running a company with 89 AI agents across 22 departments, highlighting delegation as the bottleneck, the value of agent memory, the need for department structure, and the continued importance of human leadership.
Stanford's Hacking for Defense class concluded its 11th year with lessons learned presentations from 9 teams addressing national security problems, incorporating AI tools and customer development methodologies.
A discussion query asking developers how they handle recovery when AI agents crash mid-task in production, exploring approaches like restarting, persisting state, using checkpoints, or manual inspection.
A developer shares that reducing an agent's context window by half unexpectedly improved its performance in lead qualification and CRM automation, suggesting that too much context can hide bad architecture and lead to indecision.
A technical blog post detailing the author's journey building an agentic micro-orchestrator for an open-source project, exploring patterns, market gaps, and the event sourcing data architecture for complex agentic workflows.
Cursor shares key lessons from building cloud agents, emphasizing that providing a full development environment is critical for agent output quality, and that long-running agents require durable execution and enterprise-like infrastructure.
A comprehensive overview of twenty years of Arabic NLP research, discussing lessons, failures, and open problems in the field.
Wasp, a full-stack web framework startup, reflects on the mistake of creating a custom programming language for web development after 5 years and $5M in funding, and announces they are replacing it with TypeScript.
The author shares notes and lessons learned from building AI agents at scale, focusing on RAG and memory management to help others.