Podcast Deep Dive: How to Build Long-Horizon AI Agents
mattturck · x · 2026-08-07
Podcast host Matt Turck and Mitch Troy, co-founder of Basis, dive deep into the methodology of building long-horizon AI agents. The conversation covers core technical elements such as behavior specs, ontologies, and process supervision.
Key discussion points include:
- Defining Long-Horizon Agents: What makes an agent truly capable of handling multi-day complex tasks.
- Case Study: An inside look at an autonomous agent handling multi-day tax returns.
- Economic Perspective: Viewing accounting as 'an intelligence over the economy'.
Related event: Deep Dive into Building Long-Horizon AI Agents(2 posts)→
More from coding & agent
- Naïve Raises $28.5M Series A to Build Infrastructure for Autonomous AI Agents — ycombinator · 2026-08-07
- Cloudflare Launches Kitesurf: A Lightweight Browser Built for AI Agents — craigsdennis · 2026-08-07
- Seeking Open-Source Harnesses for Seamless Cloud and Local LLM Orchestration — tat_tvam_asshole · 2026-08-07
- LangSmith Gateway Integrates Kimi K3 for Agent Execution — LangChain · 2026-08-07
- AI Alone Won't Boost Productivity: The Shift from Prompting to Automating Systems — Rahul_Chouhan · 2026-08-07
- Cognition & OpenRouter on Model Routing: Why Naive Task Routing Fails for Agents — AI Engineer · 2026-08-07