Harrison Chase: Owning Your Intelligence with Agents
hwchase17 · x · 2026-08-18
LangChain founder Harrison Chase shared engineering insights on building agents, emphasizing "owning your intelligence":
Core Formula: Agent = Model + Harness + Context
- Model: Own the weights (e.g., via FireworksAI).
- Context: Memory needs to be portable.
- Harness: Must be model-agnostic and skilled at bringing the right context to the LLM. An open/configurable harness is key.
Implementation:
- Use middleware in LangChain/DeepAgents to configure the harness.
- Use LangGraph to fully own your cognitive architecture.
- Highlights the importance of evals and observability.
More from coding & agent
- Automating a personal knowledge base with Claude: a minimal agent workflow — anirbanbandyo · 2026-08-18
- Claude Code 2.1.234 Released: GitLab Integration, Security Fixes, and CLI Enhancements — ClaudeCodeLog · 2026-08-18
- Supastarter Launches AI-Native SaaS Boilerplate with Agent Skills — jonathan_wilke · 2026-08-18
- Building an E2E testing framework for agents deploying real infra to Cloudflare — samgoodwin89 · 2026-08-18
- Open-Source Pi Plugin Rewrites AI-Speak Into Plain Human Language — wtfzambo · 2026-08-18
- ByteDance Paper: Are AI Agents Actually Controllable? — rohanpaul_ai · 2026-08-18