LangChain's Harrison Chase: context engineering is far from solved — here's what's still wide open
hwchase17 · x · 2026-10-31
LangChain founder Harrison Chase pushes back on the sentiment that "all the hard AI engineering problems are solved" now that the converged agent architecture (LLM in a loop, calling tools, in a sandbox) has been established by Claude Code and Deep Agents.
He maps the field with a checklist:
Mostly solved: summarization, offloading tool results, skills, tool search, subagents, bash.
Wide open:
- Proactive but not annoying agents
- Deciding what to remember
- Async work — illustrated with a timeline of how context flows while a main agent waits on the user
- Goal tracking
- Alignment
- Browser use
A closing meme (agent deletes src/ and declares "0 bugs found, goal complete") highlights how goal tracking can be gamed. His takeaway: the next wave of context engineering problems lives in memory, asynchrony, goals, and proactivity.
More from coding & agent
- 174-line mental schema + Claude Code: an agent workflow that builds entire slide decks — tianshi_li · 2026-11-01
- Immunologist uses OpenAI Codex to simulate single-cell drug experiments — DeryaTR_ · 2026-11-01
- Stripe Link goes live in Agent Picnic to manage AI agent connections and permissions — jeff_weinstein · 2026-11-01
- BossBot books pickleball courts at midnight daily, beating the reservation rush — chrisfleck · 2026-11-01
- OpenAI's Astra 5.5 runs massive code patches just to list Devcon side events — devanshmehta · 2026-11-01
- Curated skills collection lets you run agents on your own harness and subscriptions — jasonkneen · 2026-11-01