LangChain founder: agents are shifting from executing tasks to owning goals
hwchase17 · x · 2026-11-17
LangChain founder Harrison Chase argues that as agents grow more capable, the interface is shifting from assigning tasks to delegating goals.
- Tasks are bounded actions ("fix this bug") with a done state; goals are ongoing outcomes ("maintain a blog", "reduce my coordination burden") with no completion point.
- Two practical shifts underpin this: from specifying an action to specifying an outcome, and from a bounded assignment to an ongoing responsibility.
- In goal mode, the agent itself brainstorms, selects and updates its own task list, working in the background while the user approves key decisions via an inbox (Slack or dedicated UI).
- Accompanying diagrams contrast task vs. goal architectures, showing goal agents with layered permissions (allowed / needs approval / blocked) across tools.
Chase says this changes what an agent does, what it needs, how it's built, and how we interact with it.
Related event: LangChain founder proposes Goal Engineering for the agent era(2 posts)→
More from AGI Musings
- Ben Bajarin: enterprise AI adoption is the only conviction that matters for the decade — BenBajarin · 2026-11-17
- Paul Christiano: 1-in-3 chance of government-toppling superintelligence within a year — Dwarkesh Patel · 2026-11-17
- Sam Altman on stage: "We didn't have AGI. Now we do" — and OpenAI is withholding self-improving AI — imjustnewatai · 2026-11-17
- Vik Paruchuri: Even Experts Struggle to Tell Good Benchmarks from Bad Ones — VikParuchuri · 2026-11-17
- Report: US Has 9x China's Compute, So It Can Afford to Pace the AI Frontier — trevposts · 2026-11-17
- Open-source models now serve 30% of tokens, growing as fast as closed frontier AI — ivan_bezdomny · 2026-11-17