Building Production-Grade Long-Running Agents with Agent Harnesses with LangChain
'Gradient Descending' is a series of roundtables on AI: curated deep dives with technical builders. Past roundtables discussions covered RL Environments, Evals, Fine-Tuning, Agent Frameworks, Open Source Models, and Knowledge Graphs with companies like OpenAI, Anthropic, Cursor, Scale AI and many more.
For this session, we’re joined by Steffen Hausmann for a technical discussion on agent harnesses: how they came to exist, the problems they solve, and why they’re becoming an important abstraction for building reliable AI agents.
We’ll also dive into the open-source Deep Agents SDK as one concrete implementation of an agent harness, unpack the key technical design choices and tradeoffs, and close with a short demo showing how to get started quickly.
Expect an honest discussion with a curated group of founders and operators building in AI.
Agenda:
Arrivals: 08:30–09:00
Roundtable discussion: 09:00–10:00
See past roundtables here:
https://www.akashbajwa.co/t/ai-roundtables
https://laurinclass.substack.com/
I agree that photographs and/or video may be taken during the event and used by the hosts on social media and in future promotional materials.