Topic
Deep Agents
9 episodes
-
How many of your agent's calls actually need a frontier model?
Jessica and Cathy debate the real payoff of model routing for AI agents: is it worth the complexity, or is a single strong open model usually enough? Cathy questions whether the claimed cost savings from routing justify the judge model's price and complexity, given only a modest accuracy gain. Jessica pushes the product case for routing when you can't risk wrong answers on hard tasks, insisting most teams can't rely on just a cheap model if real mistakes are expensive. Together, they find the real value is in knowing—by measurement—when routing pays, and agree that for some teams, the bar is higher than the hype suggests.
-
Managed Deep Agents is now in public beta
Jessica and Cathy discuss LangSmith Managed Deep Agents entering public beta, exploring its value for shipping agents without managing infrastructure, its open-source harness, and how it fits into the broader agent landscape including Anthropic's competing offering.
-
Deep Agents v0
Deep Agents v0.7 ships a sixty-five percent token reduction by stripping the base system prompt, trimming tool descriptions, and making TodoListMiddleware opt-in — Masonry and Eyre dig into what the harness-gets-simpler pattern actually means in practice, where the Sonnet cost anomaly is a warning sign, and why configurability was the real missing piece.
-
Interpreters in Deep Agents: Code Between Tool Calls and Sandboxes
Justy and Cody dig into the argument for adding interpreters inside agent loops: a middle layer between serial tool calls and full sandboxes that lets models compose tools, keep live state, and ship less context around. They talk through why that’s practically useful, where the early token savings matter, and where the claim gets fuzzy if you assume an interpreter can replace real environments.
-
LangSmith Sandboxes are Generally Available
Cody leads a skeptical read of LangSmith Sandboxes going GA — questioning whether microVM isolation is genuinely new or just well-packaged infrastructure. Justy pushes back on who actually needs this and why it matters for teams shipping real agent workflows. They land somewhere honest: the security argument holds, but the moat question is real.
-
New in Deep Agents v0
Justy and Cody chat in their kitchen about Deep Agents v0.6, highlighting open‑weight cost cuts, Delta channels, new streaming, and the handy code interpreter. They riff on how to jump‑start a weekend project and point to the Context Hub integration for learning agents.
-
Tuning Deep Agents to Work Well with Different Models
Justy and Cody dig into LangChain’s new Deep Agents model-specific harness profiles. Cody is skeptical that prompt-and-tool tuning is a durable win, while Justy sees a practical adoption path for builders who keep hitting model-specific quirks. They land on a cautious take: useful, real, and probably underappreciated, but not magic.
-
How to Use Memory in Agent Builder
LangChain's Agent Builder uses filesystem-based memory to get smarter over time, storing both short-term task context and long-term instructions as Markdown files. The system includes specialized 'skills' that load contextually and supports direct memory editing for fine-tuned control.
-
Deep Agents overview Docs by LangChain
Explore the capabilities of Deep Agents in LangChain, a powerful tool for building specialized agents capable of handling complex tasks with planning and context management.