good pattern from this google paper the verifier starts from a clean context, so the explorer's reasoning can't talk it into a bad proof so the explorer can try wild ideas and the verifier tosses the wrong ones same reason deepagents subagents get their own context
@hwchase17
-
LangSmith Custom Apps builds custom review UIs for agent traces
By
–
every agent team ends up wanting its own review ui over their traces – LangSmith Custom Apps lets you build it on your own data and ship it right into the workspace
-
Improving memory in managed deepagents
By
–
Memory is hard to get working well, especially in a company setting
— Harrison Chase (@hwchase17) 2 octobre 2026
Making some improvements to how we memory in managed deepagents! https://t.co/dHRQ2JhRV4Memory is hard to get working well, especially in a company setting Making some improvements to how we memory in managed deepagents!
-
Open-weights decision model class for harness routing and judging
By
–
congrats @AravSrinivas
! more entrants in the decision model class, and this one is open weights cheap typed answers for the small calls inside a harness (routing, approvals, judging), big model for the rest -
Agent harnesses need durable runtimes, mapping pi-durable and langgraph
By
–
pretty clear every agent harness needs a durable runtime pi :: pi-durable deepagents :: langgraph
-
Guide to proper model routing for LLM systems
By
–
model routing – "no one knows what it means, but its provocative, gets the people going" we try to shed light on how to do it properly 1. understand tasks
2. understand the models
3. build the router **in the harness**
4. track outcomes lower costs, with no performance hit -
Deep Agents Course: Task Planning, File Systems, Subagents, Memory
By
–
3hr Long Deep Agents Course Great course from a member of the community on Deep Agents Covers task planning, file systems for context management, subagent-spawning, and long-term memory https://
youtube.com/watch?v=J8DzuM
mSDEU
… -
Deep Agents uses cache-aware requests to reduce costs
By
–
> Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. We do this for you in Deep Agents – see our blog on it here: https://
x.com/its_ao/status/
2070556265906917860?s=20
… -
KV Cache and Prompt Caching for Production AI Agents
By
–
If I had to choose just one metric, I'd argue that the KV-cache hit rate is the single most important metric for a production-stage AI agent. – Manus AI prompt caching is important! read about how we do it with deep agents
