I love that agent engineering keeps getting new weird problems as these things evolve
@hwchase17
-
Framework Traces a Shift From Coding Agents to Company Operating Systems
By
–
Coding agents (Claude code, codex) -> personal agents (instinct, muse) -> companyOS (???)
-
Harness Based Model Routing Uses Task Context
By
–
router lives in the harness, not a gateway, bc the harness knows the task blog: https://
langchain.com/blog/how-to-bu
ild-a-model-router-in-the-harness
… -
Deepagents Explores Asynchronous Subagent Completion Notifications
By
–
we are thinking a lot about how to make deepagents more async native. specifically about making async subagents work better/more prominent one key question is how does a finished subagent "notify" the parent agent? some default behaviors we're considering for when the parent is
-
Managed Deep Agents combines durable workflows computer use and sandboxes
By
–
this is the summary slide that describes how all agents in the future will look
— Harrison Chase (@hwchase17) 11 octobre 2026
very much aligns with our vision for managed deepagents https://t.co/bXc78RL145
durable workflows: builds on LangGraph/LSD https://t.co/uWayApPuuV
can use a computer: uses Langsmith Sandboxes… https://t.co/FivPNMTJ8Q pic.twitter.com/CR2YKJoPjMthis is the summary slide that describes how all agents in the future will look very much aligns with our vision for managed deepagents https://
docs.langchain.com/langsmith/pyth
on/managed-deep-agents-overview
… durable workflows: builds on LangGraph/LSD https://
docs.langchain.com/langsmith/depl
oyment
… can use a computer: uses Langsmith Sandboxes -
Internal agents’ proactive work raises delegated identity design questions
By
–
historically, most of our internal agents (openswe for coding, gtm agent for outreach) have acted "on behalf of" whoever is using them but as they start to do more proactive, background work… I wonder if that should change. eg i really like the idea Hone put forward of agents
-
Developers weigh credential models for internal enterprise agents
By
–
what is the future of building internal company agents? how will their identity work? 1. fixed set of credentials
2. "on behalf of" flow (uses credentials of whoever is using it)
3. some fixed credentials, others "on behalf of" -
Open SWE model routing reportedly cuts median task costs by 64%
By
–
agree – most orchestration steps don't need a frontier model for Open SWE we moved model choice into the harness, so each task goes to the cheapest model that still does the job, tested against quality. median cost per task dropped 64% https://
langchain.com/blog/how-to-bu
ild-a-model-router-in-the-harness
… -
Jev handles calibrated binary decisions inside agent harnesses
By
–
good framing from @ch3nweiii – a lot of agent steps are yes/no calls, not generation
— Harrison Chase (@hwchase17) 10 octobre 2026
Jev answers those as typed questions with calibrated probabilities, so the frontier model sticks to the hard work
where those calls sit in a harness: https://t.co/TgYoOiLc7F…good framing from @ch3nweiii – a lot of agent steps are yes/no calls, not generation Jev answers those as typed questions with calibrated probabilities, so the frontier model sticks to the hard work where those calls sit in a harness: https://
langchain.com/blog/building-
a-harness-with-jev
… -
Goodhart’s Law Complicates Evaluation Driven Development for Autonomous Agents
By
–
This is great point Goodharts law: when a measure becomes a target, it ceases to be a good measure Initial take: eval driven development works for narrowly scoped things, but for more autonomous agents it doesn’t So then – how do you hill climb those?