New series this week: how to use middleware to customize your agent harness! Case 1: business logic and compliance Many agents need a combination of agentic and deterministic steps. For example, your application might require PII redaction to run on any inputs before they're sent to a model. You can use Langchain's builtin PIIMiddleware to mask/redact/hash/block PII, or build your own custom middleware for other compliance needs.
any medical pii reductions for hippa compliance?
Wow! Last year I invented this by my own to hide Sensitive Coustomer information with the tools for langgraph and today we have this..! No doubt langchain is doing great.
#Langchain has been streamlining the agent-building process, making complex workflows much more manageable.
PII rules are a good start but a semantic layer on top, where the agent evaluates its own output in context, catches the stuff regex never will.
Great news! Increasing privacy is a great step!
Nice
Is built in middleware for the create_agent module specifically or does it work with custom agents built directly with langgraph?