LangChain DeepAgents adds Harness Profiles

// 2h agoPRODUCT UPDATE

LangChain DeepAgents adds Harness Profiles

LangChain DeepAgents has introduced Harness Profiles, a declarative configuration layer that enables developers to customize LLM runtime behaviors by automatically applying model-specific prompts, system instructions, and tool sets. This allows applications to swap models dynamically—such as replacing complex file editing tools with patching tools for specific models—without altering the core agent architecture.

// ANALYSIS

Tailoring prompts and tool subsets dynamically per model is a crucial milestone for building reliable, production-grade multi-model agents.

–**Model Optimization:** Prevents model failure by limiting weaker or different models to only the tools they can reliably handle.
–**Modular Architecture:** Decouples core agent execution code from prompt engineering and configuration settings.
–**Heterogeneous Model Support:** Eases the integration of diverse API models by handling their structural differences automatically at runtime.

// TAGS

langchaindeepagentsagentllm-orchestrationtool-use

DISCOVERED

2h ago

2026-06-12

PUBLISHED

2h ago

2026-06-12

RELEVANCE

8/ 10

AUTHOR

masondrxy

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

BENCHMARK52m ago

GPT-5.6 excels on DeepSWE coding benchmark

A shared screenshot from Datacurve's latest DeepSWE benchmark indicates significant reasoning and coding execution improvements in OpenAI's upcoming GPT-5.6 model compared to previous models. DeepSWE measures AI coding agent capabilities on long-horizon, multi-file software engineering tasks under strict sandbox environments.

NEWS55m ago

Microsoft, AWS flag Claude Fable 5 retention

Anthropic's newly introduced data retention policy for its Claude Fable 5 model has drawn flags from major cloud partners Microsoft and AWS, leading to a rollback in adoption by enterprise customers. The policy mandates a 30-day retention period for all prompts and outputs across all platforms and surfaces, including AWS Bedrock, raising security and privacy concerns among corporate clients who require strict data confidentiality.

TUTORIAL57m ago

ElevenLabs hosts Self Publishing Show audiobook workshop

ElevenLabs is running a live workshop at the Self Publishing Show, focusing on how authors can create and distribute audiobooks from scratch. The hands-on session covers auditioning AI voices, importing and editing manuscripts using ElevenLabs' creative suite, and publishing the final product directly onto the ElevenReader app.