# LangGraph

LangChain released a set of LangSmith features at Interrupt NYC and London so teams can own their intelligence in production. Previously, finding conversations meant relying on traditional filters; AI Search now retrieves traces by semantic understanding, so a team can ask whether a user got frustrated or whether PII leaked. The same update adds Managed Deep Agents v0.9, Engine v2 with red teaming, Trajectories, Custom Apps, and Fine-Tuning, covering how agents are built, understood, and improved.

LangChain released a set of LangSmith features at Interrupt NYC and London so teams can own their intelligence in production. Previously, finding conversations meant relying on traditional filters; AI Search now retrieves traces by semantic understanding, so a team can ask whether a user got frustrated or whether PII leaked. The same update adds Managed Deep Agents v0.9, Engine v2 with red teaming, Trajectories, Custom Apps, and Fine-Tuning, covering how agents are built, understood, and improved.

Enrich.AI turns enrichment analysis from a table of significant terms into a conversation: given a gene list and a short biological context, the agent chooses among more than 220 gene set libraries, over 40 million publications and gene annotation resources, then returns a literature-grounded written interpretation and six interactive plots. Across 50 MSigDB Hallmark gene sets, 65.6% of claims were grounded in retrieved evidence, 2.3% were unsupported, and the hallucination rate on database-decidable claims was 2.64%, with no fabricated citations across 90 runs.

Enrich.AI turns enrichment analysis from a table of significant terms into a conversation: given a gene list and a short biological context, the agent chooses among more than 220 gene set libraries, over 40 million publications and gene annotation resources, then returns a literature-grounded written interpretation and six interactive plots. Across 50 MSigDB Hallmark gene sets, 65.6% of claims were grounded in retrieved evidence, 2.3% were unsupported, and the hallucination rate on database-decidable claims was 2.64%, with no fabricated citations across 90 runs.

The work presents pm4aa, a pipeline that extracts object-centric event logs from GitHub repositories via PyStack't, maps commits to SE tasks with a Conventional Commits regular expression, partitions 589 users into eight roles with a priority-ordered rule classifier, applies object-centric, imperative (BPMN), and declarative (DECLARE) process mining per role, has an LLM generate process descriptions, and synthesizes a LangGraph multi-agent application through IBM BOB; on the Commitizen project (November 2017 to November 2025, 21,488 events, 4,813 objects) it produced five role agents, three smoke tests routed correctly, and a ten-participant user study rated knowledge schema, operational clarity, and human engagement at a median of 4, accountability at 3, and autonomy at only 2.

The work presents pm4aa, a pipeline that extracts object-centric event logs from GitHub repositories via PyStack't, maps commits to SE tasks with a Conventional Commits regular expression, partitions 589 users into eight roles with a priority-ordered rule classifier, applies object-centric, imperative (BPMN), and declarative (DECLARE) process mining per role, has an LLM generate process descriptions, and synthesizes a LangGraph multi-agent application through IBM BOB; on the Commitizen project (November 2017 to November 2025, 21,488 events, 4,813 objects) it produced five role agents, three smoke tests routed correctly, and a ten-participant user study rated knowledge schema, operational clarity, and human engagement at a median of 4, accountability at 3, and autonomy at only 2.