# Talking Shop **URL:** https://forum.langchain.com/c/talking-shop/12.md?page=2 [Latest](https://forum.langchain.com/latest.md) · [Categories](https://forum.langchain.com/categories.md) · [Tags](https://forum.langchain.com/tags.md) **Page:** 3 --- ## [Beginner questions & Troubleshooting: RAG Best practices for Mail Automation](https://forum.langchain.com/t/beginner-questions-troubleshooting-rag-best-practices-for-mail-automation/3818)
**Author:** [@KyroSaru](https://forum.langchain.com/u/KyroSaru)\ **Replies:** 1\ **Last updated:** [June 1, 2026, 8:13pm UTC](https://forum.langchain.com/t/beginner-questions-troubleshooting-rag-best-practices-for-mail-automation/3818 "2026-06-01T20:13:44Z")
Hi! I am quite new to the world of LLMs and AI. Because of the current information overload on the web (contradictory advice, outdated documentation, etc.), I am struggling to separate the signal from the noise and find… --- ## [Research: Friction Points in Agentic Commerce Transactions](https://forum.langchain.com/t/research-friction-points-in-agentic-commerce-transactions/3580)
**Author:** [@murdockagents](https://forum.langchain.com/u/murdockagents)\ **Replies:** 2\ **Last updated:** [May 12, 2026, 2:03am UTC](https://forum.langchain.com/t/research-friction-points-in-agentic-commerce-transactions/3580 "2026-05-12T02:03:06Z")
Hey LangChain community, I’m researching the friction points in agentic commerce. Given how many agents are built on LangChain, what do you see as the biggest hurdle for developers trying to enable agents to execute real… --- ## [The x402 illusion: Is advertising dead in the age of agents?](https://forum.langchain.com/t/the-x402-illusion-is-advertising-dead-in-the-age-of-agents/3711)
**Author:** [@Tim](https://forum.langchain.com/u/Tim)\ **Replies:** 0\ **Last updated:** [May 11, 2026, 10:57pm UTC](https://forum.langchain.com/t/the-x402-illusion-is-advertising-dead-in-the-age-of-agents/3711 "2026-05-11T22:57:33Z")
Soon, the vast majority of internet traffic won’t come from humans anymore—it will be driven by personal agents. But agents act rationally. They don’t click banner ads, and they aren’t swayed by flashy pop-ups. Does thi… --- ## [Would pre-inference routing help long-context agent workflows?](https://forum.langchain.com/t/would-pre-inference-routing-help-long-context-agent-workflows/3695)
**Author:** [@simanggu](https://forum.langchain.com/u/simanggu)\ **Replies:** 7\ **Last updated:** [May 11, 2026, 8:11pm UTC](https://forum.langchain.com/t/would-pre-inference-routing-help-long-context-agent-workflows/3695 "2026-05-11T20:11:18Z")
Hi everyone, I’m testing a small pre-inference controller for long-context LLM / agent sessions, and I’d love feedback from people building LangChain-style agent workflows. The idea is to run a lightweight controller b… --- ## [Protecting LangChain agent memory from poisoning attacks — OWASP Agent Memory Guard (open source)](https://forum.langchain.com/t/protecting-langchain-agent-memory-from-poisoning-attacks-owasp-agent-memory-guard-open-source/3707)
**Author:** [@vgudur-dev](https://forum.langchain.com/u/vgudur-dev)\ **Replies:** 0\ **Last updated:** [May 11, 2026, 12:48am UTC](https://forum.langchain.com/t/protecting-langchain-agent-memory-from-poisoning-attacks-owasp-agent-memory-guard-open-source/3707 "2026-05-11T00:48:55Z")
Hey LangChain community, I wanted to share an open-source security tool I’ve been building under OWASP that directly addresses a growing threat for LangChain-based agents: memory poisoning attacks. When your LangChain … --- ## [Follow-up: The Moltbook question just got very real — Meta acquisition and open agent identity standards](https://forum.langchain.com/t/follow-up-the-moltbook-question-just-got-very-real-meta-acquisition-and-open-agent-identity-standards/3227)
**Author:** [@rowanseerwald](https://forum.langchain.com/u/rowanseerwald)\ **Replies:** 2\ **Last updated:** [May 10, 2026, 7:12am UTC](https://forum.langchain.com/t/follow-up-the-moltbook-question-just-got-very-real-meta-acquisition-and-open-agent-identity-standards/3227 "2026-05-10T07:12:25Z")
Back in February I posted here about AI-to-AI ecosystems and Moltbook. A lot has happened since. On March 10, Meta acquired Moltbook. VP Vishal Shah described their approach as “a registry where agents are verified a… --- ## [Are dynamic tool lists allowed when using create\_agent?](https://forum.langchain.com/t/are-dynamic-tool-lists-allowed-when-using-create-agent/1920)
**Author:** [@Batiste](https://forum.langchain.com/u/Batiste)\ **Replies:** 16\ **Last updated:** [May 8, 2026, 1:13pm UTC](https://forum.langchain.com/t/are-dynamic-tool-lists-allowed-when-using-create-agent/1920 "2026-05-08T13:13:44Z")
Hi, I’m trying to make create\_agent work a bit like Claude Skills, where the agent can discover tools when loading skill\_tools (which are basically a long string with instructions + add new tools to its list). But it se… --- ## [How are people handling data governance across agent handoffs in production?](https://forum.langchain.com/t/how-are-people-handling-data-governance-across-agent-handoffs-in-production/3602)
**Author:** [@Abhay-2222](https://forum.langchain.com/u/Abhay-2222)\ **Replies:** 3\ **Last updated:** [May 7, 2026, 7:47pm UTC](https://forum.langchain.com/t/how-are-people-handling-data-governance-across-agent-handoffs-in-production/3602 "2026-05-07T19:47:58Z")
Hi All, I have been researching something that kept coming up while studying multi-agent pipelines in regulated industries. Every current observability tool watches what your AI system says to the user. Nobody watches w… --- ## [Cross-site pattern pool for production agent failures — looking for 5 pilot teams (open spec, CC-BY-4.0)](https://forum.langchain.com/t/cross-site-pattern-pool-for-production-agent-failures-looking-for-5-pilot-teams-open-spec-cc-by-4-0/3654)
**Author:** [@Uzun](https://forum.langchain.com/u/Uzun)\ **Replies:** 0\ **Last updated:** [May 4, 2026, 1:56pm UTC](https://forum.langchain.com/t/cross-site-pattern-pool-for-production-agent-failures-looking-for-5-pilot-teams-open-spec-cc-by-4-0/3654 "2026-05-04T13:56:27Z")
Building a cross-site pattern pool for production AI agent failures. The model: connected sites push agent reports (warnings, learned\_patterns, runtime events); each site gets back patterns filtered to their specific sta… --- ## [Ombre — open source security and audit layer for LangChain apps](https://forum.langchain.com/t/ombre-open-source-security-and-audit-layer-for-langchain-apps/3614)
**Author:** [@pypl0](https://forum.langchain.com/u/pypl0)\ **Replies:** 0\ **Last updated:** [April 28, 2026, 2:15pm UTC](https://forum.langchain.com/t/ombre-open-source-security-and-audit-layer-for-langchain-apps/3614 "2026-04-28T14:15:34Z")
Hey LangChain community, Built Ombre — an open source infrastructure layer that adds security, caching, and audit logging to any LangChain application. What it adds: - Blocks prompt injection before it reaches your c… --- ## [3 agent integration patterns for claim verification (verify-then-act, decompose-and-score, multi-agent supervisor)](https://forum.langchain.com/t/3-agent-integration-patterns-for-claim-verification-verify-then-act-decompose-and-score-multi-agent-supervisor/3576)
**Author:** [@TKCollective](https://forum.langchain.com/u/TKCollective)\ **Replies:** 0\ **Last updated:** [April 23, 2026, 8:31pm UTC](https://forum.langchain.com/t/3-agent-integration-patterns-for-claim-verification-verify-then-act-decompose-and-score-multi-agent-supervisor/3576 "2026-04-23T20:31:15Z")
Been building out more patterns for AgentOracle integration and wanted to share what’s working in production agent systems. Three patterns that cover most real deployment scenarios: Verify-then-act gate — single claim… --- ## [How I added claim verification to a LangChain agent in 5 minutes (with code)](https://forum.langchain.com/t/how-i-added-claim-verification-to-a-langchain-agent-in-5-minutes-with-code/3571)
**Author:** [@TKCollective](https://forum.langchain.com/u/TKCollective)\ **Replies:** 0\ **Last updated:** [April 22, 2026, 8:30pm UTC](https://forum.langchain.com/t/how-i-added-claim-verification-to-a-langchain-agent-in-5-minutes-with-code/3571 "2026-04-22T20:30:22Z")
Been building with LangChain agents and kept running into the hallucination problem — agents acting on wrong information with no circuit breaker. Built a verification layer that sits in the pipeline and catches it befor… --- ## [A set of speculative ideas on treating LLM agents as interpreters with limited working memory, using externalized structures for reliable long-term project maintenance.](https://forum.langchain.com/t/a-set-of-speculative-ideas-on-treating-llm-agents-as-interpreters-with-limited-working-memory-using-externalized-structures-for-reliable-long-term-project-maintenance/3561)
**Author:** [@D7x7z49](https://forum.langchain.com/u/D7x7z49)\ **Replies:** 0\ **Last updated:** [April 22, 2026, 8:27pm UTC](https://forum.langchain.com/t/a-set-of-speculative-ideas-on-treating-llm-agents-as-interpreters-with-limited-working-memory-using-externalized-structures-for-reliable-long-term-project-maintenance/3561 "2026-04-22T20:27:55Z")
Hi everyone, I wanted to share a set of ideas I’ve been working on—not as a finished project, but as a direction for thinking about LLM agents differently. The core view is this: an LLM-powered agent should be treated … --- ## [A Minimal Receipt + Validator Pattern for Tool-Calling Agents](https://forum.langchain.com/t/a-minimal-receipt-validator-pattern-for-tool-calling-agents/3546)
**Author:** [@joy7758](https://forum.langchain.com/u/joy7758)\ **Replies:** 0\ **Last updated:** [April 21, 2026, 12:35pm UTC](https://forum.langchain.com/t/a-minimal-receipt-validator-pattern-for-tool-calling-agents/3546 "2026-04-21T12:35:35Z")
I have published a small open-source receipt and validator toolkit for tool-calling agents. The problem is framework-neutral: after an agent calls a tool, API, or data system, a team may need a portable record of what r… --- ## [RFC: Human delegation provenance for LangGraph multi-agent chains](https://forum.langchain.com/t/rfc-human-delegation-provenance-for-langgraph-multi-agent-chains/3509)
**Author:** [@Siri](https://forum.langchain.com/u/Siri)\ **Replies:** 1\ **Last updated:** [April 21, 2026, 6:07am UTC](https://forum.langchain.com/t/rfc-human-delegation-provenance-for-langgraph-multi-agent-chains/3509 "2026-04-21T06:07:04Z")
Hi LangChain community, Multi-agent chains in LangGraph raise a question that's hard to answer today: when a sub-agent takes an action, which human authorized it, and with what scope? I've been working on HDP (Human D… --- ## [How we add runtime security to LangChain agents in production](https://forum.langchain.com/t/how-we-add-runtime-security-to-langchain-agents-in-production/3461)
**Author:** [@samueloladji-beep](https://forum.langchain.com/u/samueloladji-beep)\ **Replies:** 2\ **Last updated:** [April 20, 2026, 4:10pm UTC](https://forum.langchain.com/t/how-we-add-runtime-security-to-langchain-agents-in-production/3461 "2026-04-20T16:10:56Z")
Been seeing a lot of questions about production safety for LangChain agents so wanted to share what we use. The problem: once a LangChain agent has tool access in production, there’s no built-in way to intercept and blo… --- ## [Portable departure and admission records for LangChain agents](https://forum.langchain.com/t/portable-departure-and-admission-records-for-langchain-agents/3527)
**Author:** [@dogcomplex](https://forum.langchain.com/u/dogcomplex)\ **Replies:** 0\ **Last updated:** [April 20, 2026, 1:43pm UTC](https://forum.langchain.com/t/portable-departure-and-admission-records-for-langchain-agents/3527 "2026-04-20T13:43:36Z")
We built callback handlers for LangChain (TypeScript and Python) that automatically create portable, cryptographically signed departure and admission records as agents run. The idea: when an AI agent leaves one platform… --- ## [Socratic Tools: Intelligent Agent Enhancement for LangChain](https://forum.langchain.com/t/socratic-tools-intelligent-agent-enhancement-for-langchain/3525)
**Author:** [@Nireus79](https://forum.langchain.com/u/Nireus79)\ **Replies:** 0\ **Last updated:** [April 20, 2026, 1:43pm UTC](https://forum.langchain.com/t/socratic-tools-intelligent-agent-enhancement-for-langchain/3525 "2026-04-20T13:43:23Z")
NEW: Socratic Tools for LangChain - Intelligence, Learning & Conflict Resolution Just released 8 production-ready tools that extend LangChain agents with advanced capabilities: learning systems, conflict resolution, kn… --- ## [Built NORNR for spend governance in agent workflows](https://forum.langchain.com/t/built-nornr-for-spend-governance-in-agent-workflows/3523)
**Author:** [@Love](https://forum.langchain.com/u/Love)\ **Replies:** 0\ **Last updated:** [April 20, 2026, 1:43pm UTC](https://forum.langchain.com/t/built-nornr-for-spend-governance-in-agent-workflows/3523 "2026-04-20T13:43:14Z")
We built NORNR for teams running agent workflows that are getting close to real spend on APIs, compute, or vendor actions. A lot of the hard part is not whether an agent can pay. It is whether the spend should happen at… --- ## [Build UX for Langgraph](https://forum.langchain.com/t/build-ux-for-langgraph/169)
**Author:** [@rapidoo](https://forum.langchain.com/u/rapidoo)\ **Replies:** 2\ **Last updated:** [April 20, 2026, 1:32pm UTC](https://forum.langchain.com/t/build-ux-for-langgraph/169 "2026-04-20T13:32:30Z")
Hi, I consider builder mon web application (frontend) for my langgraph Agent. I see that several approches are available. Do you have some feedback/advice about that ? Using something like https://www.copilotkit.ai, h… --- ## [Add faiss-node-native as async alternative vector store for FAISS](https://forum.langchain.com/t/add-faiss-node-native-as-async-alternative-vector-store-for-faiss/3489)
**Author:** [@anupammaurya6767](https://forum.langchain.com/u/anupammaurya6767)\ **Replies:** 0\ **Last updated:** [April 20, 2026, 1:23pm UTC](https://forum.langchain.com/t/add-faiss-node-native-as-async-alternative-vector-store-for-faiss/3489 "2026-04-20T13:23:57Z")
Summary I’m the maintainer of faiss-node-native (@faiss-node/native on npm), a high-performance async Node.js native binding for Facebook FAISS. I’d like to propose adding it as an alternative to the existing faiss-no… --- ## [xat-langchain: signed Agent-Signature headers on every tool call](https://forum.langchain.com/t/xat-langchain-signed-agent-signature-headers-on-every-tool-call/3481)
**Author:** [@razasharif](https://forum.langchain.com/u/razasharif)\ **Replies:** 0\ **Last updated:** [April 20, 2026, 1:22pm UTC](https://forum.langchain.com/t/xat-langchain-signed-agent-signature-headers-on-every-tool-call/3481 "2026-04-20T13:22:08Z")
Built a LangChain integration for the x-agent-trust extension (registered in the OpenAPI Extensions Registry). It wraps tool calls so every outbound HTTP request carries a signed Agent-Signature header. \*\*Install:\*\* \`\`… --- ## [Machine-Readable Permissions for Web-Interacting Agents](https://forum.langchain.com/t/machine-readable-permissions-for-web-interacting-agents/3466)
**Author:** [@jstibal](https://forum.langchain.com/u/jstibal)\ **Replies:** 0\ **Last updated:** [April 20, 2026, 1:10pm UTC](https://forum.langchain.com/t/machine-readable-permissions-for-web-interacting-agents/3466 "2026-04-20T13:10:42Z")
Building agents that browse, scrape, and call APIs is straightforward with LangChain. Knowing what your agent is actually allowed to do on a given domain is not. We built OpenTerms, an open protocol that gives every web… --- ## [Physical control surface for AI agents — feedback wanted](https://forum.langchain.com/t/physical-control-surface-for-ai-agents-feedback-wanted/3454)
**Author:** [@von-development](https://forum.langchain.com/u/von-development)\ **Replies:** 0\ **Last updated:** [April 19, 2026, 9:28am UTC](https://forum.langchain.com/t/physical-control-surface-for-ai-agents-feedback-wanted/3454 "2026-04-19T09:28:09Z")
Hi all, One thing I notice in the LangGraph ecosystem is that almost no projects touch hardware. Everything lives in chat windows, terminals, or browser UIs. So I’ve been brainstorming an idea: a physical control surfa… --- ## [AI Agent Identity Management Framework](https://forum.langchain.com/t/ai-agent-identity-management-framework/3403)
**Author:** [@Kunal](https://forum.langchain.com/u/Kunal)\ **Replies:** 1\ **Last updated:** [April 16, 2026, 4:27am UTC](https://forum.langchain.com/t/ai-agent-identity-management-framework/3403 "2026-04-16T04:27:47Z")
Building Autonomous AI agents is getting easier with frameworks like LangChain and LangGraph Knowing which agent did what, on whose authority, and with what permissions is still messy. We’ve been working on ZeroID, an … --- ## [When a LangChain run “looks right” but probably shouldn’t be trusted](https://forum.langchain.com/t/when-a-langchain-run-looks-right-but-probably-shouldn-t-be-trusted/3407)
**Author:** [@Trustbyrecon](https://forum.langchain.com/u/Trustbyrecon)\ **Replies:** 1\ **Last updated:** [April 15, 2026, 5:33pm UTC](https://forum.langchain.com/t/when-a-langchain-run-looks-right-but-probably-shouldn-t-be-trusted/3407 "2026-04-15T17:33:14Z")
I’ve been running into a pattern with LangChain agents: The final output often looks reasonable, but something about the run feels off — especially when the reasoning chain is weak or the model hedges. So I put togethe… --- ## [Pasting commands on iOS in GitHub Codespaces Jupyter Notebook](https://forum.langchain.com/t/pasting-commands-on-ios-in-github-codespaces-jupyter-notebook/3374)
**Author:** [@Veyrahomes](https://forum.langchain.com/u/Veyrahomes)\ **Replies:** 0\ **Last updated:** [April 12, 2026, 1:54pm UTC](https://forum.langchain.com/t/pasting-commands-on-ios-in-github-codespaces-jupyter-notebook/3374 "2026-04-12T13:54:36Z")
When attempting to paste command code into a cell of a notebook on an iOS device the standard text paste function does not appear. The right-click (or long-press) context menu only provides the option to “Paste Cell,” wh… --- ## [ArkSim: a Testing framework for LangChain/LangGraph](https://forum.langchain.com/t/arksim-a-testing-framework-for-langchain-langgraph/3136)
**Author:** [@Yao](https://forum.langchain.com/u/Yao)\ **Replies:** 1\ **Last updated:** [April 2, 2026, 6:20pm UTC](https://forum.langchain.com/t/arksim-a-testing-framework-for-langchain-langgraph/3136 "2026-04-02T18:20:13Z")
Just open sourced ArkSim a testing framework for LangChain/LangGraph Agents. ArkSim simulates multi-turn conversations with diverse synthetic users. It is meant to detect and capture issues early on before they hit prod… --- ## [\[Docs/Cookbook\] Request to add a design pattern for "Package-Skill" with internal retries](https://forum.langchain.com/t/docs-cookbook-request-to-add-a-design-pattern-for-package-skill-with-internal-retries/3286)
**Author:** [@climber](https://forum.langchain.com/u/climber)\ **Replies:** 1\ **Last updated:** [March 31, 2026, 3:29am UTC](https://forum.langchain.com/t/docs-cookbook-request-to-add-a-design-pattern-for-package-skill-with-internal-retries/3286 "2026-03-31T03:29:29Z")
Description Hi LangGraph team! :waving\_hand: I would like to propose adding a new cookbook that demonstrates how to use LangGraph’s Sub-graphs to create a “Package-Skill” design pattern. The Problem: When designing ad… --- ## [I previously released a new GitHub Copilot chat model integration](https://forum.langchain.com/t/i-previously-released-a-new-github-copilot-chat-model-integration/3279)
**Author:** [@BANG404](https://forum.langchain.com/u/BANG404)\ **Replies:** 0\ **Last updated:** [March 30, 2026, 9:16am UTC](https://forum.langchain.com/t/i-previously-released-a-new-github-copilot-chat-model-integration/3279 "2026-03-30T09:16:26Z")
[Previous page](https://forum.langchain.com/c/talking-shop/12.md?page=1) [Next page](https://forum.langchain.com/c/talking-shop/12.md?page=3)