# Latest **URL:** https://community.crewai.com/latest.md?page=3 [Latest](https://community.crewai.com/latest.md) · [Categories](https://community.crewai.com/categories.md) · [Tags](https://community.crewai.com/tags.md) **Page:** 4 --- ## [Agent eval tools?](https://community.crewai.com/t/agent-eval-tools/7453)
**Author:** [@Derfe](https://community.crewai.com/u/Derfe)\ **Replies:** 1\ **Last updated:** [May 1, 2026, 4:20pm UTC](https://community.crewai.com/t/agent-eval-tools/7453 "2026-05-01T16:20:18Z")
Hiya all, I’m curious how people here are evaluating their CrewAI agents once things start getting a bit more complex? I mean stuff like: output quality if tool usage is actually improving regressions after changes c… --- ## [Generative UI with CrewAI](https://community.crewai.com/t/generative-ui-with-crewai/7463)
**Author:** [@visharad](https://community.crewai.com/u/visharad)\ **Replies:** 1\ **Last updated:** [April 27, 2026, 3:41pm UTC](https://community.crewai.com/t/generative-ui-with-crewai/7463 "2026-04-27T15:41:07Z")
Hi everyone, I am Visharad, one of the maintainers of openui.com, an opensource generative ui framework for ai agents. I was thinking on firing up a pr to enhance the output of the stock\_analysis crew-example. Let me kno… --- ## [Use custom embedder for RAG](https://community.crewai.com/t/use-custom-embedder-for-rag/7489)
**Author:** [@MaKa](https://community.crewai.com/u/MaKa)\ **Replies:** 0\ **Last updated:** [April 23, 2026, 9:14am UTC](https://community.crewai.com/t/use-custom-embedder-for-rag/7489 "2026-04-23T09:14:00Z")
Hello, I have an issue with the integration of our company embedder to RAG tools like DirectorySearchTool. Background: I use an internal company embedder model with openAI interface but it has a batch size limitation w… --- ## [Verifiable Tool Invocation Receipts for CrewAI Flows](https://community.crewai.com/t/verifiable-tool-invocation-receipts-for-crewai-flows/7482)
**Author:** [@Bin\_Zhang](https://community.crewai.com/u/Bin_Zhang)\ **Replies:** 0\ **Last updated:** [April 21, 2026, 12:28pm UTC](https://community.crewai.com/t/verifiable-tool-invocation-receipts-for-crewai-flows/7482 "2026-04-21T12:28:44Z")
I have been exploring a practical question around agent execution integrity and auditability: when an AI agent calls a sensitive tool, what should the evidence record look like, and how can it be checked outside the orig… --- ## [Using CrewAI to support a CapCut-based video creation workflow](https://community.crewai.com/t/using-crewai-to-support-a-capcut-based-video-creation-workflow/7475)
**Author:** [@alishawinson](https://community.crewai.com/u/alishawinson)\ **Replies:** 0\ **Last updated:** [April 20, 2026, 2:38pm UTC](https://community.crewai.com/t/using-crewai-to-support-a-capcut-based-video-creation-workflow/7475 "2026-04-20T14:38:02Z")
Hi everyone, I’m exploring CrewAI for automating parts of my content creation process. My main workflow involves creating short-form videos using capcut free. I was wondering if CrewAI can realistically fit into this se… --- ## [CrewAI Studio execution timeline keeps loading](https://community.crewai.com/t/crewai-studio-execution-timeline-keeps-loading/7473)
**Author:** [@yinjun111](https://community.crewai.com/u/yinjun111)\ **Replies:** 0\ **Last updated:** [April 19, 2026, 11:11pm UTC](https://community.crewai.com/t/crewai-studio-execution-timeline-keeps-loading/7473 "2026-04-19T23:11:32Z")
When I revisit a completed project and click on “Execution,” the Timeline keeps loading indefinitely saying “Waiting for events to load…” and never displays the previous job. Has anyone encountered this issue before, or… --- ## [Testing tasks in isolation](https://community.crewai.com/t/testing-tasks-in-isolation/7470)
**Author:** [@kalfa](https://community.crewai.com/u/kalfa)\ **Replies:** 0\ **Last updated:** [April 17, 2026, 1:37pm UTC](https://community.crewai.com/t/testing-tasks-in-isolation/7470 "2026-04-17T13:37:58Z")
I am trying to do some task test in isolation. That’s to say determine\_schema: description: \> ... expected\_output: \> ... context: - input\_task agent: query\_manager I want to fake input\_task, so tha… --- ## [Hierarchical Process - Manager Cannot Delegate Issue (Coworker Not Found)](https://community.crewai.com/t/hierarchical-process-manager-cannot-delegate-issue-coworker-not-found/6302)
**Author:** [@arturo](https://community.crewai.com/u/arturo)\ **Replies:** 2\ **Last updated:** [April 17, 2026, 4:16am UTC](https://community.crewai.com/t/hierarchical-process-manager-cannot-delegate-issue-coworker-not-found/6302 "2026-04-17T04:16:53Z")
Hello CrewAI Community, I’m encountering a persistent issue with the hierarchical process where the manager agent is unable to delegate tasks to its worker agents, even when configured according to the documentation and… --- ## [Evaluating limits of processing agents: handling large datasets without heavy reliance on tools in CrewAI](https://community.crewai.com/t/evaluating-limits-of-processing-agents-handling-large-datasets-without-heavy-reliance-on-tools-in-crewai/7462)
**Author:** [@Jamil\_Andi](https://community.crewai.com/u/Jamil_Andi)\ **Replies:** 0\ **Last updated:** [April 14, 2026, 5:12am UTC](https://community.crewai.com/t/evaluating-limits-of-processing-agents-handling-large-datasets-without-heavy-reliance-on-tools-in-crewai/7462 "2026-04-14T05:12:31Z")
Post Content: I am developing an agent using CrewAI as part of a research project aimed at evaluating the real capabilities of autonomous agents. The goal is to design an agent that can: receive a complete dataset (… --- ## [CrewAi badge not received!](https://community.crewai.com/t/crewai-badge-not-received/7461)
**Author:** [@Lovish\_Kumar](https://community.crewai.com/u/Lovish_Kumar)\ **Replies:** 0\ **Last updated:** [April 12, 2026, 5:37pm UTC](https://community.crewai.com/t/crewai-badge-not-received/7461 "2026-04-12T17:37:09Z")
Hi team, I completed the DeepLearning.AI course Multi AI Agent Systems with crewAI on April 7, 2026 and submitted the badge request form with my completion screenshot, but I still have not received the badge email after … --- ## [Whatsapp integration?](https://community.crewai.com/t/whatsapp-integration/7459)
**Author:** [@major\_tiwari](https://community.crewai.com/u/major_tiwari)\ **Replies:** 0\ **Last updated:** [April 9, 2026, 4:19pm UTC](https://community.crewai.com/t/whatsapp-integration/7459 "2026-04-09T16:19:43Z")
Is there any integration with Whatsapp? My usecase is that I upload the details in Whatsapp and that whatsapp can invoke a whatsapp crewAI agent which will create a proper PDF based on information provided in the message… --- ## [\[Question\] Are parallel \`@listen(start\_event)\` handlers expected to mutate shared state deterministically?](https://community.crewai.com/t/question-are-parallel-listen-start-event-handlers-expected-to-mutate-shared-state-deterministically/7454)
**Author:** [@zc\_Liu](https://community.crewai.com/u/zc_Liu)\ **Replies:** 0\ **Last updated:** [April 8, 2026, 9:15am UTC](https://community.crewai.com/t/question-are-parallel-listen-start-event-handlers-expected-to-mutate-shared-state-deterministically/7454 "2026-04-08T09:15:06Z")
Hi team — I’m trying to understand the intended semantics for shared state mutation in Flows when multiple listeners are triggered in parallel from the same start event. The docs describe state management as the backbon… --- ## [Badge for deeplearning.ai](https://community.crewai.com/t/badge-for-deeplearning-ai/612)
**Author:** [@Youssef](https://community.crewai.com/u/Youssef)\ **Replies:** 31\ **Last updated:** [April 7, 2026, 2:38am UTC](https://community.crewai.com/t/badge-for-deeplearning-ai/612 "2026-04-07T02:38:44Z")
Hi Team, Thank you for your wonderful course on deeplearning.ai platform. I finished the course and requested the badge but still did not get any email. Does it take a lot of time to get them reviewed ? thanks --- ## [Introducing memweave — persistent agent memory as plain Markdown files | Feedback + CrewAI integration discussion](https://community.crewai.com/t/introducing-memweave-persistent-agent-memory-as-plain-markdown-files-feedback-crewai-integration-discussion/7452)
**Author:** [@Sachin\_Sharma](https://community.crewai.com/u/Sachin_Sharma)\ **Replies:** 0\ **Last updated:** [April 3, 2026, 6:54pm UTC](https://community.crewai.com/t/introducing-memweave-persistent-agent-memory-as-plain-markdown-files-feedback-crewai-integration-discussion/7452 "2026-04-03T18:54:19Z")
Hi CrewAI community, I recently released memweave, an open-source Python library for AI agent memory, and wanted to share it here and discuss how it could integrate with CrewAI agents. What it does: Stores agent mem… --- ## [Can't deploy my 1st crew AI agent](https://community.crewai.com/t/cant-deploy-my-1st-crew-ai-agent/7450)
**Author:** [@Jai\_Pande](https://community.crewai.com/u/Jai_Pande)\ **Replies:** 0\ **Last updated:** [April 1, 2026, 7:39am UTC](https://community.crewai.com/t/cant-deploy-my-1st-crew-ai-agent/7450 "2026-04-01T07:39:30Z")
Hi All, Hope you are doing good, i am unable to deploy my 1st crew AI agent crew, i am always getting this error:- PS:- I have the default boiler plate code so the project structure is intact Thanks --- ## [Tech 30 - way to go!](https://community.crewai.com/t/tech-30-way-to-go/7449)
**Author:** [@major\_tiwari](https://community.crewai.com/u/major_tiwari)\ **Replies:** 0\ **Last updated:** [April 1, 2026, 3:33am UTC](https://community.crewai.com/t/tech-30-way-to-go/7449 "2026-04-01T03:33:28Z")
Congratulations to Team CrewAI on being selected for the Enterprise Tech 30 for the second consecutive year! --- ## [New to CrewAI and building a solid team of agents already](https://community.crewai.com/t/new-to-crewai-and-building-a-solid-team-of-agents-already/7448)
**Author:** [@Salesdroid](https://community.crewai.com/u/Salesdroid)\ **Replies:** 0\ **Last updated:** [March 29, 2026, 9:26pm UTC](https://community.crewai.com/t/new-to-crewai-and-building-a-solid-team-of-agents-already/7448 "2026-03-29T21:26:26Z")
Hi everyone, I’m Michael. Great to be here. I’m building Paperclip, a multi-agent operating layer for marketing and outbound execution across three brands: The AI Phone Guy Automotive Intelligence Calling Digital Wha… --- ## [Human in the loop - workaround](https://community.crewai.com/t/human-in-the-loop-workaround/7330)
**Author:** [@Bokis\_Angelov](https://community.crewai.com/u/Bokis_Angelov)\ **Replies:** 6\ **Last updated:** [March 27, 2026, 12:20pm UTC](https://community.crewai.com/t/human-in-the-loop-workaround/7330 "2026-03-27T12:20:26Z")
Hi everyone, I have been experimenting with CrewAI over the past year and completed the two DeepLearning courses. They helped me understand the framework well. I am now building an internal application for my organizat… --- ## [New CrewAi but excited](https://community.crewai.com/t/new-crewai-but-excited/7429)
**Author:** [@Kkunal](https://community.crewai.com/u/Kkunal)\ **Replies:** 0\ **Last updated:** [March 25, 2026, 2:39am UTC](https://community.crewai.com/t/new-crewai-but-excited/7429 "2026-03-25T02:39:19Z")
Hi Team, i am new in the agentic ai space. I have done few claude based development of website and web apps with google sheet as backend. Im not that techie types. But i am interested to know more about crewai and how i… --- ## [ArkSim: a Testing framework for CrewAI](https://community.crewai.com/t/arksim-a-testing-framework-for-crewai/7411)
**Author:** [@Yao](https://community.crewai.com/u/Yao)\ **Replies:** 3\ **Last updated:** [March 23, 2026, 7:26pm UTC](https://community.crewai.com/t/arksim-a-testing-framework-for-crewai/7411 "2026-03-23T19:26:08Z")
We’ve been working on ArkSim a testing framework for CrewAI Agents. ArkSim simulates multi-turn conversations with diverse synthetic users. It is meant to detect and capture issues early on before they hit production. T… --- ## [How do LLM Connections inject API keys into the crew process?](https://community.crewai.com/t/how-do-llm-connections-inject-api-keys-into-the-crew-process/7419)
**Author:** [@Fugsy](https://community.crewai.com/u/Fugsy)\ **Replies:** 1\ **Last updated:** [March 19, 2026, 8:52am UTC](https://community.crewai.com/t/how-do-llm-connections-inject-api-keys-into-the-crew-process/7419 "2026-03-19T08:52:29Z")
Subject: How do LLM Connections inject API keys into the crew process? I’ve configured an OpenAI LLM Connection in the dashboard. My crew still fails with AuthenticationError: Incorrect API key: sk-placeholder.... I can… --- ## [CrewAI HubSpot connection oauth failure](https://community.crewai.com/t/crewai-hubspot-connection-oauth-failure/7408)
**Author:** [@Trung\_Nguyen](https://community.crewai.com/u/Trung_Nguyen)\ **Replies:** 2\ **Last updated:** [March 17, 2026, 4:09pm UTC](https://community.crewai.com/t/crewai-hubspot-connection-oauth-failure/7408 "2026-03-17T16:09:07Z")
I’m using CrewAI Studio to build out my agent. And one of the thing it needs is a HubSpot connection. When I tried to connect via OAuth, it’s erroring out on HubSpot with this message, “Couldn’t complete the connection … --- ## [POP: a tiny CrewAI-style trial for portable persona objects](https://community.crewai.com/t/pop-a-tiny-crewai-style-trial-for-portable-persona-objects/7409)
**Author:** [@Bin\_Zhang](https://community.crewai.com/u/Bin_Zhang)\ **Replies:** 0\ **Last updated:** [March 17, 2026, 7:12am UTC](https://community.crewai.com/t/pop-a-tiny-crewai-style-trial-for-portable-persona-objects/7409 "2026-03-17T07:12:43Z")
Hi everyone, I’m experimenting with a small prototype called POP (Persona Object Protocol). The idea is to treat persona as a portable object layer instead of keeping persona scattered across prompts or config fragment… --- ## [Same CrewAI Endpoint Returns Incorrect Output When Called from AWS Servers / Product UI](https://community.crewai.com/t/same-crewai-endpoint-returns-incorrect-output-when-called-from-aws-servers-product-ui/7407)
**Author:** [@Srushti\_Zope](https://community.crewai.com/u/Srushti_Zope)\ **Replies:** 0\ **Last updated:** [March 16, 2026, 2:05pm UTC](https://community.crewai.com/t/same-crewai-endpoint-returns-incorrect-output-when-called-from-aws-servers-product-ui/7407 "2026-03-16T14:05:41Z")
Same CrewAI Endpoint Returns Incorrect Output When Called from AWS / Product UI — Works Fine from Postman We’re running a sequential CrewAI pipeline (7 tasks, 2 agents, TXTSearchTool for RAG over 2 text files, Claude vi… --- ## [crewai-soul: Markdown Memory with RAG+RLM for Your Crews](https://community.crewai.com/t/crewai-soul-markdown-memory-with-rag-rlm-for-your-crews/7387)
**Author:** [@menonpg](https://community.crewai.com/u/menonpg)\ **Replies:** 2\ **Last updated:** [March 12, 2026, 11:07am UTC](https://community.crewai.com/t/crewai-soul-markdown-memory-with-rag-rlm-for-your-crews/7387 "2026-03-12T11:07:59Z")
What I built: A memory backend that stores agent identity and memories in human-readable markdown files with full semantic search. The problem it solves: • Built-in memory is a black box — can’t read/edit it • Vector … --- ## [Tool issue with version 1.10.1](https://community.crewai.com/t/tool-issue-with-version-1-10-1/7373)
**Author:** [@SG391](https://community.crewai.com/u/SG391)\ **Replies:** 4\ **Last updated:** [March 12, 2026, 7:54am UTC](https://community.crewai.com/t/tool-issue-with-version-1-10-1/7373 "2026-03-12T07:54:08Z")
HI All, I am having issue with using tools in version 1.10.1. It works perfectly in version 1.9.3… Here is my code: base\_report\_tool = TXTSearchTool(txt=temp\_file\_path,config=text\_tool\_config) @tool(“search\_report”) … --- ## [Hallucination is happening by agents](https://community.crewai.com/t/hallucination-is-happening-by-agents/7037)
**Author:** [@narendra\_sompalle](https://community.crewai.com/u/narendra_sompalle)\ **Replies:** 11\ **Last updated:** [March 10, 2026, 5:50am UTC](https://community.crewai.com/t/hallucination-is-happening-by-agents/7037 "2026-03-10T05:50:55Z")
I build a AMS project using crewai that integrate with JIRA,Servicenow,Github,Knowledge base(RAG) I am facing Hallucination issue, can you please tell how to fix the issue. I am facing lot of issues --- ## [Bug in tool invocation for native function calling with Anthropic/Claude](https://community.crewai.com/t/bug-in-tool-invocation-for-native-function-calling-with-anthropic-claude/7392)
**Author:** [@moy](https://community.crewai.com/u/moy)\ **Replies:** 0\ **Last updated:** [March 10, 2026, 5:02am UTC](https://community.crewai.com/t/bug-in-tool-invocation-for-native-function-calling-with-anthropic-claude/7392 "2026-03-10T05:02:57Z")
I am using Crewai 1.9.3. I suspect the issue is present in current 1.10.x as well. My issue is that I was unable to invoke tools when using Claude Opus 4.5. It was always returning responses like: \[ToolUseBlock(id=‘too… --- ## [Security Guardrail for sensitive data](https://community.crewai.com/t/security-guardrail-for-sensitive-data/7357)
**Author:** [@major\_tiwari](https://community.crewai.com/u/major_tiwari)\ **Replies:** 5\ **Last updated:** [March 9, 2026, 4:11pm UTC](https://community.crewai.com/t/security-guardrail-for-sensitive-data/7357 "2026-03-09T16:11:21Z")
@maxmoura @zinyando @Dabnis @Tony\_Wood I currently serve as Director – Salesforce Delivery at a leading healthcare organization. Recently, we were tasked with evaluating various tools for implementation within one of ou… --- ## [FERPA concerns about CrewAI sharing data with LLMs](https://community.crewai.com/t/ferpa-concerns-about-crewai-sharing-data-with-llms/7355)
**Author:** [@Jim](https://community.crewai.com/u/Jim)\ **Replies:** 3\ **Last updated:** [March 9, 2026, 1:48pm UTC](https://community.crewai.com/t/ferpa-concerns-about-crewai-sharing-data-with-llms/7355 "2026-03-09T13:48:25Z")
Hi all, I help teach in an online MSCS program, we are developing a project for the students using CrewAI for malware analysis. It’s in the early planning stages, we haven’t run CrewAI yet. Sorry for the newb question. I… [Previous page](https://community.crewai.com/latest.md?page=2) [Next page](https://community.crewai.com/latest.md?page=4)