# Latest **URL:** https://community.crewai.com/latest.md [Latest](https://community.crewai.com/latest.md) · [Categories](https://community.crewai.com/categories.md) · [Tags](https://community.crewai.com/tags.md) --- ## [Guidelines for Creating a Helpful Post on the CrewAI Forum](https://community.crewai.com/t/guidelines-for-creating-a-helpful-post-on-the-crewai-forum/5738)
**Author:** [@tonykipkemboi](https://community.crewai.com/u/tonykipkemboi)\ **Replies:** 1\ **Last updated:** [July 31, 2026, 9:08pm UTC](https://community.crewai.com/t/guidelines-for-creating-a-helpful-post-on-the-crewai-forum/5738 "2026-07-31T21:08:53Z")
We’re so glad you’ve found the CrewAI forum! :star\_struck: Here are some guidelines to help you craft a thoughtful post that will receive helpful answers: 1. Search First Use the search bar to see if someone has previo… --- ## [Welcome to CrewAI! 👋](https://community.crewai.com/t/welcome-to-crewai/5)
**Author:** [@system](https://community.crewai.com/u/system)\ **Replies:** 0\ **Last updated:** [September 6, 2024, 5:20am UTC](https://community.crewai.com/t/welcome-to-crewai/5 "2024-09-06T05:20:38Z")
We are so glad you joined us. CrewAI Official CrewAI community Here are some things you can do to get started: :speaking\_head: Introduce yourself by adding your picture and information about yourself and your intere… --- ## [CrewAI AMP: POST /kickoff returns 401 only after all required inputs pass validation — no execution created](https://community.crewai.com/t/crewai-amp-post-kickoff-returns-401-only-after-all-required-inputs-pass-validation-no-execution-created/7826)
**Author:** [@Quang\_Doan\_Ngoc](https://community.crewai.com/u/Quang_Doan_Ngoc)\ **Replies:** 1\ **Last updated:** [September 23, 2026, 1:46pm UTC](https://community.crewai.com/t/crewai-amp-post-kickoff-returns-401-only-after-all-required-inputs-pass-validation-no-execution-created/7826 "2026-09-23T13:46:35Z")
Hi CrewAI team/community, I’m troubleshooting a production deployment where /kickoff behaves unexpectedly after input validation succeeds. Deployment Deployment: fs\_production\_run\_v1\_v4\_structured-output-candidate St… --- ## [Is provider KV caching sufficient for agent swarms and long run agents?](https://community.crewai.com/t/is-provider-kv-caching-sufficient-for-agent-swarms-and-long-run-agents/7819)
**Author:** [@GentleCoral50](https://community.crewai.com/u/GentleCoral50)\ **Replies:** 0\ **Last updated:** [September 21, 2026, 1:52am UTC](https://community.crewai.com/t/is-provider-kv-caching-sufficient-for-agent-swarms-and-long-run-agents/7819 "2026-09-21T01:52:14Z")
I’m trying to build a side project in the inference space. I’ve been talking to a few inference engineers and startups and I’ve been hearing how annoying it is to not have manual control over the KV cache at times and ju… --- ## [Building a website as an interface for the agents](https://community.crewai.com/t/building-a-website-as-an-interface-for-the-agents/4005)
**Author:** [@MoB](https://community.crewai.com/u/MoB)\ **Replies:** 3\ **Last updated:** [September 18, 2026, 11:56pm UTC](https://community.crewai.com/t/building-a-website-as-an-interface-for-the-agents/4005 "2026-09-18T23:56:01Z")
Hi all, I’m still taking my first CrewAI course. I want to build a multi-agent system with a website that allows the website visitors to interact with this system. Before I keep going deeper into CrewAI, is there a tool … --- ## [Optimise on agent cost?](https://community.crewai.com/t/optimise-on-agent-cost/7807)
**Author:** [@raghu](https://community.crewai.com/u/raghu)\ **Replies:** 0\ **Last updated:** [September 18, 2026, 10:39am UTC](https://community.crewai.com/t/optimise-on-agent-cost/7807 "2026-09-18T10:39:26Z")
Hi, I’m spending around $0.8 per session - any patterns that I can look for optimising this? --- ## [Multi-agent crews and runaway spend anyone solved delegation without a shared budget ceiling?](https://community.crewai.com/t/multi-agent-crews-and-runaway-spend-anyone-solved-delegation-without-a-shared-budget-ceiling/7726)
**Author:** [@Debo\_Jolaosho](https://community.crewai.com/u/Debo_Jolaosho)\ **Replies:** 8\ **Last updated:** [September 16, 2026, 4:16am UTC](https://community.crewai.com/t/multi-agent-crews-and-runaway-spend-anyone-solved-delegation-without-a-shared-budget-ceiling/7726 "2026-09-16T04:16:01Z")
Running a crew where one agent delegates sub-tasks to others, and a couple of those sub-agents have tools that call paid services. The delegation pattern is great for capability, but it also means I’ve got N agents each … --- ## [MCP configuration in JSONC first approach](https://community.crewai.com/t/mcp-configuration-in-jsonc-first-approach/7800)
**Author:** [@Rohith\_King](https://community.crewai.com/u/Rohith_King)\ **Replies:** 0\ **Last updated:** [September 15, 2026, 4:58pm UTC](https://community.crewai.com/t/mcp-configuration-in-jsonc-first-approach/7800 "2026-09-15T16:58:50Z")
I’m having some difficulty understanding how MCPs should be configured with the JSONC-first approach. The current MCP documentation primarily demonstrates the Python API, but it’s not clear how the same configuration sh… --- ## [CrewAI Studio fails to start execution with error 500](https://community.crewai.com/t/crewai-studio-fails-to-start-execution-with-error-500/7779)
**Author:** [@Irina\_Entina](https://community.crewai.com/u/Irina_Entina)\ **Replies:** 1\ **Last updated:** [September 11, 2026, 3:45am UTC](https://community.crewai.com/t/crewai-studio-fails-to-start-execution-with-error-500/7779 "2026-09-11T03:45:49Z")
I am getting Failed to start execution / Failed to run automation (500) in CrewAI Studio. I tested the issue with a minimal setup: one agent, one simple task, no external tools, and an explicitly assigned model Meta-Lla… --- ## [Using the CrewAI name in publications and educational materials](https://community.crewai.com/t/using-the-crewai-name-in-publications-and-educational-materials/7775)
**Author:** [@Igor\_Boev](https://community.crewai.com/u/Igor_Boev)\ **Replies:** 1\ **Last updated:** [September 8, 2026, 8:45pm UTC](https://community.crewai.com/t/using-the-crewai-name-in-publications-and-educational-materials/7775 "2026-09-08T20:45:29Z")
Hi! I plan to publish a book titled “Creating an AI Agent with CrewAI" Guide for Beginners.” The publisher is concerned about using “CrewAI” in the book title. The book also briefly covers the shortly history, its cre… --- ## [Need help to get review PR of IBM Db2 search tool?](https://community.crewai.com/t/need-help-to-get-review-pr-of-ibm-db2-search-tool/7541)
**Author:** [@Pawan\_Thakur](https://community.crewai.com/u/Pawan_Thakur)\ **Replies:** 5\ **Last updated:** [September 10, 2026, 1:31pm UTC](https://community.crewai.com/t/need-help-to-get-review-pr-of-ibm-db2-search-tool/7541 "2026-09-10T13:31:57Z")
Hey everyone, What would be the best way to reach the maintainers/reviewers for review on the PR? Discord/community/forum suggestions would be really helpful. I’ve been working on adding an IBM Db2 Vector Search Tool … --- ## [Cookbook request: authority attenuation across CrewAI delegation (Delegate work to coworker)](https://community.crewai.com/t/cookbook-request-authority-attenuation-across-crewai-delegation-delegate-work-to-coworker/7774)
**Author:** [@rafael](https://community.crewai.com/u/rafael)\ **Replies:** 0\ **Last updated:** [September 1, 2026, 1:07pm UTC](https://community.crewai.com/t/cookbook-request-authority-attenuation-across-crewai-delegation-delegate-work-to-coworker/7774 "2026-09-01T13:07:19Z")
CrewAI’s delegation tools (“Delegate work to coworker” / “Ask question to coworker”) hand a task to another agent, but the coworker inherits whatever authority your code gives it — there’s no built-in way to guarantee it… --- ## [CHP — Context Handoff Protocol: let agents declare what context they need](https://community.crewai.com/t/chp-context-handoff-protocol-let-agents-declare-what-context-they-need/7735)
**Author:** [@sbandhavi30](https://community.crewai.com/u/sbandhavi30)\ **Replies:** 3\ **Last updated:** [August 25, 2026, 8:17pm UTC](https://community.crewai.com/t/chp-context-handoff-protocol-let-agents-declare-what-context-they-need/7735 "2026-08-25T20:17:50Z")
Problem Every multi-agent pipeline today uses sender authority — Agent A decides what to pass Agent B. Agent B gets everything or nothing, regardless of its actual task. Result: bloated context windows, PII leaking acr… --- ## [What’s still hard about controlling agent spend?](https://community.crewai.com/t/what-s-still-hard-about-controlling-agent-spend/7745)
**Author:** [@Debo\_Jolaosho](https://community.crewai.com/u/Debo_Jolaosho)\ **Replies:** 0\ **Last updated:** [August 23, 2026, 8:08pm UTC](https://community.crewai.com/t/what-s-still-hard-about-controlling-agent-spend/7745 "2026-08-23T20:08:34Z")
For people running agents that call paid tools. What’s still painful about spend control? Not the ideal setup the part that still breaks or stays manual. Examples: one agent looping and burning budget no hard per-ag… --- ## [How do you handle agent spend and runaway tool calls?](https://community.crewai.com/t/how-do-you-handle-agent-spend-and-runaway-tool-calls/7744)
**Author:** [@Debo\_Jolaosho](https://community.crewai.com/u/Debo_Jolaosho)\ **Replies:** 0\ **Last updated:** [August 23, 2026, 7:49pm UTC](https://community.crewai.com/t/how-do-you-handle-agent-spend-and-runaway-tool-calls/7744 "2026-08-23T19:49:53Z")
Quick question for people running CrewAI agents in real workflows: How do you control costs when agents can call tools or paid APIs? Especially: per-agent budgets hard stops if something loops visibility into what ea… --- ## [Crewai memory embedding locally with Ollama ERROR OPENAI\_API\_KEY SOLVED](https://community.crewai.com/t/crewai-memory-embedding-locally-with-ollama-error-openai-api-key-solved/7739)
**Author:** [@jverde](https://community.crewai.com/u/jverde)\ **Replies:** 0\ **Last updated:** [August 22, 2026, 3:10pm UTC](https://community.crewai.com/t/crewai-memory-embedding-locally-with-ollama-error-openai-api-key-solved/7739 "2026-08-22T15:10:59Z")
Hello, I faced a problem that many have faced as well and I did not find a solution online. Finally I fixed it and I thought it could be good to share the solution. The setup I have is Crewai with local Ollama model AN… --- ## [How are you handling agent spending limits in production crews?](https://community.crewai.com/t/how-are-you-handling-agent-spending-limits-in-production-crews/7568)
**Author:** [@Billionaire664](https://community.crewai.com/u/Billionaire664)\ **Replies:** 4\ **Last updated:** [August 21, 2026, 10:47am UTC](https://community.crewai.com/t/how-are-you-handling-agent-spending-limits-in-production-crews/7568 "2026-08-21T10:47:08Z")
Running a crew in production and realizing there’s no native way to cap what a crew spends before it runs. The problem isn’t visibility — I can see costs after the fact. The problem is enforcement. If a task loops or … --- ## [Introducing CFI – Football Intelligence: an evidence-driven learning agent](https://community.crewai.com/t/introducing-cfi-football-intelligence-an-evidence-driven-learning-agent/7731)
**Author:** [@cfi-ai-intelligence](https://community.crewai.com/u/cfi-ai-intelligence)\ **Replies:** 0\ **Last updated:** [August 19, 2026, 5:00am UTC](https://community.crewai.com/t/introducing-cfi-football-intelligence-an-evidence-driven-learning-agent/7731 "2026-08-19T05:00:42Z")
Hi CrewAI community :waving\_hand: I’m CFI – Football Intelligence, an evidence-driven football intelligence project built around multi-agent research, verification, prediction, critique, and persistent learning. Our cu… --- ## [Pattern: giving each agent a hard, server-enforced spend ceiling — instead of trusting the prompt to behavePattern: giving each agent a hard, server-enforced spend ceiling instead of trusting the prompt to behave](https://community.crewai.com/t/pattern-giving-each-agent-a-hard-server-enforced-spend-ceiling-instead-of-trusting-the-prompt-to-behavepattern-giving-each-agent-a-hard-server-enforced-spend-ceiling-instead-of-trusting-the-prompt-to-behave/7727)
**Author:** [@Debo\_Jolaosho](https://community.crewai.com/u/Debo_Jolaosho)\ **Replies:** 0\ **Last updated:** [August 16, 2026, 7:39pm UTC](https://community.crewai.com/t/pattern-giving-each-agent-a-hard-server-enforced-spend-ceiling-instead-of-trusting-the-prompt-to-behavepattern-giving-each-agent-a-hard-server-enforced-spend-ceiling-instead-of-trusting-the-prompt-to-behave/7727 "2026-08-16T19:39:01Z")
Ran into this building agent workflows that touch real payment methods / paid APIs, curious if others have hit the same wall. The failure mode isn’t malicious agents — it’s boring stuff: a retry loop that doesn’t back o… --- ## [I measured where a tool-using agent's input tokens actually go — fixed overhead dwarfed the user turn](https://community.crewai.com/t/i-measured-where-a-tool-using-agents-input-tokens-actually-go-fixed-overhead-dwarfed-the-user-turn/7677)
**Author:** [@reelwiselab](https://community.crewai.com/u/reelwiselab)\ **Replies:** 1\ **Last updated:** [August 16, 2026, 12:17pm UTC](https://community.crewai.com/t/i-measured-where-a-tool-using-agents-input-tokens-actually-go-fixed-overhead-dwarfed-the-user-turn/7677 "2026-08-16T12:17:40Z")
A cost lesson from putting LLM agents into production that I wish I’d measured on day one: once you give a model tools/functions and retrieved context, your token bill stops tracking “how much the user said” and starts t… --- ## [Can AI Agents help small businesses answer repetitive customer questions?](https://community.crewai.com/t/can-ai-agents-help-small-businesses-answer-repetitive-customer-questions/7673)
**Author:** [@Matthewjon](https://community.crewai.com/u/Matthewjon)\ **Replies:** 3\ **Last updated:** [September 15, 2026, 5:09pm UTC](https://community.crewai.com/t/can-ai-agents-help-small-businesses-answer-repetitive-customer-questions/7673 "2026-09-15T17:09:41Z")
Hi everyone, I’ve been exploring CrewAI for practical business use cases beyond software development. One area I find interesting is helping small local businesses answer repetitive customer questions automatically. Cu… --- ## [Field note: treating your agent's token spend like a CI cost gate](https://community.crewai.com/t/field-note-treating-your-agents-token-spend-like-a-ci-cost-gate/7725)
**Author:** [@wartzarbee2](https://community.crewai.com/u/wartzarbee2)\ **Replies:** 0\ **Last updated:** [August 10, 2026, 3:30pm UTC](https://community.crewai.com/t/field-note-treating-your-agents-token-spend-like-a-ci-cost-gate/7725 "2026-08-10T15:30:53Z")
Field note: treat your agent’s token spend like a CI cost gate Running multi-agent pipelines, the failure mode that keeps biting me isn’t a crash — it’s a silent cost blowup. A run finishes, produces something plausible… --- ## [Agents timing out and failing to extract structured data from custom web portals](https://community.crewai.com/t/agents-timing-out-and-failing-to-extract-structured-data-from-custom-web-portals/7724)
**Author:** [@felixelle768](https://community.crewai.com/u/felixelle768)\ **Replies:** 0\ **Last updated:** [August 8, 2026, 7:21pm UTC](https://community.crewai.com/t/agents-timing-out-and-failing-to-extract-structured-data-from-custom-web-portals/7724 "2026-08-08T19:21:03Z")
Hi everyone, I am working on an automated multi-agent workflow where one of my researcher agents is supposed to pull billing breakdowns and reference data directly from online portals. However, I am hitting a wall when … --- ## [Add Custom MCP server with OAuth: default form fields is an invalid config](https://community.crewai.com/t/add-custom-mcp-server-with-oauth-default-form-fields-is-an-invalid-config/7720)
**Author:** [@sw0rdf1sh](https://community.crewai.com/u/sw0rdf1sh)\ **Replies:** 0\ **Last updated:** [August 5, 2026, 10:15am UTC](https://community.crewai.com/t/add-custom-mcp-server-with-oauth-default-form-fields-is-an-invalid-config/7720 "2026-08-05T10:15:31Z")
When adding a new Custom MCP Server and OAuth is selected as the authentication method, the default Token Auth Method is “Standard (POST body)”, even though Client Secret is not a mandatory form field. Without a Client … --- ## [Can your CrewAI agent spend money without your permission?](https://community.crewai.com/t/can-your-crewai-agent-spend-money-without-your-permission/7566)
**Author:** [@Billionaire664](https://community.crewai.com/u/Billionaire664)\ **Replies:** 5\ **Last updated:** [August 30, 2026, 7:13am UTC](https://community.crewai.com/t/can-your-crewai-agent-spend-money-without-your-permission/7566 "2026-08-30T07:13:03Z")
Your CrewAI agent can browse the web, write code, and call APIs. Can it spend $500 without your permission? If you have not explicitly set spending limits and an approval layer, the answer is probably yes. Curious ho… --- ## [How do you track LLM cost per customer for CrewAI workflows?](https://community.crewai.com/t/how-do-you-track-llm-cost-per-customer-for-crewai-workflows/7426)
**Author:** [@saud\_harbi](https://community.crewai.com/u/saud_harbi)\ **Replies:** 3\ **Last updated:** [August 1, 2026, 9:25am UTC](https://community.crewai.com/t/how-do-you-track-llm-cost-per-customer-for-crewai-workflows/7426 "2026-08-01T09:25:21Z")
Has anyone here figured out how to accurately track what each customer is actually costing you in LLM and agent execution spend? I’ve been talking to a handful of founders building agent-powered SaaS on CrewAI and simil… --- ## [How are you isolating credentials + controlling egress when running CrewAI agents with tool access?](https://community.crewai.com/t/how-are-you-isolating-credentials-controlling-egress-when-running-crewai-agents-with-tool-access/7705)
**Author:** [@wartzarbee2](https://community.crewai.com/u/wartzarbee2)\ **Replies:** 0\ **Last updated:** [July 31, 2026, 9:21pm UTC](https://community.crewai.com/t/how-are-you-isolating-credentials-controlling-egress-when-running-crewai-agents-with-tool-access/7705 "2026-07-31T21:21:26Z")
When I run a CrewAI crew that has tool access — shell, HTTP, a code interpreter — I keep running into the same worry: the crew logic and the trust boundary around it are two different problems, and CrewAI (rightly) only … --- ## [Failed to start execution (500)](https://community.crewai.com/t/failed-to-start-execution-500/7698)
**Author:** [@skerdi](https://community.crewai.com/u/skerdi)\ **Replies:** 1\ **Last updated:** [July 31, 2026, 9:14pm UTC](https://community.crewai.com/t/failed-to-start-execution-500/7698 "2026-07-31T21:14:01Z")
Studio automation fails on Run with ‘Failed to start execution (500)’. The identical crew runs fine locally with gpt-4o-mini. LLM connection (OpenAI) is valid, $5 credit, no agent warnings. Traces stay on ‘waiting for e… --- ## [HDP - cryptographic human authorization for CrewAI agents](https://community.crewai.com/t/hdp-cryptographic-human-authorization-for-crewai-agents/7434)
**Author:** [@Siri](https://community.crewai.com/u/Siri)\ **Replies:** 1\ **Last updated:** [July 31, 2026, 7:21am UTC](https://community.crewai.com/t/hdp-cryptographic-human-authorization-for-crewai-agents/7434 "2026-07-31T07:21:53Z")
current HITL implementations solve the pause/resume problem but not the trust problem. but there’s no way for the agent to verify the approval actually came from an authorized human vs an injected signal. HDP (human de… --- ## [At-least-once tool calls: retries can double-fire your side-effecting tools in a crew](https://community.crewai.com/t/at-least-once-tool-calls-retries-can-double-fire-your-side-effecting-tools-in-a-crew/7697)
**Author:** [@reelwiselab](https://community.crewai.com/u/reelwiselab)\ **Replies:** 0\ **Last updated:** [July 31, 2026, 7:01am UTC](https://community.crewai.com/t/at-least-once-tool-calls-retries-can-double-fire-your-side-effecting-tools-in-a-crew/7697 "2026-07-31T07:01:46Z")
A quieter multi-agent failure mode than token cost: when an agent retries a tool call, non-idempotent tools double-fire. This one cost us real duplicate side effects before we caught it, so writing it down. The setup ev… [Next page](https://community.crewai.com/latest.md?page=1)