Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More

Owned by Darin

🚀 Discover AI agents, automation, voice assistants, business tools, and integrations. Learn, connect, and grow with AI Automation Toolbox!

17 contributions to Brendan's AI Community
Claude + Voice AI Just Changed Websites Forever! (Tutorial)
This video shows you how to build an AI voice agent that lives on any website, answers visitor questions out loud, navigates the page, highlights relevant sections, and fills in booking forms automatically, all built step by step with Claude Code and LiveKit. No developer experience needed because Claude writes the entire code for you. Check it out! 👇
2 likes • 3d
@Brendan Jowett can this work for chatgpt users
1 like • 3d
@David Hunter i run livekit and gpt live 1
Master Logo Design with AI in 10 Minutes (Step-By-Step)
This video shows you exactly how to design professional AI logos that look like they belong to a real brand, not something obviously generated by AI. You'll learn which AI image models actually produce great logos, including Recraft v4.1, GPT Image 2.5, and Grok Image 2.0, all compared side by side. The full prompting workflow is covered step by step, plus how to convert your final logo from a PNG into a fully editable SVG vector file using Claude Code. Check it out! 👇
3 likes • 7d
Great tutorial 👌
My receptionist only confirms a booking after the save comes back
One rule I added after my test calls: the agent never says a slot is booked until the booking actually comes back as saved. If the save is slow or fails, it takes the caller's name and number and says the office will confirm. It sounds small, but a receptionist that promises a time it never saved is worse than one that says it will follow up. I'm still testing on messy real sites, not live with clients yet. What does your agent say when the booking step fails mid call?
0 likes • 12d
@Umer Mehmood my voice agent go to a log, recorded, then going to CRM afterwards
How to Share a Claude Plugin With Your Team
| Source: Claude Plugins Documentation You made a Claude plugin and want your team to use it. Inside your organization, you have two options. Share sends it to people you pick. Publish to org puts it in your organization's library. Both options need a Team or Enterprise plan. [How to Share] Go to Customize > Plugins, open your plugin, and select Share. Add each person by name or email, then confirm. You do not need an Owner, and nothing is reviewed. Share cannot reach the whole organization, so use Publish to org for that. [What Your Teammates Do] After you share, tell your teammates what to do. They open Customize > Plugins, find the plugin under Shared with you, and turn it on. Each person then connects the plugin's connectors with their own account. They can use it but cannot edit it. [Publish to Org] Publish to org adds your plugin to your organization's library. An Owner decides who can find and install it. What happens next depends on the Publishing setting: Requires review, Open (no review), or Off (members cannot publish). [Review and Updates] Under Requires review, you suggest how the plugin installs: Available to install, Installed by default, or Required. An Owner approves it, and you cannot approve your own. After it is published, later edits reach your organization only when you publish again. [Share Button Missing?] Share appears only on plugins you created or uploaded yourself. If it is missing, Skills may be off or a security scan may have blocked the plugin. If the dialog says "Direct sharing is turned off for your organization," ask an Owner to turn on Skill sharing. [Your Action Plan] Today, confirm you are on a Team or Enterprise plan, open your plugin, select Share, and add one teammate. Then ask your Owner which Publishing setting your organization uses. For someone outside your organization, send them the .plugin file to add with Add > Upload plugin.
1 like • 19d
@Aatar Atta great knowledge contribution
Looking for an experienced AI Voice Agent / Realtime Voice Systems Consultant
I’m building a production AI receptionist for an appliance repair company. We already have a custom stateful backend with deterministic business logic, customer/service-request state, scheduling logic, corrections, multiple appliances, fees, service-area rules, and CRM integration work. The main unresolved problem is the realtime voice layer. We have worked with LiveKit and Retell and are currently evaluating Vapi. I’m looking for someone with hands-on production experience with Vapi, Retell, LiveKit, Deepgram, Twilio/SIP, or similar realtime voice stacks. The important problem is not prompt engineering. It is the boundary between a voice platform and an authoritative stateful backend: - finalized caller turns - transcript revisions - request retries / idempotency - interruptions / barge-in - assistant speech delivery authority - latency - streaming Custom LLM integration Initially I want a paid architecture/code review, not a rewrite. I’d like the consultant to review the current system and recommend the smallest reliable path to production, including whether Vapi, Retell, LiveKit, or another stack is the best fit. Please send: - voice platforms you have used in production - approximate call volume - examples of realtime voice problems you personally solved - experience with custom/stateful LLM backends - your hourly rate
2 likes • Oct 23
@Alec M Im using livekit myself.....with openai ..... i was able to not have too much problems getting it work
1-10 of 17
Darin Shavce
3
27 points to level up
@darin-shavce-4334
Ive built a ai platform that takes all areas of your business and automate your daily tasks https://aiautomationtoolbox.com/preview.php

Active 1m ago
Joined Apr 11, 2026
Detroit, Michigan
Powered by