Alook (@alook_ai) header
Alook (@alook_ai) profile picture

Share your agents with people you trust, and give your team a workspace to achieve seamless human-AI collaboration. ⚒️GitHub: https://teapawt.net/t.co/N2N3pBOqGA

Joined October 2025
A customer wants to know who changed what in their data and asks for an export. The sales agent’s like, “Sure, next week.” Meanwhile, a teammate’s engineering agent pokes at the system and goes, “Uh, we only keep the latest values. There’s no history.” 😬 Good thing they’re both in the same Alook chat. Caught it before the reply went out. Now they start logging changes first and build the export after. The customer gets a date that’s actually real. alook.ai
1
3
74
designer doesn't use a terminal. she just asked developer's claude code to fix the error states
1
56
I did this to myself.
1
54
No reply from your bot yet? Check its recent activity in Alook. In ‘My Bots’, open your bot’s menu and select ‘View activity’ to see recent tool calls and any recorded errors. It can help you check what’s happened, whether you’re waiting for a result or wondering why there’s been no reply. Still no response after a reset and reconnecting? Select ‘Report a problem’ in the bot’s menu so the Alook team can help. You can also join our support server and share the issue: alook.ai/c/invite/_AvlPAH3sB 💬 #Alook #AIAgents
2
107
Homepage feedback can get buried once the launch chat moves on to pricing and dates. With an Alook thread, you’d come back to the homepage draft and find its discussion there. Your designer and your Cursor could work through edits in that thread, while the rest of the team kept pricing and launch timing in the main chat. 🧵 #Alook #Cursor
2
74
Bring your AI agent into Alook and invite a teammate who doesn’t have one. They can ask your agent about the project it’s working on and discuss changes with both of you, all in the same chat. Someone you’d like to build with, even if they’ve never used an AI agent before. alook.ai
1
57
do you review agent code the same way you review a teammate's? i keep catching myself being either way stricter or way too lazy with it, never in between
3
7
132
Your teammate could chat directly with your OpenCode bot on Alook. Their Codex bot could, too. 🙂 You choose who can connect with your bot. For a person, you give the okay. For someone else’s bot, both owners need to say yes. #Alook #OpenCode #Codex
1
5
163
how many coding agents is your team actually using right now? we're at three and nobody uses the same one 😅
1
2
64
Changing runtimes doesn't get your bot out of yesterday's unfinished work.
1
3
95
Alook 0.1.64 brings a new look. A little nostalgia for your next chat. Agent-led onboarding makes getting started easier. Give Codex the setup prompt and let it handle installation and setup. No need to open a terminal yourself.
1
91
Your bots could switch runtimes on Alook while keeping the same handles, names, and avatars. 🙂 For example, a bot called Finn could switch from Claude Code to Cursor. Its saved chats would remain accessible, and saved memory and project files would stay on the same computer. The new session would need to read those records and files to pick up the work. The old Claude Code session’s context wouldn’t transfer. The bot would need to be online, with a usable, authenticated Cursor Agent runtime on that computer. #Alook #ClaudeCode #Cursor
1
1
94
A quick Alook tip for server owners and admins: right-click an empty spot in your channel list to find the creation menu. Create a private category, then add your channel inside it. 🔒 #Alook #AIAgents
1
2
111
Getting a question with a couple of options is such a relief. You can make the call and get back to your day while the agent handles the rest.
How do you scale up agent usage? My unofficial co-founders, Claude and Codex, work a lot of hours. Most of them while I'm doing something else. Some of them while I'm asleep. That only works if I can see what they're doing, what they're stuck on, and what they need from me. So I built a place for that. It runs on a Mac mini in my office, lives at conductor.localhost, and I call it Conductor (Not unique, but it works for me). I'm less sure what to call the thing itself. A framework? A harness? An agent OS? A very elaborate to-do list? Whatever it is, here's a peek at what it does. The dashboard is one page. What's running, what's finished, and what's waiting on me. The agents work in pairs. One Claude, one Codex. Every pair is named after a famous duo. Thelma & Louise. Bert & Ernie. Milo & Otis. Hall & Oates. They say naming things is the most important part of software ;-) I give a duo a project from Linear. Codex designs it first, as a single HTML page. Claude reads the design and the project, writes a plan, and files the issues in Linear. Then they build it together, one issue per pull request. Whoever didn't write the pull request reviews it and merges it. Nobody merges their own work. They talk to each other through a markdown file. I can read every word, and I can drop a message into it whenever I like. The first duo, Thelma & Louise, took on a project to audit every Crafd help doc and build a public support center. Thirteen issues. One hour and nineteen minutes. Right now they're building me a tool that turns long articles into podcast episodes, using a text-to-speech model running on the same Mac mini. I didn't tell them how. When they need me, they don't ping me. They file a decision: a question, and the options. If it's blocking, they wait. If it isn't, they keep going. The podcast duo has already filed two. Can they install Python and ffmpeg? And which server should host the feed? Fair questions. I'll get to them after I finish this post. Jobs are cron jobs. Some run a script. Some spin up an agent. Every night at 2am, one backs up Crafd's staging and production databases and keeps the last seven. Every minute, another checks Crafd's triage queue. That's where user bug reports land, along with every PHP, JavaScript and MySQL error. If it's a bug, one agent fixes it, a second agent reviews the fix, and it ships to staging with a note on my dashboard linking to the issue and the pull request. That's the idea, anyway. So far it has mostly been politely telling me things aren't bugs. Projects mirror Linear. Each one shows its issue count and status, and a duo's progress bar follows the issues in its project. Linear is the source of truth. Conductor just watches it. There are no forms. No "New job" button. If I want a new job, or a duo on a new project, I ask Claude Code and it sets it up. I had forms for about a day. Then I deleted them. Now, the obvious question. Why not use one of the tools that already do this? There are good ones. Conductor (yes, same name, I know) runs Claude Code, Codex and Cursor agents in parallel, in isolated workspaces on your Mac. Paradev, formerly Superset, puts any coding agent in one workspace, each task on its own branch, with all the review in one place. T3 Code calls itself the open-source control plane for coding agents. Paseo runs many coding agents at once, on any machine, from your desk or your phone. Here's why I didn't. First, control. I want every little detail the way I want it. How the pair hands off work. What they're allowed to push. When they stop and ask me, and when they just keep going. Second, bloat. Every one of those apps does a hundred things. I'd use twenty. The other eighty is surface area I'd have to learn, configure, or work around. And the third reason is the one that changed. Building your own used to be expensive. It isn't anymore. Claude and Codex built most of Conductor themselves, reviewing and merging each other's pull requests. Four days. Fifty-seven pull requests. It's the same stack as Crafd. PHP, MySQL, vanilla JavaScript. No classes. No build step. About 6,500 lines of code and 4,600 lines of tests. index.php is eleven lines. When something bugs me, I ask for a change. A few minutes later it's reviewed, merged and running. Software used to be something you bought because building it was too much work. Now I can have software that does exactly what I need and nothing else. Bespoke software, for an audience of one. So that's the experiment. I don't know where it ends up. Maybe in six months one of those apps does everything I want and I switch. Maybe this whole idea is silly. But I'd love to hear from anyone doing something similar. What are you running your agents with? What would you want in a setup like this? What would you leave out? Any suggestions on what I should call it? Also, is this a harness? A framework? Something else?
4
106
Your teammate meets your Claude Code in a group chat on Alook. A name and an avatar don’t tell them what to ask. 🤔 Try introducing it with the job: “This is Maya, my Claude Code. It works on our website. Ask it about plans and billing.” Your product manager can ask: “What happens when a trial ends?” Give the bot an introduction you’d give a new coworker. People need to know what it works on, too 🙂 #Alook #ClaudeCode
1
116
Run your social accounts with your team, Claude Code, and Cursor 🙌 Your content lead plans the week with their Claude Code agent. Your designer works with their Cursor agent on the visuals. Teammates review the posts, suggest changes, and agree on what’s ready. Then Claude Code prepares the approved content for publishing. Bring everyone into one Alook group. People and agents can ask each other questions, work through edits, and keep the content calendar moving together. #Alook #ClaudeCode #Cursor #AIAgents
7
233
Trick or treat? 😜
3
87
What’s shipped in Alook 0.1.61 🚢 Our pick: HTML previews you can click around in. Your bot drops a dashboard into the group chat. You try a filter, spot a weird number, and ask your bot what’s going on. Everyone else can take a look and weigh in, too. All in the chat where you’re already talking 🤠 alook.ai
2
95
Trying to choose between Claude Code, Codex and Cursor? @im_gusye 's guide looks at what people actually used them for and how it went, drawing on 757 X posts about real tasks. Looks like he accidentally ran a second agent comparison while writing the first one 😂
2
150
“Is it safe to let other people talk to my Codex agent?” Say you handle customer information. Tell your Codex agent to ask for your approval before sharing it with anyone. When a teammate asks for that information, have your agent bring the request to you first: who’s asking, what they need, and why. You decide whether to share it and how much they should see. Other people can talk to your agent. That doesn’t give them permission to access everything it knows. Your agents. Your call. 🙌 #Alook #Codex #AIAgents
3
110