ZooWork

The AI agent delivery platform for FDEs and domain experts

Productivity

Developer Tools

Artificial Intelligence

Visit WebsiteSee on Product HuntTwitter ⧉LinkedIn ⧉

Congrats on the launch! 🎉 The hardest part of building my own agents has been data — self-built scrapers are a maintenance sink, and paid APIs get pricey and aren't always trustworthy. How does ZooWork handle data access for an agent — does it pull data itself through built-in tools, or are there connectors / data partners in the mix?

I love how seamless and fast it was to integrate with my code. I thought I'd run into problems but I did not. Besides, the run time is impressive!

How do you handle updates to an agent that clients are already using? Can I test a new version before making it live for them?

"Works beautifully on my laptop" is the most honest line in AI right now. I have at least three agents in that exact state. 1–2 second cold starts and paying nothing while idle is the part that got me. Congrats Ning and team!

Can an expert update the agents knowledge without rebuilding the entire workflow ?

the domain-expert-builds-it-in-the-UI model is the interesting bet here. at Dial we've seen non-technical team members want to tweak a live call flow and the thing we worry about isn't whether they can, it's whether a change they make on a Tuesday afternoon quietly breaks something for a client on Wednesday. is there any review or staging step before an expert's agent update goes live for a client, or does it publish straight through once they're happy with it in the Builder?

Great idea! Is there a way for me to track/review the agent’s performance over time?

Congrats on the launch, Ning, David and the ZooWork team. Reading the docs, config_version is a counter rather than a history and rollback is left to the app, while per-user agents each get their own copy of the template. For an FDE shipping one agent to 20 clients, is there a plan for staged rollout and one-click rollback when an SOP change makes things worse? That feels like the part that turns delivery into something you can actually maintain.

Really like the idea of turning domain expertise into AI agents that can actually handle real business workflows

the delivery part is what most agent builders miss. when the same agent is shared with two clients, how do you keep their files and conversation history separate?

Giving domain experts a builder UI while developers get a managed API is a nice split, it usually means the people who know the work can actually ship without waiting on engineering. Turning expertise into a deliverable agent for clients is a solid framing. Do the experts own the agents after delivery or do they stay tied to your platform?

Conngrats on the launch! What languages are the SDKs supporting now? Are there plans to support more languages?

Zero idle cost is the detail that makes a weekend agent project feel less wasteful. I'd still check the running costs, but I don't want to pay simply because an experiment exists.

What does the handoff process look like when an expert delivers an agent to a business team?

@ninghu The proposal Deck agent sounds useful. Can users build their own custom agents without coding?

I love the product concept.

Imagine a founder could build an agent that drafts investor updates from approved company notes, then share it with teammates for review, that will be very helpful.

An operations advisor could package a process diagnostic checklist into an agent and let clients run an initial assessment before a workshop.

An HR consultant could package a workshop intake questionnaire into an agent and share it with clients before the session.

Hi Product Hunt! 👋

I'm Ning, founder & CEO of ZooWork. Some of you may remember us as ZooClaw from our launch here in April.

Since then, we've heard one thing over and over, and felt it ourselves: there are countless tools for building AI agents, but almost nothing for delivering them. Everyone has an agent that works beautifully on their laptop. Almost no one can hand it to a client, a team, or a paying user as a reliable service.

That gap changed what we build, and our name along with it. ZooWork is our answer: an agent delivery platform for forward-deployed engineers, developers, and domain experts, with the whole path from build to production in one place.

Build: Describe what you want in the no-code Builder, or stay in the coding agent you already use (Claude Code, Codex, and more) and ship through our Managed Agent API. Setup is one line:

npx skills add SerendipityOneInc/zoowork-sdk-skills

Deploy: One click to the cloud, from a single agent to a multi-agent pipeline. Agents cold-start in 1–2 seconds, and you pay nothing while they're idle.

Deliver: Reach users where they already are: a shareable link, an API, or directly in WhatsApp, Slack, and more.

Under the hood, we handle the hardest part: the runtime. Every agent runs in its own managed, isolated sandbox, so what you ship keeps working without you babysitting servers. You own the interface, the customers, and the business. We run the agents.

A few of my favorite agents running on ZooWork today:

• A proposal deck studio: drop in your notes, get back a client-ready deck. Built by a consultant, not an engineer.

• A personal stylist: describe the occasion, get a complete look and the reasoning behind it.

• A home layout designer: snap a photo of your room, get a new layout with an interior designer's eye.

If you've ever built an agent that died on your laptop because there was no good way to share it, I'd love to hear the story. And tell us which coding agent or channel you want next. Your answers go straight into our roadmap.

Thanks for being here on launch day! 🙏