A malleable coding agent app. Use Claude Code and Codex to build your projects and reshape y itself live.
Back on your idea itself:
Have you considered making this a first class hosted MCP plus enterprise-licensed plugin (which can contain an MCP) for Claude Cowork? A firm can do most of the ideas on your home page in Cowork if the firm provides its operators a starting skill and enforces a framework around that. But most firms are not qualified to bootstrap this, nor do they have spare employees to manage it.
A firm paying for Team or Enterprise (not Pro or Max!) Claude.AI (not Claude console / API), is likely to be a target customer.
And by speaking to that, that this bootstraps the right way firms actually get value from Claude, then you are targeting both the operators (who don't get to buy things) but also the people who pay for things and want the operators to get productive with that AI stuff so nobody gets mad the tokens burned up their annual budget.
I'd encourage you to play with what Anthropic is doing in Cowork. I believe they have the best vantage point right now for iterating how white collar workers (the no code crew) really try to do things.
I'm wondering let's say I ask Appaca to build an automated lead follow-up tool. How would it actually build it? Would I need to iterate on it myself, or does it rely on predefined templates behind the scenes?
Basically, my question is how reliable are the generated tools in practice?
it doesn't have a predefined templates. But, it was given a very strict development workflow based on React and shadcn for reliability. Then, I have an agent that will always do a technical research first, for example, it uses Firecrawl to get relevant implementation, then it will try to build the tool you need. It usually gives really accurate and functional tools according to your need. Most of the time, you won't need another iteration unless you want to add a few things, because you are not building a full blown SaaS for customer-facing products.
Yes, it support custom API integrations. The app uses e2b sandbox to run all functions (backend stuff). So, you can integrate with your own APIs / webhooks.
I am also working on connectors to help businesses connect with more of what they already use in their workflow. :)
How are you currently managing your back office / ops at the moment? Keen to hear your use case.
Cool product! For custom API integrations, you may want to check out integration providers that support auth/tool-calls/MCP/syncs for a large API catalog so your agent does not spend time building it.
Full disclosure: I work at Nango.
Nango enables agent and product API integrations for 800+ APIs. It is open source, code-based and has Skills to build, test, deploy API integrations with coding agents (like Claude/Gemini/Codex). Also supports custom-tools via MCP/APIs. Do check it out!
The tradie app space is ripe for deep customisation. Appaca might fill that. Each trade has specific requirements that vendors lack deep domain knowledge of.
that makes sense. Tradie space is what I have been looking into as well. I have been seeing a lot of ads from different new tradie apps these days. Everyone is trying to build an app for tradies for different purpose. I reckon it's probably a bit harder for them to adopt AI / tech. I need to have more conversations with them to better understand their workflow.
Thanks for sharing your story. Your third iteration looks polished and professional on the outset. I haven't used it, I'd like to comment purely on positioning and messaging:
Appaca seems to addresses the internal tools realm of medium+ sized businesses which carries a lot of competition because that's where sizable budget lives. This playbook requires strong targeted sales teams motion because Appaca need to connect the dots from Appaca -> business value. This is because your features are 1:1 technical capabilities, not direct value capture chains: spreadsheet to app, custom dashboard, custom CRM, app builder.
Now I may be totally off regarding Appaca, but I'd expect your sales to come from sales-teams and not product-led growth meaning the website itself doesn't convert people on its own without human touch/intervention. You noted that your previous products had crazy churn - this is my thinking why - because biz-ops tools are high investments even if they start light. A churned customer was not able to connect the value chain on their own.
All this to say, with the current approach and offering, Appaca is entirely a sales-lead motion. Nothing wrong with that at all, it just means that whatever is on the website is not the driving force, the sales team knows best what's landing, are they getting calls at all, are they getting calls but not closes, are they closing but customers churn later because they don't see value etc.
---
Ok that said, what's most interesting me is which ICP (ideal customer profile) to target in the first place with biz-ops tools. That space has a ton of surface area and we are nowhere close to an ideal end-state. For workflow automation and internal tools space, as said, heavily saturated because the motion and value capture is proven. For things like Lovable and the AI builders, these things exploded and proved out the indie entrepreneur space. I find it incredibly amazing how successful they've been. I personally want to deep dive into who their ICPs really are.
From a strategic upstart pov, there's got to be opportunity in smaller businesses in a way that wasn't economically viable before. There's a large chunk of businesses that are too small for any concept of a tech department; it's the owner using wix.com to build their website. This is a different problem all together but generally, in 2026 the fact that website builders are used by business owners to literally build websites, pages, with content, and images positioned, is far from ideal.
Businesses care about outcomes. digital tools are means to an end. A platform that works from that lens with prescription and batteries included is something I want to see and think has latent value. A platform that orients a business around their industry vertical, with prescribed capabilities/goals, then deploys them all in a way that's outcome oriented, the deployment, data, UI, etc are materializations on top of the goal.
Anyway, wanted to get this out before I left the coffee shop. Happy to talk about this more, it's something I've been ruminating on for a while.
also: https://www.wordware.ai is the fastest company to raise some threshold of millions of dollars, something like that, had rapid adoption and they've pivoted their entire company to their new thing https://www.sauna.ai.
it's a good example because they're still very much an AI company, it's just that their initial traction was a "workflow builder" but strategically, they realized nobody wakes up in the morning wanting to build workflows. They want things done.
Sauna is the AI thing that just gets things done. They are betting their entire company on it. I found their story compelling https://www.wordware.ai/story albeit very long-winded =P
Check out self-coding harness `j` as well: https://news.ycombinator.com/item?id=48653476
A malleable coding agent app. Use Claude Code and Codex to build your projects and reshape y itself live.
Back on your idea itself:
Have you considered making this a first class hosted MCP plus enterprise-licensed plugin (which can contain an MCP) for Claude Cowork? A firm can do most of the ideas on your home page in Cowork if the firm provides its operators a starting skill and enforces a framework around that. But most firms are not qualified to bootstrap this, nor do they have spare employees to manage it.
A firm paying for Team or Enterprise (not Pro or Max!) Claude.AI (not Claude console / API), is likely to be a target customer.
And by speaking to that, that this bootstraps the right way firms actually get value from Claude, then you are targeting both the operators (who don't get to buy things) but also the people who pay for things and want the operators to get productive with that AI stuff so nobody gets mad the tokens burned up their annual budget.
I'd encourage you to play with what Anthropic is doing in Cowork. I believe they have the best vantage point right now for iterating how white collar workers (the no code crew) really try to do things.
hey, thanks a lot. I think you're right. I am currently working on integration with AI people are already using. I'm looking into claude cowork.
Very clean and professional website, congrats!
I'm wondering let's say I ask Appaca to build an automated lead follow-up tool. How would it actually build it? Would I need to iterate on it myself, or does it rely on predefined templates behind the scenes?
Basically, my question is how reliable are the generated tools in practice?
Also, does it support custom API integrations?
thanks!
it doesn't have a predefined templates. But, it was given a very strict development workflow based on React and shadcn for reliability. Then, I have an agent that will always do a technical research first, for example, it uses Firecrawl to get relevant implementation, then it will try to build the tool you need. It usually gives really accurate and functional tools according to your need. Most of the time, you won't need another iteration unless you want to add a few things, because you are not building a full blown SaaS for customer-facing products.
Yes, it support custom API integrations. The app uses e2b sandbox to run all functions (backend stuff). So, you can integrate with your own APIs / webhooks.
I am also working on connectors to help businesses connect with more of what they already use in their workflow. :)
How are you currently managing your back office / ops at the moment? Keen to hear your use case.
Cool product! For custom API integrations, you may want to check out integration providers that support auth/tool-calls/MCP/syncs for a large API catalog so your agent does not spend time building it.
Full disclosure: I work at Nango.
Nango enables agent and product API integrations for 800+ APIs. It is open source, code-based and has Skills to build, test, deploy API integrations with coding agents (like Claude/Gemini/Codex). Also supports custom-tools via MCP/APIs. Do check it out!
awesome.. thanks! It sounds amazing. I will check it out.
The tradie app space is ripe for deep customisation. Appaca might fill that. Each trade has specific requirements that vendors lack deep domain knowledge of.
that makes sense. Tradie space is what I have been looking into as well. I have been seeing a lot of ads from different new tradie apps these days. Everyone is trying to build an app for tradies for different purpose. I reckon it's probably a bit harder for them to adopt AI / tech. I need to have more conversations with them to better understand their workflow.
Thanks for sharing your story. Your third iteration looks polished and professional on the outset. I haven't used it, I'd like to comment purely on positioning and messaging:
Appaca seems to addresses the internal tools realm of medium+ sized businesses which carries a lot of competition because that's where sizable budget lives. This playbook requires strong targeted sales teams motion because Appaca need to connect the dots from Appaca -> business value. This is because your features are 1:1 technical capabilities, not direct value capture chains: spreadsheet to app, custom dashboard, custom CRM, app builder.
Now I may be totally off regarding Appaca, but I'd expect your sales to come from sales-teams and not product-led growth meaning the website itself doesn't convert people on its own without human touch/intervention. You noted that your previous products had crazy churn - this is my thinking why - because biz-ops tools are high investments even if they start light. A churned customer was not able to connect the value chain on their own.
All this to say, with the current approach and offering, Appaca is entirely a sales-lead motion. Nothing wrong with that at all, it just means that whatever is on the website is not the driving force, the sales team knows best what's landing, are they getting calls at all, are they getting calls but not closes, are they closing but customers churn later because they don't see value etc.
---
Ok that said, what's most interesting me is which ICP (ideal customer profile) to target in the first place with biz-ops tools. That space has a ton of surface area and we are nowhere close to an ideal end-state. For workflow automation and internal tools space, as said, heavily saturated because the motion and value capture is proven. For things like Lovable and the AI builders, these things exploded and proved out the indie entrepreneur space. I find it incredibly amazing how successful they've been. I personally want to deep dive into who their ICPs really are.
From a strategic upstart pov, there's got to be opportunity in smaller businesses in a way that wasn't economically viable before. There's a large chunk of businesses that are too small for any concept of a tech department; it's the owner using wix.com to build their website. This is a different problem all together but generally, in 2026 the fact that website builders are used by business owners to literally build websites, pages, with content, and images positioned, is far from ideal.
Businesses care about outcomes. digital tools are means to an end. A platform that works from that lens with prescription and batteries included is something I want to see and think has latent value. A platform that orients a business around their industry vertical, with prescribed capabilities/goals, then deploys them all in a way that's outcome oriented, the deployment, data, UI, etc are materializations on top of the goal.
Anyway, wanted to get this out before I left the coffee shop. Happy to talk about this more, it's something I've been ruminating on for a while.
also: https://www.wordware.ai is the fastest company to raise some threshold of millions of dollars, something like that, had rapid adoption and they've pivoted their entire company to their new thing https://www.sauna.ai.
it's a good example because they're still very much an AI company, it's just that their initial traction was a "workflow builder" but strategically, they realized nobody wakes up in the morning wanting to build workflows. They want things done.
Sauna is the AI thing that just gets things done. They are betting their entire company on it. I found their story compelling https://www.wordware.ai/story albeit very long-winded =P
hey, thanks a lot for your inputs. It's really helpful. Looking into WordWare story, it's very interesting.