I just fixed and rebuilt an entire AI automation flow without opening the flow editor once.
Here's what happened:
We have a YouTube script generation pipeline on Serenities. It takes a keyword (or YouTube URLs), generates an outline, then writes each section with precise word counts. Two branches one for URLs, one for direct topics.
The URL branch was broken. Not obviously broken. Subtly broken it was jumping straight from transcript cleansing to a single Claude call with no outline step, no section iteration, no word count targeting. Just a raw prompt that guessed at length every time.
I asked Claude to check it via MCP.
Within seconds it had read the entire flow every node, every edge, every config. It found:
- A broken template variable resolving to [undefined] instead of the word count
- Extended thinking enabled on a cleansing node (pointless, just burning tokens)
- The URL branch missing 7 nodes that the keyword branch had
- The MCP help guide serving 5 thin topics with almost no real documentation
Then still without me touching the UI it:
Added 7 new nodes to the URL branch (outline prompt, Claude outline generate, JSON cleaner, iterator,
section prompt, section writer, text aggregator)
Rewired all the edges correctly
Updated the webhook response to pull from the new pipeline
Rewrote all 5 MCP help topics with complete documentation utility node configs, template variable syntax,
Claude toolInputJson templates, debugging guides, everything
One conversation. Zero UI clicks. The flow went from broken to production-ready.
This is what MCP actually unlocks. Not just "ask AI to explain your code." Ask AI to read your live
infrastructure, reason about what's wrong, and fix it programmatically, precisely, at the API level.
We built MCP support into Serenities so AI agents can build and manage flows on behalf of users. Today I used
it on our own platform. It worked exactly as intended.
The future of automation isn't drag-and-drop. It's conversational.
serenities
RiteKit Company Logo API
Upvoted, but where is the form to invite 3 and get the 3 months of your starter plan?
serenities
@osakasaul You can simply share this with your friend in social media and send screenshot at support@serenitiesai.com to get the free paid plan.
RiteKit Company Logo API
Still testing? Create App doesn't work.
serenities
@osakasaul that error is because you are not subscribed to any plan, by default signing up won't create a plan for you, you will have to https://app.serenitiesai.com/account and select a plan. Since, you are entitled for free pro plan, let me contact support in you behalf so your plan is activated.
RiteKit Company Logo API
@nishant_lamichhane Great, and thank you!
I trust code d/l is possible, and hosting with vercel, etc., can be done? Code editing? Github inegration or connection manually?
serenities
@osakasaul For now, you can host pure frontend apps (without Serenities features) on Vercel. We're actively working on two things:
1. SDK + API keys - Deploy to Vercel and connect to Serenities backend (database, files, flows)
2. Full app export - Download and self-host the entire stack Both coming very soon! 🚀
Bottom line: The SDK integration with Vercel is ~90% done (backend ready), but needs the user-facing bits (API key UI, npm package, docs) before users can actually use it.
serenities
@osakasaul You now have free access to the paid plan.
Migma AI
bringing your own subscription is a huge flex for power users. 🧠 no more counting tokens like it's 2023. how are you handling the context window limits when projects get big? 🚀
serenities
@adam_lab If you use AI like claude.ai, they automatically handle compaction. Also, you can alwaysinitiate a new chat on any AI platform like OpenAI, Claude, or Gemini.
For instance, both Claude and Gemini now support a 1
million token context window.
Hey,
I’ve been exploring the app, and I love your idea. However, when I click on 'Create App,' the screen gets stuck, which might be a rendering issue. I’m excited to check this out, so I hope it can be resolved soon.
serenities
@hassan_bajwa Hi Sassan, could you please send us the screenshot, and try once again to see if it works or not. You can also mail us at support@serenitiesai.com
ChatPal
Looks powerful! So you bring your own OpenAI key?
serenities
@daniele_packard No, not API keys! You connect your existing AI
subscription (like ChatGPT Plus or Claude Pro).
Why this matters: API keys charge per-prompt (~$0.01-0.10 each), which adds up to $200-500/mo for heavy use. With your $20/mo subscription, you get unlimited prompts. That's 10-25x cheaper for AI usage.
You pay us $24/mo for the platform (vibe coding +
automation + database + storage).
You pay OpenAI/Anthropic $20/mo for unlimited AI. Total: $44/mo instead of $200-500/mo with API-based platforms.
serenities
@daniele_packard No, not API keys! You connect your existing AI
subscription (like ChatGPT Plus or Claude Pro).
Why this matters: API keys charge per-prompt
(~$3-75 each depending on model), which adds up to $200-500/mo for
heavy use. With your $20/mo subscription, you get unlimited prompts. That's 10-25x cheaper! You pay us $24/mo for the platform (vibe coding +
automation + database + storage). You pay OpenAI/Anthropic $20/mo for unlimited AI. Total: $44/mo instead of $200-500/mo with API-based platforms.
Great idea to be able to bring your Claude Code subscription. Can't wait to try it out!
serenities
@willsmithte you can signup to Serenities AI for free at https://serenitiesai.com/. After signing up go to Plan on Account page https://app.serenitiesai.com/account?tab=plan and select free plan. We cannot wait to see what you build with Serenities AI