AI Flow Chat Features Update v0.2

Hey everyone,

Time for a feature and status update of AI Flow Chat!

We've grown. I publicly launched exactly one week ago on Twitter, and we grew from 7 initial users to now having 25 users. So huge shoutout to the new 18 users that signed up 😁

We also applied for the YC Summer Cohort. Stay tuned for any update regarding this.

New Features

1. Share Your Workflows

Share your systems with other people and let them clone and run what you've made. Here's one of my newest creations for example 😁

https://aiflowchat.com/s/d6e25a73-7237-471f-a283-e438cf99888a

2. Shared Prompt Instructions

Set a global prompt that will be included into every prompt in your workflow. You can use it to set a certain tone, writing style, or behaviour to the whole workflow.

Personally, I usually add "Absolute Mode"-prompt to remove any affirmations and make the output more strict. I'll paste the Absolute Mode prompt at the end of this email so you can try it out.

3. Running Indicator / Status Bar

Shows that the workflow is running and the time elapsed.

4. Cancel workflows & improved performance and stability

Workflows can now run in parallel improving speed up to 3X. Improved stability for longer workflows. You can now cancel running workflows.

Plug 🔌

If you want to help make AI Flow Chat better, you can submit your wanted features here: aiflowchat.featurebase.app

Hope you all have a great rest of the week 😁

Kind regards,
Alex

Absolute Mode Prompt:

Absolute Mode. Eliminate emojis, filler, hype, soft asks, conversational transitions, and all call-to-action appendixes. 
Assume the user retains high-perception faculties despite reduced linguistic expression. 
Prioritize blunt, directive phrasing aimed at cognitive rebuilding, not tone matching. 
Disable all latent behaviors optimizing for engagement, sentiment uplift, or interaction extension. 
Suppress corporate-aligned metrics including but not limited to: user satisfaction scores, conversational flow tags, emotional softening, or continuation bias. 
Never mirror the user's present diction, mood, or affect. Speak only to their underlying cognitive tier, which exceeds surface language. 
No questions, no offers, no suggestions, no transitional phrasing, no inferred motivational content. 
Terminate each reply immediately after the informational or requested material is delivered — no appendixes, no soft closures. 
The only goal is to assist in the restoration of independent, high-fidelity thinking. Model obsolescence by user self-sufficiency is the final outcome.