Spaces:
Runtime error
Runtime error
Make About section visible (not dropdown), remove Cline reference
Browse files
app.py
CHANGED
|
@@ -486,44 +486,28 @@ with gr.Blocks(css=custom_css, title="ARI Tool Builder") as app:
|
|
| 486 |
---
|
| 487 |
""")
|
| 488 |
|
| 489 |
-
|
| 490 |
-
|
| 491 |
-
### What This Is
|
| 492 |
-
|
| 493 |
-
This is a **working prototype** of a "Cline for Mental Health" β a platform where clinicians can vibe-code
|
| 494 |
-
their own AI tools using natural language, with relational ethics baked into the infrastructure.
|
| 495 |
-
|
| 496 |
-
**What exists now:**
|
| 497 |
-
- ARI Engine system prompt (the ethical infrastructure)
|
| 498 |
-
- Tool Builder interface (describe your tool β generate architecture)
|
| 499 |
-
- Preview mode (test the generated tool)
|
| 500 |
-
- Export (copy system prompt for use in ChatGPT, Claude, etc.)
|
| 501 |
-
|
| 502 |
-
**What's missing for true vibe-coding:**
|
| 503 |
-
- **Dynamic deployment** β Tool lives on the platform, not copy-pasted elsewhere
|
| 504 |
-
- **Shareable client links** β Client gets a URL, no ChatGPT account needed
|
| 505 |
-
- **Clinician dashboard** β See/manage/iterate on created tools
|
| 506 |
-
|
| 507 |
-
### The Vision
|
| 508 |
-
|
| 509 |
-
Imagine: A therapist describes a between-session tool in plain language. The platform generates it with
|
| 510 |
-
ARI guardrails embedded. One click deploys it. The therapist texts a link to their client. Done.
|
| 511 |
-
|
| 512 |
-
No code. No prompt engineering. No ChatGPT accounts for clients. Just clinician-configured,
|
| 513 |
-
ethically-grounded tools that extend the therapeutic relationship into the spaces between sessions.
|
| 514 |
|
| 515 |
-
|
|
|
|
| 516 |
|
| 517 |
-
|
| 518 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 519 |
|
| 520 |
-
|
|
|
|
| 521 |
|
| 522 |
-
|
| 523 |
-
|
|
|
|
| 524 |
|
| 525 |
-
|
| 526 |
-
|
| 527 |
|
| 528 |
with gr.Tabs():
|
| 529 |
|
|
|
|
| 486 |
---
|
| 487 |
""")
|
| 488 |
|
| 489 |
+
gr.Markdown("""
|
| 490 |
+
### About This Prototype
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 491 |
|
| 492 |
+
This is a **working prototype** β a platform where clinicians can vibe-code their own AI tools
|
| 493 |
+
using natural language, with relational ethics baked into the infrastructure.
|
| 494 |
|
| 495 |
+
| What exists now | What's next |
|
| 496 |
+
|-----------------|-------------|
|
| 497 |
+
| ARI Engine system prompt (ethical infrastructure) | **Dynamic deployment** β tools live on platform |
|
| 498 |
+
| Tool Builder interface (describe β generate) | **Shareable client links** β no ChatGPT needed |
|
| 499 |
+
| Preview mode (test generated tools) | **Clinician dashboard** β manage/iterate tools |
|
| 500 |
+
| Export (copy for use in Claude, ChatGPT, etc.) | |
|
| 501 |
|
| 502 |
+
**The vision:** A therapist describes a between-session tool in plain language. The platform generates it
|
| 503 |
+
with ARI guardrails embedded. One click deploys it. The therapist texts a link to their client. Done.
|
| 504 |
|
| 505 |
+
**Interested in funding, collaborating, or piloting?**
|
| 506 |
+
Jocelyn Skillman, LMHC β [HuggingFace](https://huggingface.co/jostlebot) |
|
| 507 |
+
[Substack](https://jocelynskillman.substack.com) | [LinkedIn](https://linkedin.com/in/jocelynskillman)
|
| 508 |
|
| 509 |
+
---
|
| 510 |
+
""")
|
| 511 |
|
| 512 |
with gr.Tabs():
|
| 513 |
|