# DON BUG GPT

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Alan Herrera](https://cerebralvalley.ai/u/Alan01)
- **GitHub:** https://github.com/AlanHerrera01/INTI-IA-META-HACKATHON.git
- **Demo video:** https://youtu.be/8NAxNll7Q-0
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1435

INTI AI is a local-first desktop agent that gives one operator an auditable control surface for work performed on a Windows PC. A bilingual Spanish/English dashboard pairs with an agent on the operator's machine. From it the operator can:

- Pair a computer with a one-time code, inspect installed applications, grant or revoke per-device permissions, and see device state.
- Capture an allowlisted web viewport and, with a configured Meta key, have Muse Spark turn it into a typed scene of elements, UI state and uncertainties.
- Convert a goal and constraints into a typed plan with ordered actions, targets, preconditions, expected results and risk levels; unsafe proposals are rejected and planning never authorizes execution.
- Approve the exact plan by SHA-256 digest, with separate confirmation for high-risk actions; any edit invalidates approval.
- Execute approved actions in the synthetic Chromium inventory sandbox or on the local PC: create and read back text files, request Notepad or an approved HTTP(S) page, and launch authorized applications without arguments. Progress arrives as live events and per-action receipts; browser sessions pause and resume, remaining work can be cancelled, and history exports as JSON.
- Generate a document dossier in a fresh task folder (Word quotation, Excel budget with live formulas, native chart and reconciliation sheet, print-ready PDF, text summary and SHA-256 manifest), then reopen it to check fields, totals, structure and hashes.
- Diagnose failed sandbox executions with a bounded repair plan that requires fresh approval and never replays actions automatically.
- Verify sandbox outcomes independently: re-read persisted state, evaluate explicit criteria, collect hash-checked evidence, and issue VERIFIED_SUCCESS, VERIFIED_FAILURE or INCONCLUSIVE with JSON/HTML reports.
- Review measured latency, throughput and verification results, with unavailable metrics left blank instead of estimated.

It is a single-operator local release. The agent writes only inside the approved workspace and task folder, never overwrites, signs or sends files, and exposes no shell, deletion or arbitrary-executable command. Desktop screenshot capture, independent desktop-vision verification and automatic model calls are not implemented or disabled by default.

## More from Meta Global AI Developer Hackathon

- [PolymathSolo](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1432)
- [muse-fieldnotes](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1433)
- [PDF2PPt Study](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1434)
- [Testigo](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1436)
- [solo-sai](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1437)
- [Veilant.com](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1438)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1435. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt