# DarFlow Agent

- **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:** [zakaria chirah](https://cerebralvalley.ai/u/Zakariachirah)
- **GitHub:** https://github.com/Zakariachirah/darflow-agent
- **Demo video:** https://youtu.be/1eJox7rG1Hk
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/63

DarFlow Agent — an AI agent that runs the WhatsApp front desk and the expense back-office of a small Moroccan riad, built on Meta's Muse models.

Pre-existing: DarFlow, my riad management software (closed source, not in the repo). Built this week: DarFlow Agent (everything in the repo), its WhatsApp agents and the small importer added to DarFlow (copied in darflow-importer/ for review). Timeline in the README; asked the organizers in #questions.

The problem: Morocco has thousands of riads run by one manager and a few staff. Guests write on WhatsApp in every language at every hour, and expenses arrive as paper bills or are said out loud in Darija. I'm the manager of a riad: this is my daily life.

DarFlow Agent handles both on one WhatsApp number:
• Guest concierge: answers in the guest's language (Spanish, German, French, English, Darija in Latin letters), books dinner, records arrival times and transfers, resends the check-in link through tool calls, handles voice notes, and hands off prices, discounts and complaints to the manager instead of inventing answers.
• Expense back-office: staff send a photo or a Darija voice note. SAM 3.1 finds and crops every sheet of paper in the photo, Muse Spark reads each crop (strict JSON schema) and re-checks the arithmetic and VAT, a deterministic policy flags duplicates, quotes, fakes and revenue documents. The manager replies "OK" and the expense lands in DarFlow, the riad's real software, through its own business rules.
• Morning brief (added 1 Nov): every day at 08:00 the agent reviews the riad's day on its own, sends the manager one WhatsApp message (urgent / today / good to know) and proposes actions; the manager answers "1" or "tout" and the agent writes to each guest in their language. Facts and actions are built by code; Muse Spark ranks and phrases them; code checks every line against its fact.

Design principle: the model reads and talks; the code enforces (3 h dinner notice, a guest only sees their own booking, fakes and quotes are never booked).

Results: guest agent 21/21 live scenarios (incl. prompt injection, privacy probes, cancellation and complaint hand-offs, Darija in Arabic script); morning brief 3/3 live runs with 0 lines needing correction; documents 6/6 on real phone photos (incl. catching a supplier's VAT error); guardrail tests 16/16; DarFlow's full suite passes with the importer (248 tests).

## More from Meta Global AI Developer Hackathon

- [VerifEye](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/60)
- [gradepack](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/61)
- [Nexa](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/62)
- [Meaning Check](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/64)
- [Sam Williams](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/65)
- [MoyaBiz AI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/66)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/63. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt