# PakForge

- **Event:** [RAISE Summit Hackathon](https://cerebralvalley.ai/e/raise-summit-hackathon)
- **When:** Jul 4 at 9:00 AM – Jul 5 at 7:00 PM (GMT+2)
- **Where:** Paris, France
- **Team:** [fakhar alamgir](https://cerebralvalley.ai/u/Revolutionary), [Raheela Daud](https://cerebralvalley.ai/u/Mam), [Zain Qamar](https://cerebralvalley.ai/u/Anjaan)
- **GitHub:** https://github.com/prime-programmer-ar/DecisionForge
- **Demo video:** https://youtu.be/ucFQDf-gvBY
- **Gallery:** https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/62

DecisionForge is an agentic AI investigation engine built for enterprise decision-making. Unlike standard RAG or chatbots that answer immediately from surface-level retrieval, DecisionForge behaves like a human analyst — it plans a multi-step investigation, retrieves and reranks evidence across 65 cross-referenced enterprise documents (incident reports, ADRs, policies, Jira tickets, Slack threads, meeting notes), and reasons step-by-step until it has genuinely exhausted the evidence.
The core loop: Plan → Retrieve → Rerank → Evaluate → Continue or Stop — repeating across 3–4 document hops until the Evaluator decides evidence is complete. Every number the system produces (confidence score, evidence found/used/rejected/missing) is computed deterministically in Python — never hallucinated by the model. The final output is a structured ACCEPTED / REJECTED / NEED_MORE_CONTEXT verdict with full citations, a reasoning trace, a generated Executive Memo, and a Follow-up Ticket.
Built on Vultr Serverless Inference using two specialized models: Qwen/Qwen3.6-27B for planning, evaluation, and decision reasoning — and VultronRetrieverCore-Qwen3.5-4.5B for semantic evidence reranking. Results stream live to the frontend via SSE with a real-time investigation graph, evidence panel, and downloadable artifacts.

## More from RAISE Summit Hackathon

- [Echo](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/59)
- [Sentinel](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/60)
- [Anukriti](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/61)
- [KACM](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/63)
- [Avosearch](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/64)
- [MIRA](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/65)

---

Markdown version of https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/62. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt