add reports

IBM_Hackathon_Report/ibm_ai_tools_usage.md

@@ -0,0 +1,79 @@
+# IBM watsonx Usage Report
+
+## Overview
+ClaimCheck AI leverages IBM watsonx as the backbone for claim verification.  
+The system uses IBM watsonx.ai’s large language models and embedding capabilities to handle:
+1. **Text Retrieval (RAG)**
+2. **Claim Verification**
+3. **Evidence Reranking**
+4. *(Optionally)* IBM Speech-to-Text for transcription.
+
+---
+
+## Agents & IBM Integration
+
+### 1. **Transcriber Agent**
+- **Goal**: Convert audio from Zoom/phone calls to text.
+- **IBM Usage**: Can integrate IBM Speech-to-Text (STT) to provide enterprise-grade transcription accuracy.
+- **Inputs**: WAV/MP3/OGG audio file.
+- **Outputs**: JSON array of `{ speaker, start, end, text }`.
+
+---
+
+### 2. **Claim Extractor Agent**
+- **Goal**: Identify factual statements in the transcript.
+- **IBM Usage**: Powered by IBM watsonx.ai LLM (Prompt Lab) to output JSON with `{ claim_text, speaker, start, end }`.
+
+---
+
+### 3. **Retriever Agent**
+- **Goal**: Retrieve relevant knowledge base snippets to support or refute claims.
+- **IBM Usage**:
+  - **IBM Text Embeddings**: Generates semantic vector representations of KB snippets and claims.
+  - **FAISS Vector Search**: Finds top-K relevant evidence from local index.
+  - **IBM Rerank API**: Orders results by relevance.
+- **Benefit**: Reduces false positives in evidence retrieval.
+
+---
+
+### 4. **Verifier Agent**
+- **Goal**: Cross-check each claim against retrieved evidence.
+- **IBM Usage**: LLM prompt to classify as "Supported", "Contradicted", or "Unverifiable".
+- **Output**: Verdicts with reasoning.
+
+---
+
+### 5. **Summarizer Agent**
+- **Goal**: Produce final human-readable report.
+- **IBM Usage**: LLM summarization model to combine claims, evidence, and verdicts into structured output.
+
+---
+
+## Deployment & Scalability
+While deployment is not in the scope of this hackathon, in a production setting:
+- **IBM watsonx.ai models** can run in a secure IBM Cloud environment.
+- **IBM Orchestrate** could be used to automate claim verification workflows (triggered after each meeting).
+- **IBM Code Assistant** could accelerate code integration for enterprise clients.
+- **Scalable Vector Store**: IBM Cloud Object Storage could hold large KB datasets for retrieval.
+
+---
+
+## Required Capabilities & Datasets
+- **KB Sources**: SLA documents, compliance policies, contractual clauses, product documentation.
+- **Integrations**: Zoom/Teams API for call recordings.
+- **Agents**: 5 specialized agents as described.
+- **IBM Services**:
+  - Text Embeddings API
+  - Text Rerank API
+  - LLM Prompting via Prompt Lab
+  - (Optional) Speech-to-Text
+
+---
+
+## Why IBM watsonx is Critical
+- **Enterprise readiness** — Secure, compliant AI processing.
+- **High accuracy retrieval** — Embeddings + Rerank reduce noise.
+- **Custom KB adaptability** — Works across industries.
+- **Unified ecosystem** — AI models, APIs, and orchestration tools in one platform.
+
+By combining these capabilities, ClaimCheck AI transforms unstructured meeting dialogue into **evidence-backed, compliance-ready reports** in near real-time.

IBM_Hackathon_Report/problem_statement.md

@@ -0,0 +1,76 @@
+# Problem & Solution Statement
+
+## Problem
+In industries where critical decisions depend on the accuracy of verbal communication—such as finance, healthcare, legal compliance, and customer support—important claims made during meetings or calls often go unverified.  
+For example:
+- A customer service rep claims a service has "99.99% uptime."
+- A vendor promises "P95 latency under 200 ms globally."
+- A team assures compliance with "30-day data retention policies."
+
+These statements, if untrue or unsupported, can result in:
+- Legal liabilities
+- Financial loss
+- Reputation damage
+- Regulatory penalties
+
+Existing meeting transcription and summarization tools do not go far enough — they focus on creating readable notes, but do not actively **validate** or **cross-check claims** against authoritative knowledge bases.
+
+---
+
+## Solution
+We have built **ClaimCheck AI**, an *agentic AI* system that automatically:
+1. **Transcribes** conversations (speech-to-text).
+2. **Extracts** claims made in the dialogue.
+3. **Retrieves** relevant evidence from a curated Knowledge Base (KB) using IBM watsonx embeddings and reranking.
+4. **Verifies** whether each claim is supported, contradicted, or unverifiable.
+5. **Summarizes** the findings in a structured, auditable report.
+
+---
+
+## Target Users
+- **Compliance Officers** – Automatically flag unsupported statements in regulated industries.
+- **Enterprise Managers** – Validate vendor promises and internal KPIs.
+- **Customer Success & Support Teams** – Ensure commitments to customers are accurate.
+- **Legal Teams** – Use as supporting evidence for contractual disputes.
+
+---
+
+## User Interaction Flow
+1. **Upload a call recording or connect via Zoom/phone integration**.
+2. The platform transcribes the audio.
+3. An AI claim extractor detects possible factual statements.
+4. IBM watsonx-powered retrieval finds the top-matching KB evidence.
+5. A verifier agent cross-checks claims against evidence.
+6. A final report is generated with:
+   - List of claims
+   - Associated evidence
+   - Verdict: Supported / Contradicted / Unverifiable
+
+---
+
+## Creativity & Uniqueness
+Unlike traditional meeting summarizers:
+- **Evidence-backed summaries** — not just "what was said," but "whether it’s true."
+- **Multi-agent pipeline** — dedicated agents for transcription, claim extraction, retrieval, verification, and summarization.
+- **Scalable KB integration** — supports industry-specific compliance rules, SLAs, and historical records.
+- **Audit trail** — every verdict links back to the evidence snippet.
+
+This approach moves beyond passive transcription to **active truth verification in real time**.
+
+---
+
+## Agentic AI in Action
+ClaimCheck AI works as a *multi-agent system*:
+1. **Transcriber Agent** – Converts speech to text (IBM Speech-to-Text possible).
+2. **Claim Extractor Agent** – Uses LLM prompting to detect factual statements.
+3. **Retriever Agent** – Uses IBM watsonx text embeddings + FAISS + IBM reranker.
+4. **Verifier Agent** – Cross-references claims with evidence and generates verdicts.
+5. **Summarizer Agent** – Produces structured human-readable reports.
+
+---
+
+## High Impact
+ClaimCheck AI could:
+- Prevent false compliance reporting in regulated industries.
+- Detect SLA breaches before they become customer escalations.
+- Save legal teams countless hours in discovery and evidence-gathering.

README.md

@@ -1,6 +1,6 @@
 # ClaimCheck.AI — Agentic Fact Verification for Calls
 
-**ClaimCheck.AI** is an agentic AI pipeline that turns meeting audio (Zoom/phone) into an evidence-backed report:
+**ClaimCheck.AI** is an multi-agent AI platform that turns meeting audio (Zoom/phone) into an evidence-backed report:
 1) **ASR Agent** → transcript + timestamps  
 2) **Claim Extraction (watsonx.ai LLM)** → JSON claims  
 3) **Evidence Retrieval (watsonx.ai Embeddings + FAISS + optional Rerank)** → KB hits