README copy edits: trim 'in one breath' / 'three things'; soften cost claim to 'significant'

README.md

@@ -30,7 +30,7 @@ tags:
 > that runs on hardware you own — built entirely on **open models ≤32B**, with **OpenBMB
 > MiniCPM** as the load-bearing model (and fine-tuned for the domain).
 
-## 💡 The idea (in one breath)
+## 💡 The idea
 Retail back-offices drown in paperwork and report requests. **ERP-DocIQ** is an open-source,
 UiPath-style assistant that **reads your documents**, **answers questions about your ERP in
 plain English**, and **automates the boring clicks** — all on small models, no per-robot
@@ -44,7 +44,7 @@ fine-tune), and **slow to change** (new layouts wait on a closed retraining tool
 of that, every "what did we spend in Q2?" becomes a **BI ticket**. They wanted an AI-native,
 open, cheaper alternative they control.
 
-## 🛠️ The solution approach — three things, one Gradio app
+## 🛠️ The solution approach — one Gradio app
 1. **Read any document (OCR + IDP).** A hybrid pipeline — OCR → classify → extract → normalize →
    enrich (RAG) → validate → post / human-review — reads orders, receipts, invoices, contracts
    and complex multi-layer forms, **even messy scans/photos**, into structured ERP records.
@@ -80,7 +80,7 @@ knowledgebase (`results/erp_sft.jsonl`):
   execution. See `results/erp_finetune_report.json`.
 
 ## 📈 Benefits / value delivered
-- **70%+ lower inference cost** vs per-document RPA licensing (model routing + prompt caching).
+- **Significantly lower inference cost** vs per-document RPA licensing (model routing + prompt caching).
 - **No vendor lock-in, data stays on-prem** — open weights you can run, read and fine-tune.
 - **Self-service ERP analytics** (NLQ) deflects routine BI/report tickets off the queue.
 - **Reads documents classic OCR can't** — MiniCPM-V cuts character error **~5.6× vs Tesseract**