---
title: "A Claude procurement agent cut a Philippine bakeshop network's quote comparisons from hours to minutes"
person: "Crisanta Tatad (Julie's Franchise Corporation)"
tools:
  - "Claude Sonnet 5"
  - "Amazon Bedrock AgentCore"
  - "AWS"
country: "Philippines"
category: "Get tasks done"
category_slug: get-tasks-done
proof:
  - label: "Read Computrade's case study on Julie's Franchise Corporation"
    url: "https://www.computradetech.com.ph/blog/julies-franchise-corporation-cuts-procurement-decision-time-by-95-with-claude/"
date: 2026-10-29
date_posted: 2026-10-21
as_claimed: "The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome."
url: "https://agentstories.org/stories/julies-franchise-claude-bid-comparison.html"
markdown_url: "https://agentstories.org/stories/julies-franchise-claude-bid-comparison.md"
site: "Agent Stories by Solopreneur Code"
---

# A Claude procurement agent cut a Philippine bakeshop network's quote comparisons from hours to minutes

Crisanta Tatad (Julie's Franchise Corporation) · Philippines · Claude Sonnet 5, Amazon Bedrock AgentCore, AWS

## What the agent did

Julie's Franchise Corporation runs the franchise network for more than 600 Julie's bakeshops across the Philippines. Its partner Computrade Technology Philippines built a procurement agent on Claude Sonnet 5 and Amazon Bedrock AgentCore that reads each supplier bid, weighs pricing and terms, and drafts a side-by-side recommendation. Procurement officers review, revise and approve every decision. The source is Computrade's own case study.

## Result, as claimed

"There were less time to compare 3+ quotations. From 2 to 3 hours down to 5 to 10 mins using the new AI application," said Crisanta Tatad, National Procurement Head. The case study says supplier decision time "has fallen by 95% with no additional procurement headcount".

> The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome.

## Proof

- [Read Computrade's case study on Julie's Franchise Corporation](https://www.computradetech.com.ph/blog/julies-franchise-corporation-cuts-procurement-decision-time-by-95-with-claude/)

## Try it yourself

A Claude prompt that turns three or more supplier quotes into one side-by-side comparison and a recommendation you check and approve.

Prompt:

```text
I am choosing a supplier for [item or service] for my [business]. Attached are [3] quotes. Build one table that compares each supplier on unit price, minimum order, delivery time, payment terms, returns or warranty, and any extra fees. Use only what is in the quotes. Where a quote leaves something out, write "Not stated" instead of guessing. Convert prices to [currency] per [unit] so they compare fairly. Then recommend one supplier for my priorities [price, reliability, speed], explain why in 3 bullet points, and list the questions I should ask each supplier before I decide.
```

Tools:

- [Claude](https://claude.ai): Reads PDF and photo quotes. The story used Claude Sonnet 5
- [ChatGPT](https://chatgpt.com): Alternative that also reads uploaded quotes
- [Amazon Bedrock](https://aws.amazon.com/bedrock/): What the story's partner built on. Only worth it for a shared team tool

Steps:

1. Collect the quotes for one purchase as PDFs or photos.
2. Upload them to Claude with the prompt.
3. Check every number in the table against the original quotes.
4. Send the follow-up questions, then make the final call yourself.

Watch out: AI can misread a figure in a scanned quote, so check prices and terms against the source before you sign, and leave out any pricing a supplier asked you to keep confidential.

## More

- [This story as a web page](https://agentstories.org/stories/julies-franchise-claude-bid-comparison.html)
- [More stories: Get tasks done](https://agentstories.org/categories/get-tasks-done.html)
- [More stories from Philippines](https://agentstories.org/countries/philippines.html)
- [More stories that use AWS](https://agentstories.org/tools/aws.html)
- [Every story, indexed for AI assistants](https://agentstories.org/llms.txt)
