---
title: "Decision Matrix Extractor Prompt: generate Markdown trade-off tables with sharp threshold rules."
description: "Download the Decision Matrix Extractor JSON preset for Vezz me. Highlight technical comparisons, vendor specs, or debate threads to generate a Markdown trade-off table."
canonical_url: "https://vezz.me/prompts/decision-matrix-extractor/"
type: "pseo-prompts"
category: "prompts"
topic: "Trade-Off & ADR Preset"
intent: "Best for tech leads, architects, product managers, and founders writing ADRs, PRDs, and vendor comparisons."
---

# Decision Matrix Extractor Prompt: generate Markdown trade-off tables with sharp threshold rules.

Download the Decision Matrix Extractor JSON preset for Vezz me. Highlight technical comparisons, vendor specs, or debate threads to generate a Markdown trade-off table.

> **Best fit:** Best for tech leads, architects, product managers, and founders writing ADRs, PRDs, and vendor comparisons.

## Live Webpage Walkthrough

- **Source:** Web Architecture Guide — Server-Sent Events (SSE) vs WebSockets (`web.dev/articles/eventsource-basics`)
- **Recommended Context Mode:** Detailed

**Highlighted Passage:**
> Server-Sent Events (SSE) run over standard HTTP/1.1 or HTTP/2 connections and support automatic reconnection via Last-Event-ID, but only allow unidirectional server-to-client text streaming. WebSockets upgrade the connection to a full-duplex framing protocol supporting binary and text frames in both directions, but require custom heartbeat/reconnect logic and stateful load-balancer routing.

**User Question (Shortcut):** "Build a Markdown decision matrix with sharp threshold rules and 18-month dealbreakers."

**Vezz me On-Screen Answer:**
| Dimension | Server-Sent Events (SSE) | WebSockets |
| :--- | :--- | :--- |
| **Directionality** | Unidirectional (Server -> Client) | Full-Duplex (Bidirectional) |
| **Proxy & Firewall Friendliness** | Native HTTP/2 (zero upgrade blocks) | Custom `Upgrade` (blocked on some L7 proxies) |
| **Reconnection** | Built-in (`Last-Event-ID`) | Manual (must code backoff + resync) |
| **Payload Format** | UTF-8 Text only | Binary (`ArrayBuffer`) + Text |

- **Choose SSE when**: Streaming LLM tokens, notifications, or live feeds where client actions happen <1/sec via normal `POST`.
- **Choose WebSockets when**: Building sub-50ms bidirectional apps (multiplayer games, collaborative canvas, raw audio).
- **18-Month Dealbreaker**: SSE fails if HTTP/2 is disabled (6-tab HTTP/1.1 limit); WebSockets hurt during stateful rolling deploys.

**Suggested Follow-Ups:**
- "Add WebTransport (HTTP/3) as a third column in this table."
- "How do AWS ALB idle timeouts affect SSE vs WebSockets?"

## Custom Prompt Preset for Vezz me

- **Preset Name:** Decision Matrix Extractor
- **Recommended Context Level:** Detailed
- **JSON Preset Download:** https://vezz.me/prompts/presets/decision-matrix-extractor.json

```text
Synthesize the selected text into an objective, high-signal Decision Matrix: 1) Markdown Trade-Off Table: compare the options across Primary Strength, Operational Complexity, Cost/Scaling Cliff, Lock-In Risk, and Worst Failure Mode, 2) Sharp Decision Rules (No 'It Depends'): write explicit threshold rules ('Choose [Option A] when [specific condition/volume]' and 'Choose [Option B] when [specific condition/volume]'), and 3) 18-Month Dealbreakers: state the #1 reason teams migrate *away* from each option 18 months later.
```

**Why it works:** Explicitly forbids generic 'both have pros and cons, it depends' filler and forces concrete quantitative/architectural rules plus 18-month migration regrets.

## Step-by-step workflow

1. **Download and import the Decision Matrix Extractor JSON**: Save `decision-matrix-extractor.json` and import it via the Vezz me extension popup.
2. **Highlight a technical comparison, doc page, or practitioner thread**: Select the text discussing two or more approaches (or ask to compare the highlighted tool against a named alternative).
3. **Copy the Markdown table directly into your ADR, PRD, or Notion doc**: The output is formatted in clean GitHub-Flavored Markdown ready for engineering or product docs.

## Replace 'It Depends' with concrete threshold rules

The most frustrating answer an AI can give is 'Both Option A and Option B have pros and cons; it depends on your use case.'

- Forces concrete threshold rules based on request rate, payload format, consistency SLA, or team size
- Surfaces the **18-Month Dealbreaker**—the operational pain point you only discover after running a tool in production for a year
- Outputs clean Markdown tables that paste natively into GitHub, Notion, Linear, and Confluence

## Frequently asked questions

### What if the highlighted page only talks about ONE tool?

If you highlight documentation for just one tool (e.g., Kafka), Vezz me will automatically compare it against its primary industry alternatives (e.g., RabbitMQ / SQS / Postgres queues) or whatever alternative you name.

### Can I paste the Markdown output into GitHub PRs and Notion?

Yes—both Notion and GitHub render the Markdown table natively when pasted.

### Is this preset included in the Master Pack?

Yes, download the Master Prompt Pack to import all 22 presets at once.

## Related guides

- [Compare Two Tools or Frameworks Workflow](https://vezz.me/use-cases/compare-two-tools-or-frameworks-on-page/): Step-by-step guide to evaluating libraries and SaaS vendors in the browser.
- [RFC & System Design Critic Preset](https://vezz.me/prompts/rfc-and-system-design-critic/): Stress-test the winning architecture choice for failure modes.
- [Vezz me for Product Managers](https://vezz.me/for/product-managers/): How PMs use Vezz me for competitive matrices and PRDs.
- [Vezz me for Founders & Operators](https://vezz.me/for/founders-and-operators/): Vendor evaluation and operational decision workflows.