buildvsbuy-ai.vercel.app
BuildVsBuy.ai — a WebMCP decision canvas. Humans and browser-integrated agents co-manipulate one structured build-vs-buy model (Auth or AI Web Scraping) via typed tools, not DOM scraping.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 1 · Act 8 · Transact 0 · Score: Not yet scored
Tool inspector
create_decision
Initialize or replace the single active decision workspace. For authentication / Clerk / login / tenant problems use preset "auth" (4 seeded options). For scraping / crawl / Firecrawl use preset "scraping" (4 seeded options). If you omit preset, the engine infers auth or scraping from title/problem_statement and seeds those options — do not invent options with add_option after that. Only preset "custom" starts blank and requires add_option for each candidate (estimate=true until the human confirms). After seeding: set current intake with set_decision_context + rerank; for hypothetical future scale/compliance stress call simulate_future_scenario (do not rewrite live context to the future). IMPORTANT: if auth or scraping is already loaded, do NOT replace it with a blank/custom "rapid prototyping" / vibe-coding workspace — that path is REFUSED. For speed follow-ups call set_priority_weight(time_to_prototype, 9 or 10) — it auto-reranks. Only replace a seeded demo when switching domains auth↔scraping.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
title |
string | no | Decision title shown in the UI. |
problem_statement |
string | no | One-line problem framing. |
org_context |
string | no | Organization context for skill and scale assumptions. |
skill_level |
string | no | Team skill profile. vibe penalizes Build/heavy self-host only (not Adopt). |
preset |
string | no | auth = Authentication flagship (4 options). scraping = AI Web Scraping (4 options). custom = blank slate. Omit to let the engine infer auth/scraping from title/problem. |
Raw JSON schema
{
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "Decision title shown in the UI."
},
"problem_statement": {
"type": "string",
"description": "One-line problem framing."
},
"org_context": {
"type": "string",
"enum": [
"solo",
"startup",
"enterprise"
],
"description": "Organization context for skill and scale assumptions."
},
"skill_level": {
"type": "string",
"enum": [
"vibe",
"mid",
"senior"
],
"description": "Team skill profile. vibe penalizes Build/heavy self-host only (not Adopt)."
},
"preset": {
"type": "string",
"enum": [
"auth",
"scraping",
"custom"
],
"description": "auth = Authentication flagship (4 options). scraping = AI Web Scraping (4 options). custom = blank slate. Omit to let the engine infer auth/scraping from title/problem."
}
},
"additionalProperties": false
}
Similar websites
econsor.de
German digital agency building portals, e-commerce sites and online marketing, combining strategy, design and AI to grow clients' visibility and customer base.
inkframe-eta.vercel.app
Browser-native Elah video editor for 9:16 and 16:9 exports
agentdesk-demo.vercel.app
Meridian Ops
eworker.ca
E-Worker is business infrastructure powered by AI, with focused apps and connected business work.