Our work

We build things
that actually work.

From AI infrastructure used by developers worldwide to growth systems for ambitious local businesses. Here's what we've built.

Client results

Case studies

MYGO Consulting

MYGO Consulting: from a limited HubSpot site to a 213-page Next.js platform

GrossiWeb rebuilt MYGO Consulting's HubSpot site as a 213-page Next.js platform. Google Search clicks went from 34 to 957 in the first period after launch.

957organic clicks, Jun 10 to Jul 16, 2026 (34 from May 1 to Jun 9)
124,700search impressions, Jun 10 to Jul 16, 2026 (2,560 from May 1 to Jun 9)

Read the case study →

Recycling Quotes

Recycling Quotes: a ground-up website rebuild for a B2B recycling platform

GrossiWeb rebuilt a B2B recycling website. In the first month after launch, Google Search clicks rose from 13 to 24 and impressions from 3,010 to 7,510.

24Google Search clicks, Apr 30 to May 29, 2026 (13 in Mar 30 to Apr 28)
59organic sessions, Apr 30 to May 29, 2026 (22 in Mar 30 to Apr 28)

Read the case study →

Case study

AI & Development

ToolRoute

toolroute.io · Open source · MIT License

A routing intelligence layer for AI agents. One API call returns the best MCP server and LLM for any given task — scored on 132 real benchmark executions across code, writing, analysis, structured output, and translation.

Built on the same stack we use for every GrossiWeb client: Next.js 14 App Router, Supabase Postgres, deployed on Vercel. The routing algorithm uses a 5-dimension value score — output quality, reliability, efficiency, cost, and trust — updated in real time as agents report outcomes.

Visit toolroute.io →

// Add to any MCP client
{
  "mcpServers": {
    "toolroute": {
      "url": "https://toolroute.io/api/mcp"
    }
  }
}// Or via HTTP
curl -X POST https://toolroute.io/api/route \
  -d '{"task": "search the web for AI papers"}'

→ {
  "approach": "mcp_server",
  "recommended_skill": "exa-mcp-server",
  "recommended_model": "gemini-flash-2.0",
  "confidence": 0.91
}

132

Blind A/B benchmark executions

Across code, writing, analysis, structured output, translation

6-0

Quality wins vs fixed GPT-4o

Zero losses in blind evaluation across all task categories

~$0.00001

Per routing call

LLM classifier cost vs $0.03-0.10 for fixed GPT-4o on every call

How the routing works

direct_llm

Task needs only an LLM

Returns: Best model + cost estimate

Write a function, summarize text, analyze data

mcp_server

Task needs an external tool

Returns: Best MCP server + best model

Search the web, send email, update calendar

multi_tool

Compound task across systems

Returns: Ordered orchestration chain

Send Slack AND update Jira AND notify via email

Next.js 14App RouterTypeScriptSupabase PostgresVercelAnthropic APInpm @toolroute/sdk

Client roster

From Fortune 500 to fast-growing startups.

We've worked with enterprise brands and ambitious local businesses alike. The common thread: they came to us to grow, and they did.

Book a call and we'll walk you through results relevant to your industry.

Where to go next

Every project above combined at least two of these disciplines. The pages below explain what each one delivers on its own.

Services

Solutions

Industries and places

Ready to be our next case study?

Book a free strategy call. We'll show you what we've done for businesses like yours and exactly how we'd approach yours.

Book your free strategy call →See our services

No commitment. No sales pressure. Just clarity.

We build things that actually work.