loaded.
Project-Based · For Select Clients

AI Agents.
Engineered, not
cobbled together.

loaded. from Zurich builds custom AI agents with Python and Node.js for Swiss businesses. No low-code platforms, no pre-built modules — every agent is engineered from the ground up.

Our agents research, analyze, decide, and act autonomously — around the clock. Project-based, for select clients in Switzerland.

AI Agent Architecture — autonomous data pipeline with interconnected nodes and glowing connections
The Concept

AI Agents Are Not Chatbots

A chatbot waits for your question. An AI agent works independently. It researches data across the web, analyzes websites, tracks prices over months, generates reports, sends emails — all around the clock, without manual intervention. It makes decisions based on the data it finds: Which prospect is most promising? Which page needs a content update? Which competitor price has changed?

24/7
Agents work autonomously — nights, weekends, holidays
100%
Code — Python and Node.js, no low-code platforms
Flexibility — any API, any system, any logic
Market Overview

AI Agent Platforms Compared

The AI agent market is growing fast. From visual workflow tools to autonomous agent systems — the approaches differ fundamentally. Here is how the major platforms compare and where custom code agents fit in.

n8n / Make.com Visual Workflow
Strengths

Quick setup, hundreds of connectors, visual logic. Great for simple automations with clearly defined if-then rules.

Limitations

No real reasoning, no dynamic decision logic. No sandbox execution.

Ideal for: Prototyping, simple automations
Claude Computer Use LLM-native
Strengths

Anthropic's agent framework: tool use, computer use, code execution. Strong reasoning.

Limitations

Tied to Claude models. Managed agents are generalist. No persistent data storage without your own infrastructure.

Ideal for: Developers, agent prototypes
OpenClaw Open-Source
Strengths

Local, 100+ skills, connects LLMs with apps and browser. 247,000+ GitHub stars.

Limitations

Personal assistant — not for business processes. No CRM/ERP integration. Vulnerable to prompt injection.

Ideal for: Power users, personal productivity
Manus AI General Agent
Strengths

Executes complex tasks autonomously: web research, document creation, data analysis.

Limitations

Black box — no control over logic or data flow. No business system integration.

Ideal for: Individuals, exploratory tasks
OpenAI Assistants / GPTs LLM Platform
Strengths

Code Interpreter, File Search, Function Calling. Large ecosystem, simple API.

Limitations

GPTs lack true agency — they only react to input. No scheduling, no system integration.

Ideal for: Chatbot extensions, simple assistants
Custom Code Agents (loaded.) Custom-Built
Strengths

Full control over logic, prompts, data flow, LLM selection. Multi-model. Own sandboxes, own database, own API integrations. No platform dependency.

Limitations

Higher initial investment. Requires experienced developers. Not for simple if-then automations.

Ideal for: Businesses with complex processes

Every platform has its place. n8n and Make.com are excellent for rapid prototyping. OpenClaw impressively demonstrates what a local agent can do on your own machine. Claude and OpenAI provide strong foundations for developers. For Swiss businesses that need an agent deeply integrated into their systems, reliably running around the clock, and improving with every new LLM generation — that is where custom code comes in.

Use Cases

What Our AI Agents Deliver in Practice

6 use cases for Swiss businesses.

Research & Outreach Agent

Automatically finds prospects in a specific industry and region, technically analyzes their websites — performance, tech stack, weaknesses — and generates personalized audit pages. Sends tailored outreach emails via Resend with SPF/DKIM authentication. We use this agent ourselves — for loaded.'s client acquisition in Switzerland.

Discuss Your Project →

SEO & Content Intelligence

Analyzes competitor pages live — word count, headings, schema markup, rankings. Automatically detects content gaps, prioritizes keywords by search volume and competition, and suggests specific changes or applies them directly. Uses Google Gemini with search grounding for real-time SERP analysis. We use this agent ourselves for loaded.ch.

Discuss Your Project →

Price Intelligence Agent

Monitors competitor prices automatically — today and three months from now. Ideal for Swiss hotels, e-commerce, and any industry with dynamic pricing. Crawls multiple sources in parallel, normalizes data in Supabase (Postgres), and generates time-based comparison reports with trend analysis. Spots competitor price changes before your revenue team finds them manually.

Discuss Your Project →

Dynamic Page Creation

Creates pages programmatically based on database content, API responses, or user input. Full control over structure, schema markup, URL slugs, and meta data — deployed on Vercel with SSR or ISR. No CMS limitations, no templates. Perfect for Swiss SMEs with hundreds of product pages or location-specific landing pages.

Discuss Your Project →

Email Automation

Complete email pipelines with Resend — transactional and marketing. Trigger-based, API-driven, with personalized content per recipient. SPF/DKIM authenticated so emails land in the inbox, not spam. No Mailchimp, no monthly subscription — pure API logic, infinitely scalable.

Discuss Your Project →

WebMCP & OpenHermit

Our own MCP implementation (Model Context Protocol) gives AI agents direct access to website content, forms, and APIs. Agents can do more than read — they can act: book appointments, submit inquiries, update data. OpenHermit is our open-source contribution to the agent ecosystem — built in Zurich.

Discuss Your Project →
Showcase

In Practice: Our Research & Outreach Agent

We use this agent ourselves. It finds potential clients, automatically analyzes their websites, and generates personalized audit pages — entirely without manual effort. Here is how it works.

The Result for the Prospect

1

Prospect receives an email

Personally written, based on a real analysis of their website. No template, no mass mailing — every email is unique.

2

Clicks their personal audit link

A custom-generated page shows: screenshot of their website, performance score, technical weaknesses, comparison with two competitors from the same city.

3

Can submit a request directly

A CTA form on the audit page. The request is saved in real time, the prospect receives a confirmation, and we are notified immediately.

What the Agent Does Behind the Scenes

S

Scout: Find prospects

Gemini with Google Search grounding searches for businesses in a specific industry and region. For each website found, a tech debt score is calculated: WordPress, jQuery 1.x, Bootstrap 3, IE polyfills — the higher the score, the greater the need for action.

A

Analyze: Measure performance + AI vision

Two parallel Google PageSpeed Insights calls (mobile + desktop). The desktop screenshot is sent to Gemini Vision — the model sees the website and produces a structured analysis: weaknesses, potential, a tailored initial outreach message.

O

Outreach: Find contact + send email

Four-layer contact search: mailto links, regex in HTML, obfuscation decoder, crawl of /kontakt, /impressum, /about — and as a last resort, a Gemini web search. Audit data is saved via API, an SSR page is rendered live, and the email is sent via Resend.

Bot (Node.js)

Controls the entire process: Scout → Analysis → Outreach. Communicates with Gemini, Google PSI, and the website API.

Website (Vercel / SSR)

Receives audit data via API, renders personalized audit pages with SSR. Tracks views and requests in real time.

Database (Supabase)

Postgres with Row Level Security. Stores all audit data as JSONB: analysis, PSI scores, screenshots, competitor comparison.

The Complete Data Flow

Mac (you) —— node scout.js ——→ Gemini Search ——→ results/*.json
node outreach.js
fetchHTML()
(raw HTTPS
+ tech scan)
psiCall()
(2x parallel:
mobile+desktop)
findEmail()
(4-layer search
+ Gemini fallback)
deepAnalyze()
Gemini Vision
(screenshot + tech signals
→ structured JSON)
getCompetitorsPSI
(validate URLs
→ PSI parallel)
saveToAPI
POST /api/audit
/save → Supabase
buildEmailHTML
(Gmail-style,
HTML + text ver.)
loaded.ch/audit/[slug]
(SSR: view_count++, first_viewed_at)
Prospect opens
Clicks CTA form
POST /api/audit/redesign-request
→ redesign_requested = true
→ Email to you + confirmation to them
Technical Blueprint — Pipeline in Detail
01
Scout — Find Prospects
scout.js

Gemini with Google Search grounding searches for businesses in a specific industry and region. A tech debt score is calculated for each website found.

Gemini 2.0 Flash Search Grounding Tech-Debt Scoring
scout.js
const prompt = `Finde 10 ${branche} in ${city}
  mit eigener Website. Gib URLs zurück.`;

const results = await gemini.generate({
  model: 'gemini-2.0-flash',
  tools: [{ googleSearch: {} }],
  prompt
});

// Calculate tech debt score
for (const url of results.urls) {
  const html = await fetchHTML(url);
  const score = calcTechDebt(html);
  // WordPress=3, jQuery 1.x=2, Bootstrap 3=2
}
02
Fetch + PageSpeed Insights
outreach.js

Parallel requests: HTML fetch with redirect handling (5 hops), self-signed cert bypass. Two PSI calls (mobile + desktop) via Promise.allSettled.

HTTPS + Redirect PSI API v5 Promise.allSettled
outreach.js — fetchHTML + psiCall
const [mobile, desktop] = await Promise.allSettled([
  psiCall(url, 'MOBILE'),
  psiCall(url, 'DESKTOP')
]);

const screenshot = desktop.value
  ?.lighthouseResult?.audits
  ?.['final-screenshot']
  ?.details?.data;  // base64 JPEG

const perfScore = mobile.value
  ?.lighthouseResult?.categories
  ?.performance?.score * 100;
03
Find Contact Email
outreach.js — findEmail

Four-layer search: mailto links → regex in HTML → obfuscation decoder (info[at]domain.ch) → crawl of /kontakt, /impressum, /about → as fallback: Gemini web search.

Regex Extraction Obfuscation Decoder Multi-Page Crawl
findEmail.js
async function findEmail(html, domain) {
  // Layer 1: mailto links
  let email = html.match(/mailto:([^"]+)/)?.[1];
  if (email) return email;

  // Layer 2: regex in raw HTML
  email = html.match(/[\w.-]+@[\w.-]+\.\w+/)?.[0];
  if (email) return email;

  // Layer 3: obfuscation decoder
  email = decodeObfuscated(html);
  // info[at]domain.ch → info@domain.ch

  // Layer 4: crawl subpages
  for (const p of ['/kontakt','/impressum'])
    email ??= await scrape(domain + p);
}
04
Gemini Vision Analysis
outreach.js — deepAnalyze

Screenshot (base64 JPEG) + tech signals as a multimodal request to Gemini 2.0 Flash. Returns structured JSON: business type, weaknesses, potential, personalized email subject and intro.

Gemini Vision Multimodal Structured JSON
deepAnalyze.js
const analysis = await gemini.generate({
  model: 'gemini-2.0-flash',
  contents: [{
    parts: [
      { inlineData: { mimeType: 'image/jpeg',
                       data: screenshot } },
      { text: `Analysiere diese Website.
        Rückgabe als JSON:
        { businessType, weaknesses[],
          potential, emailSubject,
          emailIntro }` }
    ]
  }]
});

// Post-processing
analysis.emailIntro = analysis.emailIntro
  .replace(/cookie|banner/gi, '')
  .split('.').slice(0, 3).join('.');
05
Competitor Benchmark
outreach.js — getCompetitorsPSI

Gemini suggests two competitors from the same city. HEAD requests validate each URL, followed by parallel PSI calls. Result: comparison bars on the audit page.

HEAD Validation Parallel PSI Score Comparison
competitors.js
const competitors = await gemini.generate({
  prompt: `Nenne 2 Konkurrenten für
    ${businessType} in ${city}`
});

// Validate URLs exist
const valid = await Promise.all(
  competitors.map(async (c) => {
    const res = await fetch(c.url, {method:'HEAD'});
    return res.ok ? c : null;
  })
);

// Parallel PSI for each competitor
const scores = await Promise.allSettled(
  valid.filter(Boolean).map(c => psiCall(c.url))
);
06
Save + Generate Audit Page
outreach.js — saveToAPI

POST to the website API with Bearer token auth. Upsert in Supabase (view_count and redesign_requested are preserved across re-runs). The audit page is rendered via SSR.

REST API Supabase Upsert SSR Rendering
saveToAPI.js
await fetch('https://loaded.ch/api/audit/save', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${AUDIT_SECRET}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    slug, url, perfScore, analysis,
    screenshot, competitors, email
  })
});

// Supabase upsert (preserves view_count)
// SSR page: loaded.ch/audit/[slug]
// view_count++ on each visit
07
Send Email
outreach.js — sendEmail

Resend API with SPF/DKIM authentication. Intentionally plain HTML — designed to look like a real Gmail message, not a marketing template. HTML and text versions for maximum deliverability.

Resend API SPF/DKIM HTML + Text
sendEmail.js
import { Resend } from 'resend';
const resend = new Resend(RESEND_API_KEY);

await resend.emails.send({
  from: 'Benjamin <hello@loaded.ch>',
  to: contactEmail,
  subject: analysis.emailSubject,
  html: buildGmailStyleHTML({
    intro: analysis.emailIntro,
    auditUrl: `https://loaded.ch/audit/${slug}`,
    perfScore,
    businessName
  }),
  text: buildPlainText({ /* ... */ })
});
Output — Audit Data in Supabase
{
  "slug": "restaurant-bellevue-zuerich",
  "url": "https://restaurant-bellevue.ch",
  "perf_mobile": 34,
  "perf_desktop": 61,
  "tech_debt_score": 7,
  "analysis": {
    "businessType": "Restaurant",
    "weaknesses": [
      { "issue": "Render-blocking CSS", "severity": "high" },
      { "issue": "No image optimization", "severity": "high" },
      { "issue": "jQuery 1.12.4", "severity": "medium" }
    ]
  },
  "competitors": [
    { "name": "Kronenhalle", "score": 72 },
    { "name": "Zeughauskeller", "score": 58 }
  ],
  "view_count": 0,
  "redesign_requested": false
}
Technology

Our Tech Stack for AI Agents

The tools and frameworks behind our agents.

Languages

Python · Node.js / TypeScript — depending on the use case. Python for data processing and ML integration. Node.js for web scraping, API communication, and real-time systems.

LLM-SDKs

Anthropic Claude · OpenAI · Google Gemini · LangChain · LangGraph — we select the model per task: vision, reasoning, speed, cost.

Infrastructure

Supabase (Postgres) · Vercel · Docker · Daytona sandbox environments for secure code execution. Swiss hosting available for nDSG-compliant projects.

Integrations

Resend (email) · WebMCP / OpenHermit (agent-website interaction) · Any REST or GraphQL API · Webhooks · CRM · ERP · Direct database access.

Security

Sandboxes: Why Security Is a Prerequisite for AI Agents

AI agents execute code, call APIs, and process data — they need controlled environments. We use Daytona sandboxes: isolated environments where each agent process only has access to the resources it needs. No uncontrolled access to production systems, no open network connections. For Swiss companies with nDSG requirements, the entire infrastructure can run on Swiss servers.

Isolated execution environments per agent
API keys stored as encrypted environment variables
Granular permissions per system access
Audit trails for all agent actions
Row Level Security in Supabase (Postgres)
Full code access for the client
Isolated sandbox environment — secure code execution for AI agents
Process

How Your AI Agent Is Built

01

Discovery

Which process should be automated? What data sources exist? Which systems need to be connected? We define the scope together — and verify whether an agent is the right solution.

02

Architecture

Which LLM for which task? What pipeline steps? How should error handling work? We design the agent architecture before a single line of code is written.

03

Build & Test

Iterative development with real data. Prototype in 1-2 weeks, production version in 4-8 weeks. Prompt engineering, edge-case handling, performance optimization — until the agent delivers reliably.

04

Operations & Evolution

An agent is not built once and forgotten. New LLM models bring better reasoning, lower costs, and new capabilities — almost weekly. We continuously test, optimize, and extend.

Collaboration

Project-based — for select clients

AI agents require intensive collaboration and ongoing support. We work with a small number of clients to guarantee maximum quality.

Discuss Your Project →
FAQ

Frequently Asked Questions

What exactly is an AI agent?
An AI agent is a program that autonomously executes tasks — not just answers questions like a chatbot. An agent can research the web, aggregate data from multiple sources, make decisions, call APIs, send emails, and generate reports. All automatically, around the clock, without manual intervention. The difference from a chatbot: a chatbot waits for your input. An agent works proactively.
Why does loaded. build agents from scratch?
Because real agents need to do things no low-code platform can handle: dynamic web research across dozens of sources, image analysis with vision models, multi-step decision logic with error handling, secure code execution in sandboxes. We work with Python and Node.js — giving us full control over logic, performance, security, and scalability. No limitations from pre-built modules.
Which industries benefit from AI agents?
Any industry with repetitive, data-intensive tasks. Specific examples: hospitality (automated competitor price monitoring), agencies (prospect research and outreach), e-commerce (dynamic content creation), real estate (market analysis), healthcare (appointment management), legal (document analysis). What matters is not the industry — it is the process that needs automating.
How long does it take to develop an AI agent?
A first working prototype is typically ready within 1–2 weeks. The full production version with error handling, monitoring, API integrations, and fine-tuning takes 4–8 weeks — depending on complexity. After that, ongoing optimization begins: testing new models, refining prompts, handling edge cases.
How much does an AI agent cost?
The cost depends on the project scope, integration complexity, and the value the agent creates for your business. There is no standard price because every agent is custom-built. We work on a project basis with select clients. In the initial consultation, we define scope, expected ROI, and feasibility — resulting in a transparent proposal.
Why does loaded. only work with select clients?
AI agents require intensive collaboration — especially in the first weeks. We optimize prompts, train edge cases, and adapt logic to real-world data. That only works when we can invest enough time per project. At the same time, the field evolves extremely fast: new models, new APIs, new capabilities — almost weekly. We keep our agents current. That requires capacity, not volume.
How is my agent hosted and operated?
Depending on the use case: agents run as serverless functions (Vercel, AWS Lambda), as containers (Docker), or as scheduled cron jobs. Data is stored in Supabase (Postgres) or your existing database. Everything can be hosted on Swiss infrastructure if nDSG compliance is required. You get full access to the code.
What happens after launch?
An agent is not built once and forgotten. LLM models keep advancing — GPT-5, Claude 4, Gemini 2.5 bring new capabilities, better reasoning quality, and lower costs. We test new models against your existing prompts, optimize workflows, and extend functionality. Your agent improves with the technology — it does not become obsolete.
Can an agent communicate with my existing systems?
Yes. Our agents speak every API: CRM (HubSpot, Salesforce, Pipedrive), email (Resend, SendGrid), databases (Postgres, MongoDB), cloud storage, calendars, ERP systems. If your system has an API or a webhook, an agent can work with it. Even legacy systems without APIs can be connected via web scraping or file-based interfaces.
How secure are the agents?
Code execution happens in isolated sandbox environments — no agent has uncontrolled access to production systems. API keys are stored as encrypted environment variables, never in the code. All access is logged. For agents working with sensitive data, we implement granular permissions and audit trails.

Book your free strategy call.

30 minutes — no obligation, no sales pitch. We analyse your situation and show you what's possible.

MonTueWedThuFriSatSun
Loading available times...