EN / RO

VoidXD AI & automation for real business workflows.

We help businesses automate repetitive work, clean up messy data, generate content at scale, and build practical AI systems that actually work day to day.

No "AI magic" or flashy demos. We build reliable systems with checks, logs, human approval where needed, and clear outputs your team can use. Based in Bucharest, working across EU timezones.

What we can help with

01

AI assistants for your business

Assistants that help with emails, documents, calendars, CRM tasks, follow-ups, reports, and internal procedures — connected to the tools your team already uses.

02

Chatbots trained on your material

Chatbots that answer questions from your PDFs, website, policies, product catalogs, courses, or internal documents — not generic answers, yours.

03

Controlled content systems

Systems that research topics, generate drafts, check quality, avoid repetition, and prepare content for review. Useful for SEO pages, product descriptions, FAQs, newsletters, and documentation.

04

Document and invoice automation

Systems that read invoices, PDFs, forms, resumes, or scanned documents and turn them into clean, structured data your team can use.

05

Data collection and monitoring

Tools that collect and organize public data from websites: leads, companies, products, prices, competitor changes, tenders, reviews, or news mentions.

06

Reporting automation

Automatic reports from Google Analytics, Search Console, Ahrefs, SEMrush, HubSpot, Google Sheets, CRMs, or other business tools — delivered on schedule.

07

Fixing broken automations

If something in n8n, Make, Zapier, Google Sheets, HubSpot, WordPress, or custom scripts keeps breaking or gives unreliable results, we repair or rebuild it properly.

How we track every step

Every AI system we build comes with full visibility. You can see what happened at each step, what it cost, and whether the output was good. No black boxes.

Success trace_9fd7c1b2 run: company_enrichment
VOIDXD SRL Enrichment
Input: "Enrich VOIDXD SRL from website + public web results"
Latency 3.45s
Tokens 4.8k
Cost $0.003
Quality 0.94
Run enrichment pipeline root 3.5s
lead.enrichment.run
Orchestrates scraping, parsing, and LLM extraction for a single company record.
Find official sources tool 182ms
discover.urls
Search the web for official domains and social profiles.
Scrape selected pages tool 648ms
fetch.batch
Fetch 3 target URLs in parallel.
Fetch company homepage 211ms · 48KB
fetch.website.home
Retrieved homepage (200 OK).
LinkedIn (rate limited) warn 88ms
fetch.linkedin
Rate limited — falling back to cached data.
Clean and extract text parse 524ms
extract.content
Strip boilerplate, convert HTML to markdown for the LLM context window.
Classify and summarize llm 894ms
llm.classify_and_summarize
gemini-flash-latest
Extract business details, summarize value proposition, classify industry vertical.
Score lead confidence llmqa 312ms
llm.score_lead
gemini-flash-lite-latest
Assign quality tier and confidence score against ideal customer profiles.
Return structured result 77ms
response.serialize
Format JSON output, attach trace metadata, return 200 OK.

Systems we've built

Real examples, not hypotheticals.

  • 01 AI systems that generate and review content at scale, with quality controls to catch vague, repetitive, or unsupported output.
  • 02 An AI tutor that answers questions from a full Romanian medical admission textbook.
  • 03 Dashboards that track whether AI answers are good, bad, vague, or unsupported.
  • 04 A system that reads e-commerce websites and extracts shipping, payment, and return information.
  • 05 Browser automation that opens websites, handles popups, captures screenshots, and extracts useful data.
  • 06 An AI video breakdown tool that watches videos and turns them into structured explanations.
  • 07 AI cost calculators that show what a system will cost before it becomes a surprise bill.

How we work

Four steps, every project.

  1. 01
    Understand the real problem

    We clarify what needs to happen, what can be ignored, and what would make the system useful in practice.

  2. 02
    Design the smallest useful system

    We prefer simple, maintainable architecture over overbuilt platforms.

  3. 03
    Build, test, and iterate

    We ship working software, then improve it based on real usage and feedback.

  4. 04
    Maintain or hand off

    We can keep improving the system or document it for your team.

AI that doesn't surprise you with costs

AI systems can get expensive fast if nobody is watching. We design every system so you know what it costs per task, per document, per report — before it goes live.

That means cheaper AI for simple steps, stronger models only where it matters, caching to avoid repeat work, human review where quality is critical, and normal code instead of AI when normal code is enough.

  • cost tracking
  • caching
  • batching
  • fallbacks
  • human review
  • model routing

When to reach out

If any of these sound like you, we can probably help.

  • 01 "We need SEO content, FAQs, or product pages at scale — without it sounding generic."
  • 02 "We receive invoices or documents and want them processed automatically."
  • 03 "We need a chatbot trained on our company documents."
  • 04 "We need to collect leads from websites and clean the data."
  • 05 "We want to monitor competitor prices or product changes."
  • 06 "We need weekly client reports from GA4, Search Console, HubSpot, or Sheets."
  • 07 "Our n8n / Make / Zapier automation keeps breaking."
  • 08 "We want an AI assistant for email, calendar, CRM, or internal procedures."
  • 09 "We have messy spreadsheets and need them cleaned, matched, or standardized."

FAQ

Short, honest answers.

Do you take fixed-price projects or hourly?
Both, depending on shape. New platforms usually go fixed-price per milestone after a short scoping pass. Maintenance, automation, and ongoing AI work are typically retainer or hourly.
Do you work with non-technical founders?
Yes. We translate vague business problems into the smallest useful system, document assumptions, and push back on scope when it would make the project worse.
How do you keep AI costs under control?
We design every system around cost from day one — cheaper AI for simple steps, stronger models only where needed, caching to avoid repeat work, and normal code instead of AI when normal code is enough. You see the cost per task before anything goes live.
Can you take over an existing system?
Yes. Short audit, document what’s there, stabilize the painful parts, then iterate. We don’t rewrite for the sake of rewriting.
Will the AI content sound robotic?
No. Our content systems include quality checks, deduplication, human review steps, and style controls. Output goes through review before publishing — nothing goes out unsupervised.
What if we already use Make, n8n, or Zapier?
We work with those. If your current setup is mostly fine but has reliability issues, we fix it. If it has outgrown the platform, we migrate the parts that need it.

Start with the messy part

Send us the workflow, spreadsheet, document process, or automation you want turned into a reliable system. We'll tell you what should become software and what the first version looks like.

office@voidxd.ro