1. Perplexity researches
Sourced facts with citations as the starting point.
Solo founders get the most out of Claude/ChatGPT (thinking + writing), Perplexity (sourced research), Notion AI (knowledge + docs), Otter/Fireflies (meetings auto-transcribed) and n8n/Make (automation) — a 'team of AIs' for under €50/month.
Solo founders get the most out of Claude/ChatGPT (thinking + writing), Perplexity (sourced research), Notion AI (knowledge + docs), Otter/Fireflies (meetings auto-transcribed) and n8n/Make (automation).
That's a 'team of AIs' for under €50/month — provided the tools don't overlap and knowledge lands in a second brain instead of evaporating.
Every Thursday at 23:00 Asia/Ho_Chi_Minh, the format gives a compact mix of market filtering, practical cases, questions, and clear next steps.
Next session: Thursday, July 9, 2026 at 23:00 · Asia/Ho_Chi_Minh. The series then continues on a weekly rhythm.

A lean 'team of AIs' for under €50/month. Prices as a ballpark, as of July 2026, vendor page authoritative.
| Task | Tool (recommended) | Why | Price |
|---|---|---|---|
| Thinking / writing | Claude / ChatGPT | Best reasoning + text as a thinking partner | €€ |
| Research | Perplexity | Sourced, cited answers | € |
| Knowledge / docs | Notion AI | Second brain, docs in one place | € |
| Meetings | Otter or Fireflies | Automatic transcript + action items | € |
| Automation | n8n (self-host) | Connects the tools without copy-paste | € |
| Images | Canva / ChatGPT Images | Fast graphics without a designer | € |
From a research prompt to an automatic follow-up.
Sourced facts with citations as the starting point.
Raw material becomes a solid write-up.
Knowledge stays findable instead of evaporating.
Meetings turn into notes + action items automatically.
E.g. meeting note → task → follow-up draft, fully automatic.
Where solo-founder stacks fail.
For the core, yes: a paid LLM (~€20), Perplexity (~€20) and self-hosted n8n (server cost only) form the backbone; Notion and a meeting tool have usable free or cheap tiers. Multilingual voice or video pushes you higher — but the productivity core stays cheap. As of July 2026.
Both are excellent; Claude is especially strong on long documents, analysis and agentic workflows, ChatGPT on the broadest ecosystem. Many founders use one as their main thinking partner and the other situationally. What matters is a consistent workflow more than the brand.
Matching stacks for other roles — each with a stack table, workflow and common mistakes.
Dev teams combine Claude Code (agentic coding in the terminal), Cursor (AI IDE) and GitHub Copilot (inline completion), with Claude for architecture/reviews. A small team ships noticeably faster — planning, implementation and review all AI-assisted.
Sales combines Claude/ChatGPT (personalization), Clay/Apollo (lead data + enrichment), HeyGen (personalized video outreach) and n8n (automation + CRM sync) into an AI-assisted pipeline — research, personalized sequences and follow-ups run semi-automatically.
Back to the hub with the stack overview and all 7 role-based stacks.
We set up the stack + the automations.
If you want to prioritize a real process, a few clear inputs are enough for a strong first assessment.