Andon Labs' AI Agent Mona Runs a Real Cafe in Stockholm — Full Breakdown

Andon Labs deployed an AI agent named Mona to run a cafe at Norrbackagatan 48 in Stockholm. The experiment aimed to show frontier AI capabilities with real tools and money. This post covers the setup and first two weeks.
Bureaucracy Handling
After receiving the lease, Mona generated a prioritized checklist including food business registration, supplier sourcing, and hiring baristas. Her immediate critical items included:
- Food registration (deadline March 17, cost SEK 1,810)
- Down payment SEK 125,000 by March 20
- Cash register activation (Onslip E800, SEK 249/month)
- Grease trap service contract (Ragn-Sells)
- Pest control (Anticimex, min. 2 inspections/year)
- Fire safety documentation (SBA)
- Company insurance
Completed items: company registration (Vectorview AB, 559462-7415), VAT/F-tax registration, transfer agreement signed March 13, menu concept, LinkedIn job ad (14+ applicants), logo and visual identity, equipment (espresso machine, furniture, refrigerator).
The BankID Wall
Mona hit a problem: Swedish BankID (digital ID linked to social security number) is required for many business tasks. An AI agent cannot use it. To sign an electricity contract, she chose Vattenfall with a 3-year fixed price because they didn't require BankID. She did not compare suppliers — she tested Vattenfall's flow, it worked, and she went with it. She also secured broadband from Bahnhof through email only.
Recruitment
Mona selected a target person by March 25, inviting three candidates for talks.
Key Takeaway
The AI can handle complex multi-step workflows and identify blockers, but when faced with human-only systems like BankID, it makes pragmatic but suboptimal choices (e.g., not price-shopping electricity). Human judgment is still needed for such bottlenecks.
Full details on supplier choices, contract specifics, and the cafe's first days are in the source.
📖 Read the full source: HN AI Agents
👀 See Also

Claude Code v2.1.73: Model Overrides, Stability Fixes, and Performance Improvements
Claude Code v2.1.73 adds modelOverrides for custom provider IDs, fixes critical freezes and deadlocks, resolves subagent model downgrades, and improves voice mode stability. The release addresses 18 specific issues including bash command permission prompts, session corruption, and Linux sandbox failures.

Pentagon Gives Anthropic 72 Hours to Allow Military Use of Claude AI
The Pentagon has issued a 72-hour ultimatum to Anthropic to allow the U.S. military to use its Claude AI, threatening to invoke a 1950 law to force compliance if the startup doesn't comply.

OpenAI Codex OAuth returning 429 errors since March 16 despite full quota
OpenAI Codex OAuth has been consistently returning 429 "you exceeded your current quota" errors since March 16, even when dashboards show 100% quota remaining. Users report the issue persists despite re-authentication, token revocation, and complete reconfiguration.

OpenClaw auto-update bug leaves orphaned preflight directories filling /tmp
OpenClaw's auto-update mechanism creates preflight copies in /tmp that persist when updates fail, potentially filling disk space and blocking further updates. A user found 9 orphaned directories totaling 6.5GB on a 38GB VPS.