Resources
How to govern an autonomous agent.
Oversight law, approval gates, data residency, secrets handling, MCP and agent memory — plus the API reference and the security model. Written to be useful whether or not you ever sign up.
6 shelves · 6 guides · everything free to read
The library
Six shelves. No gate on any of them.
Each one is a real destination with real content behind it — nothing here is a placeholder for something we intend to write.
- 01
Blog
Field notes on running a company with an agent — playbooks, teardowns, and the thinking behind how Monopea operates. Written for founders doing the work.
Open - 026 guides
Guides
Evergreen explainers on the hard parts: human-oversight law, approval gates, data residency, secrets handling, MCP, and agent memory. Useful whether or not you ever sign up.
Start with EU AI Act Article 14: human oversight for AI agents
Open - 03
API & MCP docs
The REST /v1 surface, the WebSocket chain-of-thought stream, and the MCP server — with the auth model, the proposals lifecycle, and copyable calls.
Start with Quickstart — auth, then one call
Open - 04
Security model
How the gate, the write-only vault, tenant isolation and the signed audit chain are actually built — the page to hand your reviewer.
Open - 054 comparisons
Comparisons
Honest, axis-by-axis comparisons against the alternatives — including the ones we lose on, because a comparison that never loses is an advert.
Open - 066 playbooks
By profession
What a governed agent does for founders, fiduciaries, law firms, medical practices and agencies — written per trade, not per feature.
Open
The blog
Field notes, most recent first.
Guide8 min read
Automating Founder Inbox: AI Agents for Prioritization and Drafts
A founder's playbook for AI inbox management: triage buckets, on-brand drafts, human-in-the-loop approval gates, and the metrics that prove the hours saved.
Read articleGuide8 min read
AI Agents for Founder Decisions: A Playbook for Strategic Clarity
A practical playbook for using AI agents to prepare founder decisions: what to delegate, how to structure briefs, and where human approval stays.
Read article
Guide8 min read
Automating Investor Updates: How AI Agents Keep Founders Focused on Growth
AI agents for investor updates gather your numbers, draft the narrative, and hold every send for your approval before it reaches an investor.
Read article
Guides
The parts that are actually hard.
Evergreen explainers, each one a concept defined honestly before it is connected back to how we implement it. Regulatory pieces teach the requirement — they are not legal advice.
- 01
Guide · Compliance
EU AI Act Article 14
What the EU AI Act’s human-oversight requirement means for AI agents — oversight as an external control, not a prompt instruction — and how to architect for it.
- 02
Guide · Security
Approval gates
Why “always ask first” in a system prompt is not a control — and what a real approval gate looks like: default-deny policy, a proposal lifecycle, fail-closed unknown tools, and audit chains.
- 03
Guide · Residency
Swiss data residency
What Swiss data residency really means for AI agents — FADP basics, the storage-versus-processing distinction vendors blur, CLOUD Act exposure, and the questions to ask any provider.
- 04
Guide · Security
Secrets management
Why an AI agent must never see your credentials, how prompt injection turns context into an exfiltration channel, and the write-only vault pattern that fixes the class.
- 05
Guide · Concepts
What is MCP?
The Model Context Protocol — the open standard connecting tools and data to AI agents, and the layer where governance either happens or doesn’t.
- 06
Guide · Concepts
Long-term memory
Why persistent memory turns an assistant into an operator — and why it must be tenant-owned, inspectable, and stored somewhere you can name.
Hand it the first job this afternoon.
Open a workspace, give the agent a task, and approve what it proposes. Stored in Switzerland, processed in the EU.