The Intelligence Library

Operational intelligence from real client delivery

Every resource here is extracted from systems we actually shipped — implementations, workflows and measured outcomes, not generic AI content. Free to read, built to be used.

Newsletter

Operations

What we shipped last quarter, and what it changed

Three systems we built last quarter, and the screens behind them.

The founder inbox command centre we built, showing 87 messages in the day's feed, 6 processed, 1 AI drafted, 5 AI flagged, 3 human needed, 0 refunds, 1 urgent, 81 dropped, a 0.94 average confidence and a 17 percent automation rate, with the alert queue beneath.

We built three systems for clients last quarter. Every one of them stops at a person, and that is why the teams trust them.

5 min read

2026-09-04

Read the issue

Newsletter

Automation

The Verdict Board: What We'd Adopt, Deploy and Skip in AI Automation

We looked at the AI automation ideas getting the most attention and asked a harder question. What actually survives when it meets real operations? Five calls, each with a receipt.

Live capture from the Founder Inbox OS: the human review queue and alert queue with drafted replies, confidence scores and masked sender names — the receipt behind verdict 01.

Inbox triage, call memory and ad production are proven AI jobs when a person controls the output.

7 min read

2026-08-09

Read the issue

Newsletter

Workflows

Three systems to install before Q4 planning

Founder Brief: Three systems we built and still run.

The founder inbox command centre on a real day, showing 87 emails in the feed, 6 processed, 81 dropped by pre-filter rules, a 0.94 average confidence, and the alert queue beneath.

Put the week on a schedule. One client's report has closed every week for a year and a half, and it earned trust the day their founder challenged a number on it in front of everyone.

4 min read

2026-07-01

Read the issue

Newsletter

Operations

Teardown: the inbox that drafts itself

The inbox system we built, on a real month of a client's mail.

The founder inbox command centre we built, on a thirty day window, showing 2256 messages processed, 1052 drafted by AI, 1204 flagged, 91 needing a human and 5536 dropped by filter rules, at a 47 percent automation rate.

Plain rules did the heavy lifting. In one month 5,536 messages were dropped before any AI ran, each logged against the rule that dropped it.

6 min read

2026-06-24

Read the issue

Newsletter

Reporting & Dashboards

The weekly reporting cadence that ends "how are we doing?"

A teardown of a reporting system that has run for a real client for a year and a half. The actual Monday emails, the actual Friday reports, the Slack thread where a number got challenged, and the workflow underneath.

The report that ends "how are we doing?" — the real client reporting folder of dated weekly status reports, with the n8n executions list showing the scheduled sends succeeding. Client name masked.

One client's week has closed with a Friday status report for a year and a half, and opens with a scheduled Monday email. This issue shows the real artifacts, masked and cropped but never rewritten.

7 min read

2026-06-17

Read the issue

Newsletter

Reporting & Dashboards

Agency360 Product Update

Inside Agency360 — one invitation-only agency login across Meta Ads, Google Ads, Shopify and Xero, a data preview on every connector, and connection health that shows whether a source is usable before it reaches a client report.

Agency360 — the real System Status view reading All Systems Operational, with connector, system and automation health panels and the Meta Ads connector showing Success and its last sync time. Client names masked.

Meta Ads, Google Ads, Shopify and Xero connect under one invitation-only agency login.

5 min read

2026-06-03

Read the issue

Get the DashboardLim Brief

Real systems we've shipped, and the practical AI lessons from building them. Every library addition ships through the Brief first.