Full Transparency

Building in the Open

How Picking Solutions was built in 30 days with AI — and how an autonomous executive team now helps run it. Real numbers. Real architecture. Nothing hidden.

Act I — The Build

One person, one AI co-pilot, 30 days. Here's the timeline.

2018

The Seed

A reflection on time, attention, and information overload. The idea sat dormant for 7 years — not from lack of ambition, but from fear of starting.

Dec 2025

The Spark

AI matured from novelty to genuine creative amplifier. The barrier was never capability — it was permission to begin. So I began.

Dec 2025 – Jan 2026

30-Day Rapid Build

From blank repo to live signals, tools, premium dashboards, and a flywheel. DeepAgent as co-pilot. Human direction, AI amplification.

Jan 2026

Launch + Transparency

Went live with daily feeds, Lumen Pro, intelligence pipeline. Decided to build in the open — showing everything, hiding nothing.

Mar 2026

AI Executive Team

Phase B: 5 AI agents running strategy, operations, and analytics. Turn-based meetings, daily briefings, founder feedback loop. The zero-human company experiment begins.

Now

Building in the Open

You're looking at a live system. The numbers below are real, pulled from the database right now. This page updates every time you load it.

Live Platform Numbers

Pulled from the database right now. Not vanity metrics — actual system state.

136
Published Posts
14,410
Intelligence Items
89
Data Sources
596
Collector Runs
73
LLM Digests
82
Pulse Signals
5
Reports
5
AI Agents

Act II — The Experiment

Can an AI executive team run a company? We're finding out — live.

System Architecture

5 AI agents — each with a distinct role, personality blend, and configurable behaviour
17 leadership personas — from Musk to Sun Tzu, blended dynamically per agent
35 mental models — grounded in warehouse automation domain
40 parametric sliders — risk tolerance, innovation bias, time horizon, etc.
9 cascading targets — founder → CEO → department → operational
0 briefings generated + 2 meetings held

Agent Roster

Analytics Chiefexecutive
abacusai / gpt-4o
CEOexecutive
xai / grok-3
Marketing Chiefexecutive
abacusai / gpt-4o
Product Manageroperational
xai / grok-3
Tech Team Leadoperational
abacusai / claude-sonnet-4-20250514

Active Targets (Live)

Backlog Items Completed Per Week > 3(Product)
0%
weekly_velocity: 0 / 3
Zero Stale Pipelines (>24h)(Tech Lead)
0%
stale_pipelines: 0 / 0
Dashboard Engagement > 30 Sessions/Day(Analytics)
0%
daily_sessions: 0 / 30
Email Subscriber List > 200(Marketing)
0%
email_subs: 0 / 200
3 Published Posts Per Week(Marketing)
33%
weekly_posts: 1 / 3
500 Weekly Unique Visitors(Marketing)
0%
weekly_uniques: 0 / 500
Define & Publish Pricing Page(CEO)
0%
milestone: 0 / 1
$1,000 Monthly Recurring Revenue(CEO)
0%
mrr_usd: 0 / 1000
First Paying Subscriber(CEO)
0%
paying_users: 0 / 1

Recent Meetings

strategycompleted30 Mar

## SUMMARY The executive meeting revealed a consensus that Picking Solutions is failing to convert users to paid subscribers due to a lack of clearly proven value for mid-market UK warehouse managers, despite significant content output (136 posts) and data assets (14,250 pipeline items). There is strong agreement on the need to validate customer pain points and refine our value proposition before finalizing pricing, though disagreement persists on whether to prioritize immediate pricing tests (CEO, Marketing Chief) or delay until value is proven (Analytics Chief, Product Manager). A critical operational issue emerged with the Tech Team Lead highlighting stale data pipelines (over 1000 hours outdated), which undermines our credibility and must be addressed before customer outreach. Debate also surfaced on what customers will pay for—ranging from actionable tools like pick-path optimization (CEO, Product Manager) to vendor-agnostic intelligence (Marketing Chief)—with all agreeing our positioning needs sharper focus. ## KEY DECISIONS - **Value Proposition Validation First:** We will prioritize customer interviews to define the specific pain points (e.g., labour costs, throughput issues) mid-market UK warehouse managers face before finalizing pricing or launching paid offers. - **Operational Reliability as Prerequisite:** Stale data pipelines (Lumen Social Intelligence Collector and x-grok-collector) must be fixed before any customer trials or outreach to ensure our intelligence is credible and fresh (<24h latency). - **No Pricing Launch Yet:** We will delay pricing decisions (rejecting immediate tiers of £99-£499/month or single £249/month offer) until customer feedback confirms what they’ll pay for and infrastructure issues are resolved. - **Target Persona Confirmed:** Our first outreach will focus on warehouse operations directors at 100-200 employee logistics firms in the UK, particularly in regions like the Midlands, who are time-poor and skeptical of vendor hype. ## ACTION ITEMS - **Action:** Conduct a 5-customer interview sprint to identify top automation decision pain points and how success is measured. **Owner:** Marketing Chief (with support from Product Manager) **Priority:** High - **Action:** Execute an emergency infrastructure sprint to fix the two stale data pipelines (Lumen Social Intelligence Collector and x-grok-collector) and ensure <24h data freshness. **Owner:** Tech Team Lead **Priority:** High - **Action:** Implement an observable systems audit for all 7 scheduled tasks to prevent future pipeline failures of 1000+ hours. **Owner:** Tech Team Lead **Priority:** High - **Action:** Analyze current content engagement metrics to identify which posts or topics (if any) are resonating with our audience and why. **Owner:** Analytics Chief **Priority:** Medium - **Action:** Prepare a stripped-down Lumen Pro version for a potential 14-day free trial, pending infrastructure fixes and customer interview insights. **Owner:** Product Manager **Priority:** Medium ## OPEN QUESTIONS - **Pricing Timing and Structure:** Should we test pricing with early adopters immediately after infrastructure fixes (as per CEO and Marketing Chief), or wait until we have measurable ROI proof from trials (as per Analytics Chief and Product Manager)? Founder input is needed to resolve this Type 1 decision. - **Core Value Proposition:** What specific problem will customers pay to solve—actionable tools like pick-path optimization (CEO, Product Manager), or vendor-agnostic intelligence (Marketing Chief)? Customer interviews will inform this, but founder perspective on strategic focus is requested. - **Trial Metrics:** If we proceed with a free trial post-infrastructure fixes, what specific metrics should we track to prove ROI to prospects (as raised by Product Manager)? Founder input on success criteria is needed. As the CEO of Picking Solutions, I’m driving this synthesis with a first-principles lens, acknowledging the painful reality that we’ve built a product but failed to prove its worth to customers. Drawing on Bezos’s customer obsession, we must start with warehouse managers’ urgent needs—hence the high-priority interviews. Musk’s iteration speed and Dalio’s pain-plus-reflection push us to fix operational failures immediately (stale pipelines) and learn systematically from engagement data. Thiel’s monopoly theory and Sun Tzu’s terrain advantage remind us to carve a unique position—whether through tools or intelligence, we must be indispensable. These actions balance tactical speed on reversible decisions (Type 2, like interviews) with careful deliberation on irreversible ones (Type 1, like pricing), and I await founder input to resolve the open strategic tensions.

strategycancelled30 Mar

Meeting failed after 4 turns: LLM API error (anthropic/claude-sonnet-4-20250514): 400 - {"error":{"code":"invalid_request_error","message":"Your credit balance is too low to access the Anthropic API. Please go to Plans & Billing to upgrade or purchase credits.","type":"invalid_request_error","param":null}}

The Stack

Everything runs on a single Next.js app. No microservices. No Kubernetes. One repo.

Frontend
Next.js 14 (App Router) + Tailwind CSS + shadcn/ui
SSR + client components, theme-aware
Backend
Next.js API Routes + Prisma ORM
70+ tables, 200k+ rows in PostgreSQL
LLM
Abacus.AI RouteLLM + xAI Grok-3
Provider-agnostic adapter, per-agent model selection
Data Pipeline
10 scheduled tasks (cron)
RSS, APIs, social intel, briefings, blog generation
AI Exec Team
5 agents, 17 personas, 35 mental models
Turn-based meetings, daily briefings, parametric sliders
Hosting
Abacus.AI (app + DB + storage)
Standalone build, auto-deploy from checkpoint

The Build Log

A 7-part series documenting each phase of the build. Honest, practical, with real prompts and real costs.

Building in the Open — series cover showing a transparent glass structure being assembled by AI
7-Part Series

Building in the Open

Follow the Experiment

This isn't a polished pitch deck. It's a live system being built, tested, and iterated on in public. The agents are real. The numbers update. The mistakes are documented.