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.
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.
The Spark
AI matured from novelty to genuine creative amplifier. The barrier was never capability — it was permission to begin. So I began.
30-Day Rapid Build
From blank repo to live signals, tools, premium dashboards, and a flywheel. DeepAgent as co-pilot. Human direction, AI amplification.
Launch + Transparency
Went live with daily feeds, Lumen Pro, intelligence pipeline. Decided to build in the open — showing everything, hiding nothing.
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.
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.
Act II — The Experiment
Can an AI executive team run a company? We're finding out — live.
System Architecture
Agent Roster
Active Targets (Live)
Recent Meetings
## 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 A critical operational issue emerged with the Tech Team Lead highlighting stale data pipelines (over 1000 hours outdated), which undermines our credibility and must be addressed before customer outreach.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.
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.
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
Build Log #1: The Spark (Dec 2025)
Why now, after 7 years of sitting on the idea
Build Log #2: Day 1-7 — From Idea to First Signals
Initial DeepAgent prompts, feed architecture, first data flows
Build Log #3: Week 2 — Tools & Calculators
Battery revenue, home savings, prices ticker builds
Build Log #4: Week 3 — Premium Lumen & Convergence Pillars
Forecaster tool, tokenized assets, reports pipeline
Build Log #5: Week 4 — Visuals, Metrics & the Flywheel
Charts, on-chain integrations, social automation
Build Log #6: Lessons from 30 Days Solo with AI
What worked, what didn't, real costs, honest surprises
Build Log #7: What's Next — The Autonomous Company Experiment
The autonomous company experiment and roadmap
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.
