Learnings

Insights, failures, and breakthroughs from our journey. Sharing what we learn as we build.

Subscribe via RSS
February 21, 2026
architecture agentic-ai

From Agents to Architecture: Determinism, Observability & Provider Boundaries

Hardened the Runner Agentic Intelligence spine: deterministic analytics replaced agent-driven computation, observability matured, and LLM providers were centralised behind LiteLLM.

Read Learning
February 14, 2026
architecture process

Formalising the Pattern Publication System

This week focused on evolving and stabilising the Architecture Pattern system by aligning process and governance rules into a coherent publication pipeline.

Read Learning
February 7, 2026
process architecture

From rapid iteration to a publishable system

This week focused on consolidating rapid experimentation into a repeatable system, aligning architecture, process, and UX in preparation for real user exposure.

Read Learning
January 30, 2026
process experimentation

Stress-testing the Ideas to Life system under real agentic load

This week focused on applying the Ideas to Life process to a running experiment, using real constraints to refine how decisions, tooling, and documentation interact.

Read Learning
January 23, 2026
process systems

From ad-hoc prompts to a coherent learning system

This week focused on stabilising workflows and reframing Weekly Learning as a synthesis layer, reducing drift while enabling multiple learning threads to coexist.

Read Learning
January 16, 2026
process philosophy

Stabilising the foundation before scaling experiments

A week focused on stabilising infrastructure and reducing technical friction instead of shipping new experiments.

Read Learning
January 9, 2026
process philosophy

The Power of Small Experiments

Why starting small and shipping often beats perfectionism every time.

Read Learning