IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

904 articles

07 Oct 2026 · 8 min read

agentic-ai

4. Prove Whether a Smaller Chatbot Is Good Enough

Build independent evaluation sets, score grounded answers and measure quality, cost and coverage together.

07 Oct 2026 · 10 min read

agentic-ai

5. Train the Behavior, Retrieve the Knowledge: A LoRA Playbook

Prepare supervised examples, configure an adapter experiment and decide whether fine-tuning earns its operational cost.

07 Oct 2026 · 8 min read

agentic-ai

6. Make the Chatbot Faster Without Quietly Making It Worse

Optimize context, output, caching, retrieval and inference using an end-to-end latency and token budget.

07 Oct 2026 · 8 min read

agentic-ai

7. Run a Private Chatbot as a Production Service

Plan tenant isolation, bounded tools, deployment gates, failure recovery and observability for a production chatbot.

07 Oct 2026 · 8 min read

agentic-ai

8. Price a Chatbot Product Around Real Unit Economics

Calculate cost per successful task, account for cache writes and capacity, and offer transparent client pricing.

07 Oct 2026 · 8 min read

agentic-ai

9. Design a Chatbot People Can Trust, Configure and Recover From

Specify answer and analysis workflows, safe configuration, accessible interactions and a practical demo walkthrough.

07 Oct 2026 · 8 min read

agentic-ai

1. Analyze the Work Before You Build the Chatbot

Define chatbot jobs, risk boundaries, quality targets and a measured path toward fewer model dependencies.

07 Oct 2026 · 10 min read

agentic-ai

2. Build a Data Agent That Can Explain Its Numbers

Design a governed data agent with a semantic layer, read-only tools, tenant isolation and verifiable answers.

07 Oct 2026 · 8 min read

agentic-ai

Building a Private Decision Layer for Chatbots on a CPU Homelab

A CPU-only chatbot and agent routing demo: trained classifier heads, bilingual tests, measured LXC latency, failure cases and a live homelab deployment.