Notes from the team.
Field notes on building production AI agents — workflows, automation, Claude Code, Hermes, and self-hosted deployment.
May 22, 2026 · 5 min
The Agent You're Building Will Probably Fail — and That's a Process Problem
Most agent projects fail for process reasons, not model ones. Six steps — ground truth, workflow redesign, evals before deployment, explicit human oversight, token-cost design, and change management — matter far more than the model, which is maybe 10% of whether the agent succeeds.
February 22, 2026 · 12 min
Agent Skills
Agent Skills package procedural knowledge into reusable folders — instructions, rules, templates, and optional scripts — that agents detect and apply automatically. The result: portable, composable, consistent workflows across platforms.
August 23, 2025 · 7 min
Why "The Lean Startup" Matters Today
Eric Ries' Lean Startup, distilled into 12 actionable principles across Vision, Steer, and Accelerate. Why validated learning and the Build–Measure–Learn loop still beat building in the dark — with examples from Dropbox, Tesla, and Airbnb.
March 21, 2025 · 5 min
A Dive into the MCP Framework
The Model Context Protocol is a universal adapter that lets AI assistants talk to external systems, data, and tools. A walk through MCP's client–server architecture: hosts, clients, and servers exposing resources, tools, and prompts.
December 14, 2024 · 4 min
Building LLMs for Production: Enhancing Prompt Effectiveness
Fifteen practical prompt-engineering tips for production LLMs. Ambiguity is the enemy: clear instructions, iterative refinement, edge-case testing, and treating prompts with the same version-control rigor as code.
December 2, 2023 · 6 min
Retrieval-Augmented Generation (RAG)
How RAG grounds LLMs in external knowledge to cut hallucinations and enable domain-specific answers — retrieve relevant documents, augment the prompt with that context, then generate, all without costly retraining.