Taivo Pungas Taivo Pungas

Skills, not agents

I used to think shipping an agent product meant building: 1. The core LLM loop. 2. Skills: describing to the LLM how to do particular things (including building

1 Jan 2026 · 1 min read

AI Ranch podcast with Evalds Urtans

Mostly talking about AI, Pactum and selling to enterprises. It was recorded at the end of August, so some things are already likely stale! Find the podcast on

24 Dec 2025 · 2 min read

Principal

I recently noticed that it's a bit clunky to talk about "users" of our agents. Building complex enterprise software, we have multiple types of

13 Dec 2025 · 1 min read

Anchor on what won't change

When things are stable, you make plans by anchoring to the question "what will change?". With your customers, your company, technology, regulation or anything else about

26 Nov 2025 · 1 min read

Invest into context

I have a 14,000-word document I maintain manually, to add into ChatGPT queries I make related to my role as CTO. It covers a lot of ground

26 Aug 2025 · 2 min read

My deep research use cases

Deep research is underappreciated. The feature exists in all three LLM chat apps I pay for (ChatGPT, Claude and Gemini) and is unfortunately heavily rate limited, which makes

12 Aug 2025 · 3 min read

Shaping is high-leverage work for leaders

I've recently seen several engineers struggle when moving to the role of leading a small product team and managing a couple engineers. There are so many

23 Jul 2025 · 2 min read

Are software jobs set to grow or shrink?

There seem to be two views of what will happen with engineers' jobs given the new efficiencies from using advanced AI coding tools (Cursor, Claude Code, etc)

5 Jul 2025 · 2 min read