About this episode
What actually makes software an AI agent? A plain walk-through of the model, the tools it can call and the loop around them, built up step by step on a small sales-analysis agent. Then how to tell an agent from a workflow with AI inside, and how capable agents really are today.
Written by Kiran Krishna. Narrated with an AI voice. · LinkedIn
In this episode
Sources check every one
- Gartner, 25 June 2025, on agentic AI vendors and "agent washing" gartner.com
- Anthropic, Building effective agents (19 December 2024) anthropic.com
- OpenAI, A practical guide to building agents (2025) cdn.openai.com
- Simon Willison, on the agreed definition of an agent (18 September 2025) simonwillison.net
- METR, Measuring AI Ability to Complete Long Tasks (2025) arxiv.org
- METR, Time Horizon 1.1 (29 January 2026) metr.org
- METR, time horizons of frontier models (data to May 2026) metr.org
