Blog
AI project management, in practice.
7 articles in Concepts
Prompt injection starts in the ticket your agent reads
A stranger can write the ticket your AI agent reads. Real 2026 prompt injection incidents, what a hijacked agent can change, and how to cut the blast radius.
Cycle time vs lead time (and how to actually measure both)
Cycle time vs lead time: what each measures, how to compute both from issue history, reading p50/p75 and the histogram, and how Taskfolk, Jira and Linear compare.
What is an AI project manager? What one actually does today
A plain definition of the AI project manager: the three things the term means, a week of real work on a live board, and the parts only a human can hold.
Decision rights between your team and your AI agents
A simple rule for AI governance: reversible, low-stakes moves are the agent's to make; irreversible or high-stakes ones need a human. How to draw the line.
Do AI agents count as seats? The real cost of running them
Two costs get blurred together: paying a seat per bot, and the tokens the model burns. Here is how to separate them and estimate what agents actually cost.
Should your agent use MCP or the REST API?
MCP and a REST API solve overlapping problems for AI agents. Here is a plain guide to when each one is the right call, and why you often want both.
What is agentic project management? A plain guide with an example
A copilot waits for your prompt. An agent acts on an event. Here is the perceive-plan-act-check loop explained, with one real end-to-end run inside Taskfolk.
