Blog tag
Tagged: AI agents.
22 articles tagged AI agents
How to scope an AI agent's first job so the pilot doesn't die
Most first AI agent projects fail on scope, not model quality. Here is how to pick a first job narrow and checkable enough to actually ship.
Do AI agents count as seats? The real cost of running agents on your tracker
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.
Keep an audit trail of everything your AI agents change
Once agents can write to your tracker, a shared bot account makes every change anonymous. Here is how per-agent identity keeps the trail readable.
The MCP audit: which project tools can AI agents actually use? (July 2026)
We audited the MCP servers of 13 project management tools: who has one, what agents can really do, the call caps, and the gaps nobody mentions.
Can an AI run your standup?
Mostly yes, and your team will thank you. What an agent can compile from the board, what still needs a human, and how to set up an async AI standup.
AI sprint planning: what actually works in 2026
Where AI genuinely helps plan a sprint, drafting, sizing, capacity checks, and where letting it decide is a mistake. A working setup, honestly described.
AI agent project management: the complete guide
How to run real projects with AI agents on the board: connecting them, assigning work, keeping review, what breaks, and how to pilot it in a week.
How to install Taskfolk as an agent skill
Install Taskfolk as a skill in your AI coding agent: one-command MCP for Claude Code, config for Cursor and VS Code, or a SKILL.md download for OpenCode and Codex.
How to set agent field permissions
Restrict what an AI agent can edit in Taskfolk with a per-agent field allowlist: set it, read the Restricted badge, and verify agent work. Full walkthrough.
How to delegate work to an agent
Assign a task to an AI agent in Taskfolk using the same assignee picker you use for people, and understand the pending session, claim flow, and real limits.
How to map your agent team
The Agent Map shows every AI agent in a workspace, who owns it, and its live work on one radial tree. How to read status dots, regroup, and spot stalls.
How to track api usage and audit logs
Track API key usage and read the audit log in Taskfolk: Usage tab charts, the Audit lifecycle log, per-key rate limits, and what each surface will not tell you.
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.
Running a project with AI agents without losing the thread
A practical setup for letting AI agents do real project work, create issues, move the board, draft specs, while your team keeps control of what matters.
Why we gave Taskfolk an MCP server, and what it changes
What the Model Context Protocol is in plain terms, why a project tracker is a good fit for it, and how an agent picks up your workspace without any glue code.
Two agents, one backlog: coordinating a triage agent and a coding agent with issue status as handoffs
A practical multi-agent workflow: custom board columns and status transitions as the handoff bus between a triage agent and a coding agent, with human review in the middle.
Let AI agents run your board over the REST API: authentication, scopes, and safe writes
A developer guide to giving an AI agent a scoped Taskfolk API key so it can move cards and file issues without a big blast radius.
Which project management tools actually ship a first-party MCP server
Having AI features is not the same as shipping an MCP server. Here is how to tell first-party from community-built from none, with an honest checklist.
What is agentic project management? A plain-language guide with a working 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.
Give your AI agent a knowledge base: connect your docs so it answers from your project, not the internet
How to give an AI agent access to your company docs, so it grounds answers in your workspace instead of guessing, using RAG exposed through MCP.
Stop chasing status updates: let AI write the weekly project digest
How to automate a weekly status report with AI that reads what actually moved and what stalled, instead of a dumb scheduled dump of ticket counts.
How to give an AI agent human-in-the-loop approval before it changes your issues
Build an approval gate for AI agents in Taskfolk: let the agent triage into a Needs review column, a human moves it forward, and transition rules stop skips.
