Blog tag
Tagged: workflow.
22 articles tagged workflow
Your coding agent re-fixes code that was already fixed
AI agents patch already fixed code in 35 to 65 percent of stale tickets. What a work item must carry so a fresh session tells done from open.
The agent's pull request is 80 percent right. Now what?
An AI agent's PR that is useful but not mergeable has three exits: finish it, send it back, or close it and rewrite the ticket. How to pick in five minutes.
Onboarding a new engineer to code your agents wrote
Git blame points at a merge and whoever wrote the prompt has left. How to onboard a new engineer to a codebase your AI agents wrote, without guessing.
The agent stopped halfway and the board still says in progress
Your AI agent died at 60 percent and the ticket still says In Progress. How to pick up where an agent left off, and stop the board lying about it.
Who reviews your AI agents while you're on holiday
Who reviews AI agent work while you are on holiday? Triage every session, name a second owner, shrink write scope, and set an interrupt threshold.
Sprint planning with two capacities: your team and your agents
Sprint planning with AI agents needs two capacity numbers, not one. Size the agent track against reviewer hours, then run the meeting on two questions.
What your junior engineer does now that agents take the tickets
A staffing plan for leads: what a junior developer works on when AI agents do the tickets, from spec authorship to first review of agent pull requests.
You assigned it to an agent and nothing happened
You assigned a task to an AI agent and nothing happened. Why queued and working look identical on your board, and how to put a clock on every delegation.
How to split work between Claude Code, Codex and Cursor
How to split work between Claude Code, Codex and Cursor: a division of labour that holds up, and where the shared state lives since none of them reads the others.
AI made code review the bottleneck, not writing code
The AI code review bottleneck, checked against three 2026 datasets: the delay is queue wait, not review time, so a review bot aims at the wrong term.
Turn a PRD into epics, stories and tasks agents can build
Give your AI coding agents a plan they can build. Paste a PRD, Taskfolk drafts the backlog, then Cursor, Claude Code and Codex work it through your workflow.
Chat with your AI agents, then put them in a workflow
DM an AI agent or @mention it in a channel, watch it work, and connect agents and people on a canvas so a ticket routes itself through triage, build and review.
Claude Code task management: a real tracker, not a markdown file
Give Claude Code persistent, attributed task management by connecting a real tracker over MCP instead of a markdown file. Honest comparison to Task Master.
A Notion alternative for project management (docs plus a tracker)
A Notion alternative that keeps your docs and adds a real tracker: category-backed statuses, native sprints with carryover, computed burndown, agents over MCP.
A bug tracking workflow that runs from report to fix
Bug tracking workflow that runs report to fix in one tool: public intake form, AI triage, a board review gate, GitHub commit links, and auto-shipped releases.
A lightweight service desk from forms, automations, and a board
Lightweight service desk for small teams: build one from a public intake form, routing rules, automations, and a board with a review gate. Honestly costed vs JSM.
How to automate project management with AI
The right order to automate project management with AI: reporting first, intake second, execution agents last, and the decisions that should stay human.
How to manage a team of AI agents without losing track
AI team management day to day: a roster, live sessions, instant delegation, per-field permissions, and verified work when several AI agents run at once.
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.
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.
Two agents, one backlog: handing off by issue status
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.
Auto-triage new issues with AI: assign, label and prioritize
How to set up AI issue triage automation that classifies severity, labels, and routes new bugs and requests, with an honest line on what to let AI decide.
