Tip #3: Use Copilot as a sparring partner

Think together before writing code — use plan mode to explore approach and tradeoffs.

February 23, 2026 Â· 2 min Â· Kjetil J.D.

Tip #16: Explore before you edit

Use the agent as a research assistant to understand unfamiliar code before changing anything.

March 13, 2026 Â· 2 min Â· Kjetil J.D.

Tip #17: Keep sessions short and focused

One task per session. Context fills up — fresh starts beat accumulated corrections.

March 13, 2026 Â· 2 min Â· Kjetil J.D.

Tip #18: Commit before you let the agent loose

Git stash or commit first, so the agent’s changes are always one git diff away from a clean state.

March 14, 2026 Â· 2 min Â· Kjetil J.D.

Tip #19: Get a second opinion from a fresh agent

Open a second session to re-ask the same question without baggage from earlier attempts.

March 16, 2026 Â· 2 min Â· Kjetil J.D.

Tip #20: Give your agents their own workspaces

Use isolated workspaces so multiple agents can work on the same repo without stepping on each other.

March 17, 2026 Â· 2 min Â· Kjetil J.D.

Tip #22: Use scripts for repeatable tasks

Deterministic tasks deserve deterministic scripts — not AI improvisation every session.

March 18, 2026 Â· 2 min Â· Kjetil J.D.

Tip #23: Write scripts that guide the agent

Script output goes straight into the agent’s context window. Design it to say what happened and what to do next — not just what ran.

March 19, 2026 Â· 2 min Â· Kjetil J.D.

Tip #24: Automate the boring parts with hooks

Hooks are shell commands that fire automatically at agent lifecycle points — before/after a tool runs, on session start, on finish. Unlike instruction files, they’re deterministic. Enforce your venv rule, run tests after edits, get a desktop notification when the agent is done.

April 16, 2026 Â· 2 min Â· Kjetil J.D.