Writing agent instructions: spell out judgment calls and boundaries like you would for a new teammate
JosephJacks_ · x · 2026-10-20
Part 3/7 of the Plane Agents series argues that a task like "triage new tickets" leaves the important decisions open: what makes a ticket urgent? What if impact is unclear? Which fields stay untouched? The rules you'd explain to a new teammate are what the agent needs too. The example agent config spells these out: only set Urgent when the customer can't work and has no workaround; ask the reporter instead of guessing when impact is unclear; never change the assignee or state. The takeaway: make implicit judgment criteria, boundaries, and non-actions explicit in agent instructions.
More from coding & agent
- Cua launches Spaces SDK to run Claude Code and any agent on compute you choose — Scobleizer · 2026-10-20
- Dev: top AI agents do more backup and verification on DB migrations than 99.99% of engineers — tristanbob · 2026-10-20
- 20 questions to answer before letting agents touch production data — Then_Respect_1964 · 2026-10-20
- Baseten webinar: how to evaluate open models for coding agents on your own codebase — baseten · 2026-10-20
- Every's Slack agent turns article links into videos with a storyboard-first workflow — every · 2026-10-20
- Don't be a meat proxy for your agent — make it a metal proxy for you — danshipper · 2026-10-20