cd /news/ai-agents/agent-task-briefing-checklist-10-ant… · home › topics › ai-agents › article
[ARTICLE · art-142461] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Agent task briefing checklist — 10 anti-patterns (free)

A developer published a checklist of 10 anti-patterns that cause AI agent tasks to fail, arguing that most breakdowns trace back to the task brief rather than the model. The list pairs each failure mode — such as vague goals like "make it better," unbounded repo write access, and pasted API keys — with a one-line fix, including naming the artifact and acceptance test, allowlisting directories, and pointing to a secret manager instead of embedding credentials. The checklist is offered as a free excerpt from a set of paid briefing templates.

by read1 min views1 publishedSep 30, 2026

If you hand work to an AI agent (Cursor, Claude Code, Codex, custom agents), most failures trace back to the brief, not the model. Here are 10 anti-patterns I keep seeing, each with a one-line fix. Copy freely. Smell these in your briefs. Each wastes tokens, time, or trust.

“Make it better.” / “Clean this up.” / “Explore options.”

Fix: Name the artifact and the acceptance test.

Tools say “repo write: Y” with no path limits.

Fix: Allowlist directories; forbid .env, secrets, infra by default.

“Research the market” with no table, memo, or decision.

Fix: Definition of Done = files a human will open in a meeting.

“Be exhaustive” + “max 10 minutes” + “cite everything.”

Fix: Rank constraints; mark Hard vs Soft.

API keys in the brief “for convenience.”

Fix: Point to a secret manager / env name; never paste values.

“Whatever you need to get it done.”

Fix: Escalation table; stop conditions.

No human owner → agent invents product policy.

Fix: Owner field required; acceptance is a human step.

“Write in our voice” with no voice doc or samples.

Fix: Link 2 good examples or a 10-line voice sheet.

“Confidence must be 95%.”

Fix: Ask for source grades and assumption tags instead.

Out of scope empty → agent expands forever.

Fix: At least two explicit non-goals.

This is a free excerpt from a small set of briefing templates I sell. If you want the full fill-in-the-blank packs (briefing, eval, digest, research, incident), they're at https://briefstack.surge.sh/ — the list above is useful on its own either way.

── more in #ai-agents 4 stories · sorted by recency
── more on @cursor 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/agent-task-briefing-…] indexed:0 read:1min 2026-09-30 · —