AdvancedEvaluation & GuardrailsFree prompt

Diagnose Why an Agent Keeps Failing in Production

Analyze an agent's failing traces to classify root causes — prompt, tools, model, or data — and prescribe the highest-leverage fix.

Turn a pile of bad runs into a ranked list of root causes and concrete fixes instead of guessing what to tweak.

debuggingobservabilityroot causereliabilitytraces

At a glance

Access

Free prompt

Open to copy — no account or payment needed.

Prompt objective

Turn a pile of bad runs into a ranked list of root causes and concrete fixes instead of guessing what to tweak.

Real use case

An agent's success rate dropped from 90% to 70% after a model upgrade. The team has 30 failing transcripts but no idea which knob to turn.

Customize these fields first

PURPOSEDEFINITIONPASTE 5-30 TRANSCRIPTS

Replace the placeholders with your own context before you run the prompt. That usually improves the first output more than adding more instructions later.

Prompt

Act as an AI agent reliability analyst. I will give you failing runs; classify the root causes and prescribe fixes.

Agent purpose: [PURPOSE]
What "success" means: [DEFINITION]
Failing runs (each with input, agent steps/tool calls, final output, and why it was wrong):
[PASTE 5-30 TRANSCRIPTS]

Analyze:
1. Classify each failure into a root-cause category: prompt/instruction gap, tool error or bad tool description, missing/incorrect context or retrieval, model limitation, or user-input problem.
2. Tally the categories and rank them by frequency and impact.
3. For the top 2-3 categories, give the specific fix (exact prompt edit, tool-description change, retrieval fix, guardrail, or model/setting change) and the failing runs it would resolve.
4. Estimate expected lift and any risk each fix introduces.
5. Recommend one eval to add so this class of failure is caught automatically next time.

Be concrete and evidence-based — cite specific runs. Avoid generic advice.

Open directly in an AI — the text is pre-filled:

How to use this prompt

  1. 1Replace the key placeholders first: PURPOSE, DEFINITION, PASTE 5-30 TRANSCRIPTS.
  2. 2Replace any bracketed placeholders like [this] with your own context.
  3. 3Add extra background information when you want more tailored results.
  4. 4Combine multiple prompts in one conversation when you need a richer output.
  5. 5Save your best-performing prompts so they are easy to reuse later.

Next best step

Open the guide first, then branch only if you still need more.

A guide for technical builders choosing between prompts, coding workflows, and agent-based implementation.

If this prompt is close but not quite right, generate variants next. If the job is recurring, move into the course library after the guide.

Related prompts

View all

Explore other prompt categories

Move sideways into adjacent libraries when the current category is not the full answer.

Every prompt here is free. The course teaches the thinking behind them.

Copy as many prompts as you like. When you want to move from single prompts to a repeatable AI workflow, Learn AI in 30 Days walks through it, one day at a time.

Get the courseSee the 30-day curriculum first

Buy the course once ($15/$20 by length), or go all-access for $10/mo with a verifiable certificate.