The problem
What the customer needs
- A consistent method for fixing a bad output, not a different guess every time.
- To avoid wasting time regenerating the same weak result over and over with no real change.
- To know when the problem is genuinely "this model tier can't do this" versus something fixable in how the task was set up.
Why naive approaches fail
- Hitting regenerate repeatedly hoping for a better roll, without changing anything about the prompt or context.
- Assuming a weak output means "the model isn't good enough" and escalating to a higher tier, when the real problem was missing context.
- Quietly rewriting the output by hand every time without ever diagnosing why it came back weak, so the same problem repeats on the next task.
- The specific reason the output was weak has been identified, not just "it wasn't great"
- A fix was applied to the actual cause, prompt specificity, missing context, or a missing example, before regenerating
- Model-tier escalation is used only after prompting and context fixes have been ruled out
- The diagnosis is fast, a couple of minutes, not a long investigation
The system
What each part does
5 components, each owns a concept. Click any card to drill into the underlying primitive.
Weak-Output Diagnosis
name the specific problem first
Before touching the prompt again, name precisely what's wrong: too generic, missing a specific requirement, wrong tone for the audience, factually off, or structurally not what was asked for. "It wasn't great" isn't a diagnosis, it's a shrug.
Configuration
One sentence: "This is too generic because it doesn't reference our client's specific situation" is a diagnosis. "This isn't good" is not.
Prompt Specificity Check
the first thing to check, almost always
Most weak outputs trace back to a vague or underspecified prompt: no stated audience, no stated format, no stated constraints. Before considering anything else, check whether the original ask actually told Claude what a good answer would look like.
Configuration
Did the prompt state who this is for, what format it should take, and what "good" looks like? If any of these were left implicit, that's very likely the actual problem.
Context Completeness Check
did Claude actually have what it needed
If the prompt was reasonably specific, check next whether Claude had the actual source material it needed, the client background, the prior decisions, the relevant data, or whether it was working from a vague description of those things instead.
Configuration
Was the actual source document attached, or was it described from memory in the prompt? Missing or paraphrased context is the second most common cause of a weak output, right behind prompt vagueness.
Example Anchor Check
would a sample of "good" have helped
For tasks where tone, format, or style matters and is hard to describe in words, check whether providing one concrete example of a similarly good output would have anchored Claude more effectively than more description would.
Configuration
If the task is genuinely about matching a specific voice or format (a particular report style, a particular tone), one short example usually outperforms another paragraph of description.
Model-Tier Escalation Check
the last thing to check, not the first
Only after prompt specificity, context completeness, and example-anchoring have been ruled out as the cause, consider whether the task genuinely exceeds the current model tier's reasoning capability and warrants a tier upgrade for this specific task.
Configuration
Ask: if I fixed the specificity, context, and examples and the output is still weak on genuinely hard reasoning, that's a real signal to escalate tier. If those weren't fixed first, tier escalation is premature.
Data flow
6 steps to production
Name the specific problem with the output
Write one sentence describing precisely what's wrong: too generic, missing a stated requirement, wrong tone, factually off, or wrong structure. This single step prevents the common failure of regenerating repeatedly without ever identifying what actually needs to change.
↪ Concept: adjusting-approach-from-feedbackCheck prompt specificity first
Look back at the original prompt: did it state the audience, the format, and what a good answer would look like? Most weak outputs trace back to an underspecified prompt, so this is almost always the first thing to check, not the last.
↪ Concept: task-type-prompting-strategiesCheck whether Claude had the actual source material
If specificity looks fine, check whether the real source documents were attached, or whether Claude was working from a paraphrased or partial description of them. Missing context produces weak, generic-sounding outputs that look like a capability problem but aren't.
Try one concrete example before assuming it's unfixable
For tone- or format-sensitive tasks, add one short example of a similarly good output and re-ask. This often resolves what looks like a stubborn quality problem faster than additional written description would.
Only then consider a model-tier escalation
If specificity, context, and an example have all been tried and the output is still weak specifically on hard reasoning, that's a genuine signal the task may need a stronger model tier. Escalating tier before trying the first three steps usually just produces a more expensive, still-weak output.
↪ Concept: optimizing-ai-workflows-for-efficiencyCarry the fix forward, not just for this one output
If the diagnosis was missing context or a vague prompt template, fix the underlying prompt or workflow so the next similar task doesn't hit the same problem. A one-time patch on a single output is a partial fix; catching the pattern is the real one.
The four decisions
| Decision | Right answer | Wrong answer | Why |
|---|---|---|---|
| First response to a weak output | Diagnose the specific cause before changing anything | Hit regenerate repeatedly and hope for a better result | Regenerating without changing the input rarely fixes a systematic problem like a vague prompt or missing context, it just produces variations of the same weak answer. |
| Output is generic and doesn't reflect the client's specifics | Check whether the actual source material was provided | Assume the model isn't capable enough and escalate tier | Generic output is the classic symptom of missing context, not insufficient model capability. Providing the real source material usually resolves it directly. |
| Order of troubleshooting steps | Prompt specificity → context → example → model tier, in that order | Jump straight to the highest model tier as a first move | Model-tier escalation is the most expensive and least likely fix for the majority of weak outputs, which trace back to specificity or context, not raw capability. |
| A weak output on a tone- or style-sensitive task | Provide one concrete example of the desired style | Write another paragraph trying to describe the style in words | Style and tone are often easier to show than to describe. A single good example frequently outperforms additional descriptive instruction. |
Where it breaks
4 failure pairs. Each maps to an exam-style question - the naive move on the left, the disciplined fix on the right.
A weak output gets regenerated five times in a row with no change to the prompt or context, producing five variations of the same problem.
AP-CCAOF-D7-01Diagnose the specific cause first, then change the actual input (prompt, context, or example) before regenerating.
A generic-feeling output gets treated as a capability problem, and the task is immediately rerun on the highest model tier without changing anything else.
AP-CCAOF-D7-02Check prompt specificity and context completeness first. Most generic outputs are a missing-context problem, not a capability ceiling.
A team member rewrites a weak output by hand every time without ever figuring out why it came back weak, so the same issue recurs on the next similar task.
AP-CCAOF-D1-03Take the extra minute to name the specific cause and fix the underlying prompt or context, so the fix carries forward to future tasks.
A weak, off-tone output gets re-prompted with three more paragraphs of description of the desired tone, with limited improvement.
AP-CCAOF-D1-04Provide one concrete example of the desired tone or format instead of adding more descriptive instruction.
Cost & latency
The four-step check (specificity, context, example, tier) is designed to be fast enough to run every time a weak output appears, not just on the worst cases.
Diagnosing the actual cause before re-asking converges on a good output far faster than repeated undirected regeneration.
Since specificity and context problems are far more common than genuine capability limits, checking them first avoids paying for a tier upgrade that wasn't the actual fix.
Diagnosing the root cause, not just patching one output, improves the underlying prompt or workflow so the same problem doesn't recur on the next similar task.
Ship checklist
Two passes. Build-time gates verify the code; run-time gates verify the system in production.
Build-time
- Specific problem with the weak output named in one sentence before any fix is attempted↗ adjusting-approach-from-feedback
- Original prompt checked for stated audience, format, and definition of "good"↗ task-type-prompting-strategies
- Confirmed whether actual source material was attached versus paraphrased
- One concrete example tried for tone- or format-sensitive tasks before assuming it's unfixable
- Model-tier escalation considered only after the first three checks were tried↗ optimizing-ai-workflows-for-efficiency
- Underlying prompt or workflow fixed, not just the single weak output patched
Run-time
- Team defaults to diagnosing a weak output before regenerating or rewriting by hand
- Prompt-specificity and context checks are run in that order before considering tier escalation
- Team keeps a short library of good examples for tone/format-sensitive recurring tasks
- Root-cause fixes get carried into the underlying prompt or Project setup, not just patched once
- Team knows the signal for a genuine model-tier escalation versus a fixable prompting or context gap