Area 03 · AI Agents · Concept 05 of 20

Reflection

The agent reviews its own output and tries again to fix mistakes.

01–10 · The basePhase 3 · Weeks 11–14≈ 45 min

The idea

Reflection adds a review step: after producing a draft, the model (or a second model call with a critic prompt) checks it against the task and criteria, lists problems, and revises. It catches missing requirements, wrong formats and obvious errors.

It works best with concrete checks: run the code and read the error, validate JSON against the schema, compare the answer with the sources. A critic with no new information often just rubber-stamps the draft.

Each reflection round costs a full call. Limit rounds (one or two) and stop early when checks pass.

Why it matters

It is a simple way to raise quality on tasks with checkable criteria, like code that must pass tests.

Picture it

Words to know

  • Evaluator-optimiserA generator and a critic in a loop.

Try it without code

Critique your own draft

  1. Ask a chat app to write a function.
  2. Then ask it to list three bugs or edge cases in its own code and fix them.
  3. Run both versions.

Use it in code

Generate code, run tests, feed failures back, up to two rounds.

python
import subprocess, anthropic
client = anthropic.Anthropic()

def generate(prompt):
    m = client.messages.create(model="claude-sonnet-5-5", max_tokens=1200,
                               messages=[{"role": "user", "content": prompt + "\nReturn only Python code."}])
    return m.content[0].text.strip().removeprefix("```python").removesuffix("```")

task = "Write slugify(text) that lowercases, replaces spaces with '-', and strips punctuation."
code = generate(task)
for round_ in range(2):
    open("slug.py", "w").write(code)
    res = subprocess.run(["python", "-m", "pytest", "-q", "test_slug.py"], capture_output=True, text=True)
    if res.returncode == 0:
        print("tests pass"); break
    code = generate(f"{task}\nYour code:\n{code}\nTest failures:\n{res.stdout[-2000:]}\nFix it.")
PRACTICE · TICK IT AFTER THIS

Write 5 pytest cases for a small function and measure how often one reflection round turns a failing draft into a passing one.

Common mistakes

  • Reflection with no external signal.
  • Unlimited revise loops.

Go deeper