Conversations and feedback
Conversations show where a system helps and fails.
What you will learn
- Explain: define success before optimizing
- Apply the idea in an example: Conversations and feedback
- Recognize limitations and verify the exercise outcome
Conversations show where a system helps and fails. Turn feedback into a cause and a test.
These steps refer to features identified in the application code. This material has not been validated on a live instance; check the documentation and the options in your version.
How it works, step by step
Define success before optimizing
Prepare representative requests and expected answers or properties. Include ordinary cases, ambiguity, missing data and tool errors. For RAG, measure evidence retrieval separately from answer correctness. Recall@k measures the share of relevant evidence found in the first k results; precision@k measures the share of returned results that are relevant. For agents, also track actions, permissions and stopping. An LLM-as-judge can speed evaluation but needs calibration against humans. Do not change prompt, model and index simultaneously if you want to understand what improved results.
Fluency and truth are checked separately
A hallucination is unsupported or incorrect content presented as an answer. It can arise from missing information, ambiguity or incorrectly combined patterns. Ask for evidence and check the original document, date, units and conditions. A real citation may still fail to support the claim. Use current sources for current facts, a calculator for arithmetic, and “cannot determine” when evidence is missing. Do not treat confidence expressed in prose as a calibrated probability.
Errors need explicit paths
A timeout differs from a permission error. Retry only transient errors, with bounded attempts and increasing delays. An operation with side effects may execute before its response is lost; retrying without an idempotency key can duplicate the effect. Streaming shows progress but does not guarantee completion. Checkpoints may allow failed stages to resume within runtime limits. Store the run identifier, stage, duration and error while removing secrets from logs. Measure slow paths as well as averages.
The visual map
Follow the solid arrows for the main flow. Dashed blue arrows supply data or context; dashed pink arrows show feedback or returning results. Colors and shapes distinguish models, stores, decisions and outputs. On smaller screens, scroll horizontally to follow the entire diagram.
A complete example
“Unhelpful answer” can mean a wrong deadline, technical language or an unavailable tool. Read the conversation, identify the cause and add a regression case.
Try it yourself
- Review ten fictional conversations and group failures by cause.
- Record the input, source and expected outcome before running the experiment. Use only the fictional data in the example.
- Follow the diagram stages. At every step record what information is received and produced; do not confuse intermediate output with the final outcome.
- Repeat after removing necessary information or making the input ambiguous. Check whether the system clarifies, stops or invents an answer.
- Compare with the explained solution. Keep the configuration, date, result and an explanation for differences. Change one thing and retest.
An explained solution
Each observation has a cause, proposed change and follow-up check. A successful exercise lets you show the connection between input, stages and outcome. When information is missing, a cautious answer is more useful than invented details. Compare more than style: check conditions, sources and operations too.
When it helps and what can go wrong
Positive feedback is not a guaranteed truth label. Choose this approach when it improves a measured need. Keep a simple baseline and compare outcomes using identical inputs. One successful example does not establish reliability in every situation.
Check your understanding
Does a good style score prove agent success?
No. The agent may write beautifully after using the wrong tool or data.
Is a link in an answer enough?
No; it must support the specific claim and fit the time and circumstances.
What outcome should this exercise produce?
Each observation has a cause, proposed change and follow-up check.
Words to remember
- Regresie / Regression: A change that breaks a previously correct case.
- Grounding: Grounding an answer in verifiable evidence.
- Idempotency: Controlled repetition without duplicating an effect.
Sources and your next step
To prepare: U03 — Stop, Resume and Restart