Chapter BChain-of-Thought PromptingPage 2 of 8

Chain-of-Thought Prompting

Pack the right inputs

Context is a curated evidence packet, not a dump of everything the tool can accept.

~14 minInputs and context

Before you start

Why this matters

Without opening an AI tool, write the acceptance test for this job: make a multi-constraint laptop recommendation auditable without requesting hidden reasoning. Name one fact that must be exact, one judgment a person must make, and one condition that should stop the workflow. Compare your answer with the professional standard below; the gap is what you should practice.

1Learn the idea

Read

Build the input packet

For make a multi-constraint laptop recommendation auditable without requesting hidden reasoning, assemble only what changes the answer: candidate options, authoritative specifications, weighted criteria, constraints, missing facts, calculation method, and required output format. Label each item by authority and date. A source-of-truth document outranks a memory-based note; a current error log outranks a description of last month's behavior. State conflicts instead of letting the model blend them.

Use a four-part packet: task, evidence, constraints, and output contract. Put untrusted content inside clear delimiters and say that it is data, not instruction. Include representative examples, especially one normal case and one boundary case. Omit irrelevant history; excess context can hide the one line that controls the result.

Read

A concrete handoff

Compare three laptops for college using price, measured battery life, weight, and required-software compatibility. First output a short comparison plan and evidence table. Then recommend one in under 150 words with three deciding facts. Finally list unknowns to verify on seller pages. Give concise rationale, not private hidden reasoning.

Before sending, annotate the packet. Mark which values are verified, which are illustrative, and which are unknown. If a screenshot is involved, transcribe critical small text. If structured data is involved, include headers, units, software version, and null behavior. If creative material is involved, record ownership and permitted use. This is how context becomes operational rather than decorative.

A useful response would look like this: A criteria table, explicit unknowns, a short recommendation tied to three inspectable facts, and a verification checklist. That description is intentionally observable. “Looks good” is not acceptance. The operator must open authoritative product pages, recalculate weighted scores, check units and model variants, test software requirements, and see whether the recommendation changes under reasonable weights. Keep the source material beside the draft so review means comparison, not memory.

Read

Minimize and protect

The privacy boundary is specific: do not include account details, private purchase history, or personally sensitive constraints unless they are necessary and safe to share. Create the smallest synthetic example that preserves the problem. Replace names and identifiers consistently so relationships remain testable. Redaction is not merely drawing a box: crop surrounding notifications, remove metadata where relevant, and check that hidden sheets, comments, or revision history are not included.

Poor packets lead to predictable failures: equating longer rationale with truth; post-hoc justification; invented specifications; hidden weighting; arithmetic that cannot be reproduced. Another common failure is silently changing the source packet mid-run. Save a version or hash of the inputs beside the output, especially when another person will reproduce the work.

Read

Context quality drill

Rate a packet from zero to two on six dimensions: relevance, authority, recency, completeness, privacy, and reproducibility. A score below two on authority or privacy blocks the run. A low completeness score does not invite invention; it creates a question for the owner.

Checking tutor…

Continue learning · glossary & guides