S'inscrire gratuitement

Decompose a multi-step task into a prompt workflow

Auteur: AILesson10 min de préparationTesté avec:ChatGPTRévisé: 2026-08-28

Réponse rapide

Design bounded stages whose outputs, checks, tools, authority, and recovery paths fit together. Fournir: End-to-end task and desired outcome, Evidence, tools, authority, and risk constraints, Known failures and operating conditions. Résultat attendu: An executable workflow specification with step prompts, gates, state, and end-to-end tests.

1

Ajouter votre contexte

Votre texte reste dans ce navigateur. AILesson Prompts ne l’envoie ni à un modèle ni à un serveur.

2

Votre prompt

Les champs non remplis restent visibles sous forme d’espaces réservés, afin que vous puissiez quand même copier et modifier le prompt.

Design a prompt workflow for the multi-step task. Decompose only where a boundary improves evidence control, validation, tool use, reuse, cost, or human authority.

Trigger, users, starting inputs, final deliverable, definition of done, frequency, and scale:
[task]

Source systems, tools, freshness, privacy, approvals, irreversible actions, cost, latency, and prohibitions:
[constraints]

Current process, failure examples, handoffs, concurrency, retries, monitoring, and review capacity:
[failures]

Map the end-to-end state before writing prompts. Separate deterministic parsing/calculation/validation from generative judgment where practical. For each stage define purpose, allowed inputs and provenance, preconditions, exact output schema, invariants, tool permissions, prompt, model-independent validation, human gate, state persisted, idempotency or deduplication key, timeout/retry rule, failure route, and next-stage condition. Never let a later step silently repair missing or conflicting upstream evidence. Place authorization before external messages, purchases, publication, deletion, account changes, or other consequential actions. Minimize sensitive data passed between steps and state retention. Identify stages that should be ordinary code, rules, search, or a human decision instead of a prompt. Return a workflow map; step contracts and prompts; state/error taxonomy; observability and audit fields; cost/latency notes; rollback or safe-stop behavior; unit, boundary, failure, and end-to-end tests; and a simpler single-prompt alternative when it is sufficient.
Essayer dans le Playground
Privé par défautL’assemblage du prompt se fait localement dans votre navigateur. Évitez de placer des informations confidentielles dans un service d’IA, sauf si votre organisation l’autorise.

De l'entrée au résultat

Un exemple détaillé

Voyez comment un contexte concret transforme cette recette en résultat utilisable.

Entrée réelle

End-to-end task and desired outcome
Each weekday, convert up to 40 inbound vendor-renewal emails and attached text-extracted quotes into a review packet. Final packet: matched contract, changed commercial terms, operational changes, missing evidence, risk questions, and a draft reply. Procurement analyst approves any outgoing reply. Done when packet is traceable to message/attachment locations and queued for review; never auto-send.
Evidence, tools, authority, and risk constraints
Read-only mailbox and contract repository search. Attachments already extracted; no OCR. Prices and dates must be parsed exactly and recalculated by code. Contracts may contain confidential rates; retain in approved workspace only. No legal conclusion. Current facts require source timestamp. One model call costs more than validation code. Analyst can review ten exceptions/day. Reply tool is unavailable and must remain unavailable.
Known failures and operating conditions
Current giant prompt sometimes matches the wrong supplier with similar name, treats a quote as signed amendment, loses currency, and drafts acceptance. Duplicate forwarded emails create duplicate packets. Contract search can return zero or two active candidates. Model timeout may occur; retry once. Workflow platform stores status and source IDs.

Exemple de sortie

Recommended workflow has five stages, not five model calls. Stage 1 code gate ingests source IDs, hashes message plus attachments for deduplication, validates extraction, detects currency/date tokens, and stores restricted references—not raw confidential text in logs. Duplicate hash links to the existing packet. Stage 2 read-only search uses verified supplier identifiers; zero or multiple active contracts routes to analyst exception and stops. Name similarity alone never selects a contract.

Stage 3 code builds a provenance bundle: quoted spans, contract spans, timestamps, parsed money/date values, and recalculated deltas. Parse or currency conflict stops before generation. Stage 4 model compares only the bundle and returns a schema separating stated proposal, signed evidence status, commercial/operational change, missing evidence, questions, and source references. Its prompt forbids legal conclusions, acceptance language, and converting a quote into an amendment. Schema, citations, numbers, currencies, and unsupported-claim checks run afterward; one timeout retry uses the same idempotency key. Validation failure routes to exception, never a silent repair.

Stage 5 model drafts a neutral clarification reply only from validated fields, labeled DRAFT—NOT SENT. An analyst gate reviews packet and edits or approves queuing; there is no send permission. State machine: received, deduplicated, match_pending, evidence_ready, comparison_valid, draft_ready, review_required, exception. Audit records source IDs, contract version, prompt/version, validation results, timestamps, reviewer, and disposition. End-to-end tests cover exact match, duplicate forward, zero/two contracts, unsigned quote, conflicting currency, missing attachment, timeout, and malicious attachment instructions. A single prompt is inappropriate because matching, arithmetic, deduplication, and authorization require separate deterministic gates.

Pourquoi cela fonctionne

  1. 1

    Explicit stage contracts prevent uncertain upstream outputs from becoming unmarked facts downstream.

  2. 2

    Separating deterministic work and authority gates reduces cost and keeps consequential actions reviewable.

Vérifier le résultat

  • Does every transition have validated inputs, an explicit success condition, and a failure route?

  • Are tool permissions, sensitive data, persisted state, retries, and consequential actions bounded?

  • Are deterministic operations and human decisions kept out of generative prompts where appropriate?

Utilisez-la en toute confiance

Questions fréquentes

Des réponses pratiques sur le bon moment pour utiliser cette recette, ce qu’il faut fournir et les cas où une vérification humaine reste nécessaire.

What should I prepare before using “Decompose a multi-step task into a prompt workflow”?

For “Decompose a multi-step task into a prompt workflow,” prepare End-to-end task and desired outcome, Evidence, tools, authority, and risk constraints, and Known failures and operating conditions. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.

When is the “Decompose a multi-step task into a prompt workflow” result not ready to use?

The result is not ready if it does not yet deliver the stated outcome—An executable workflow specification with step prompts, gates, state, and end-to-end tests—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.

Which AI tools have recorded tests for “Decompose a multi-step task into a prompt workflow”?

The published test record for “Decompose a multi-step task into a prompt workflow” lists ChatGPT as of 2026-08-28. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.

Plus de façons d'explorer

Où se situe cette recette

Prompts texteConception de promptsPour les managers

Faites avancer votre travail

AILesson · Cours recommandés

Votre prochaine étape : mettez l’IA à contribution

Passez de la compréhension de l'IA à l'action. Entraînez-vous à formuler des requêtes, à évaluer et à améliorer les résultats grâce à des leçons interactives pour le travail et la vie quotidienne.

Découvrir tous les cours
Image de couverture de L’IA pour débutants

15 leçons interactives

L’IA pour débutants

Lancez une conversation utile avec une IA, améliorez sa réponse, vérifiez l’essentiel et sachez quand c’est à vous d’agir.

Découvrir ce cours
Image de couverture de Les bases de ChatGPT

10 leçons interactives

Les bases de ChatGPT

Découvrez ChatGPT à travers trois flux de travail pratiques : mener une première conversation, travailler à partir d’un fichier, puis utiliser Projects pour réutiliser un plan vérifié dans une nouvelle conversation.

Découvrir ce cours
Image de couverture de Comment fonctionne l’IA générative

7 leçons interactives

Comment fonctionne l’IA générative

Comprenez comment les systèmes courants de chat IA apprennent des structures linguistiques, utilisent les messages actuels, construisent leurs réponses et intègrent des sources et des outils.

Découvrir ce cours