Resource
How to Use Multi-Step Prompts
Big tasks fail in single prompts. Multi-step prompting breaks a goal into focused, sequential prompts — each output validated, then fed into the next.
Competitor Analysis Prompt Workflow
A sequential prompt workflow for competitor analysis: scope what the analysis must decide, evaluate every competitor on the same criteria, and end with findings a pricing or positioning call can rest on.
Overview
'Analyze our competitors' in one prompt returns a feature-table essay that informs nothing. The workflow version starts from the decision — what will this analysis change? — sets the criteria before looking at anyone, evaluates every competitor on those same criteria with evidence notes, and synthesizes into findings with confidence levels. This resource loads a 7-step competitor analysis scoped to a real trigger: a quarterly pricing decision.
How to use this resource
-
Build the loaded workflow
The pricing-decision goal at 7 steps loads the research arc with counter-evidence included.
-
Lock the decision first
Step 1 names the decision this analysis serves — it's what keeps the analysis from becoming an essay.
-
Demand evidence notes
The evaluation matrix marks unverified claims explicitly — those are your follow-up list, not your conclusions.
-
Rerun quarterly
Save the workflow; next quarter, same sequence, fresh evidence. Comparable analyses compound.
Why This Works
- Decision-scoping converts 'know the competitors' into 'answer this question'
- Same-criteria evaluation makes five competitors actually comparable
- Unverified-claim marking keeps confident-sounding gaps out of the conclusions
Best for
- Pricing, positioning, and roadmap decisions that need competitive grounding
- Recurring quarterly competitive reviews
- Teams whose competitor docs go stale because they're painful to produce
Not for
- Comparing two of your own prompts — that's the Prompt Comparator
- A quick one-competitor lookup — one prompt suffices
Use cases
- Analyzing competitors with a specific decision as the anchor
- Replacing feature-table essays with evidence-backed evaluation matrices
- Preparing the competitive input for a pricing or positioning call
FAQ
Why does step 1 make me define the decision and out-of-scope list before looking at any competitor?
Locking the decision first — here the Q3 pricing call — plus a 3-5 criteria list and an explicit out-of-scope list is what stops step 4 from sprawling into a feature-table essay. The Multi-Step Prompt Builder writes that scoping as the opening prompt so every later step judges candidates only against those fixed criteria. You run the chain in ChatGPT, Claude, or Gemini and confirm the criteria fit your call.
How does the evaluation step handle claims I can't back up with evidence?
Step 4's prompt tells the assistant to cite evidence for every claim and write 'unverified' wherever evidence is missing, rather than guessing. Those unverified cells become your follow-up research list, not conclusions you act on. The Builder writes that instruction into the chain, but the assistant marks the cells wherever you run the prompt; NewPrompt never checks whether any citation is actually true.
What is the counter-evidence step in the 7-step sequence for?
The fifth step (question, sources, landscape, evaluation, counter-evidence, synthesis, recommendation) deliberately hunts for evidence against the evaluation matrix before synthesis. It exists so confident-sounding gaps get challenged instead of flowing straight into the recommendation. The Multi-Step Prompt Builder sequences it as its own prompt; you run and read that counter-evidence output before continuing to synthesis.
Can I reuse this workflow for next quarter's competitive review, or do I rebuild it each time?
Build it once — save the generated 7-step chain and paste the same sequence into a fresh conversation each quarter, so the fixed criteria and criteria-by-candidate matrix keep the analyses comparable. The Builder produces that reusable prompt chain; it does not store your competitors or auto-refresh their data, so you supply the current evidence yourself every run.
More resources from Multi-Step Prompt Builder
Resource
Prompt Chaining: Outputs as Inputs
Prompt chaining runs prompts in sequence where each output becomes the next prompt's input — the technique that turns a chat into a pipeline.
Resource
AI Workflow Prompts: From Goal to Sequence
An AI workflow prompt set turns one goal into an executable sequence — objective, prompt, and expected output per step, ready to run top to bottom.
Resources that pair well
Resource
Bug Triage Assistant
Convert scattered bug notes, Slack messages, or user complaints into structured engineering tasks with reproduction steps, severity, and root cause hypothesis.
Resource
Agent Task Template
A reusable AI agent task template with variables for objective, context, available tools, constraints, success criteria, failure handling, and output format.
Resource
Fix a Vague Prompt
'Make it good', 'be detailed', 'keep it interesting' — vague prompts get vague output. The fix is mechanical: replace every fuzzy word with a checkable instruction.
Related tools
Tool
Multi-Step Prompt Builder
Break a big goal into a sequential prompt workflow — each step with an objective, prompt, and expected output.
Guides for this resource
Guide
How to Make AI Compare Options Before Recommending One
Ask AI which option to pick and it names one in the first sentence — no criteria, no options laid side by side, its assumptions hidden. Here's how to make it compare the choices against explicit criteria first, then recommend with caveats you can actually check.