What you can do
Solve works like a research analyst. Provide context, name constraints, and define your output format to get a sharp result. Vague prompts return broad, generic summaries. Before research begins, Rocket asks clarifying questions to resolve ambiguity in your prompt. You can also reference previous work through @-mentions or attach files and URLs for additional context.Weak prompts vs. strong prompts
- Weak prompts
- Strong prompts
| Prompt | Why it fails |
|---|---|
| ”Tell me about the SaaS market” | Too broad. No segment, geography, or specific question. |
| ”Who are our competitors?” | Solve does not know who “we” refers to or what market you operate in. |
| ”What should we build?” | No context about your product, users, or constraints. |
| ”Is this a good business idea?” | No specifics about the idea, market, or success criteria. |
| ”Help with pricing” | No product details, target market, or competitor benchmarks. |
Frame better questions
Include context about your situation
Include context about your situation
Tell Solve who you are and what stage you are at. “We’re a seed-stage startup with 3 engineers targeting SMBs” produces very different recommendations than the same question without context.Include:
- Your company stage (pre-launch, seed, Series A, etc.)
- Your target customer (segment, size, industry)
- Relevant constraints (budget, timeline, team size)
- What you have already tried or decided
Name names
Name names
Instead of “analyze the competition,” name the 3 to 5 competitors you care about. Instead of “research the market,” name the specific category. Specificity turns a survey into a focused analysis.Instead of: “What are the trends in AI?”
Try: “What are the top 3 trends in AI-powered B2B sales tools for 2025? Focus on products like Gong, Outreach, and Salesloft.”
State the purpose of the answer
State the purpose of the answer
A market size estimate for a pitch deck needs different precision than one for internal planning. Tell Solve what the output is for.Instead of: “What’s the market size for project management tools?”
Try: “I need a TAM/SAM/SOM estimate for project management tools targeting remote-first companies, formatted for a Series A pitch deck.”
Request specific formats and frameworks
Request specific formats and frameworks
If you want a SWOT analysis, say “SWOT analysis.” If you want a comparison table, say “create a comparison table.” Explicit format requests prevent Solve from guessing your intent.Useful format requests:
- “Create a feature comparison table”
- “Use a RICE scoring framework”
- “Structure this as a two-page investor memo”
- “Give me a pros/cons list for each option”
- “Present the bull case and bear case separately”
Set boundaries on scope
Set boundaries on scope
Without boundaries, Solve may go too broad or too narrow. State what to include and what to skip.Instead of: “Analyze Stripe”
Try: “Analyze Stripe’s pricing model and payment processing fees specifically. Do not cover their banking or identity products.”
Commands
Use follow-up messages to extract more value from the initial report. Three patterns work well: drill-down, challenge, and pivot.Follow-up patterns
| Pattern | When to use | Example sequence |
|---|---|---|
| Drill-down | You want more detail on one section of the report. | 1. “Map the competitive landscape for no-code database tools.” 2. “Tell me more about Airtable’s enterprise strategy. What features do they gate behind enterprise pricing, and how does that compare to Notion?” 3. “Based on this analysis, if I were building a no-code database for agencies, what 3 features would differentiate me from Airtable?” |
| Challenge | You want to stress-test the conclusions. | 1. “Build an investment thesis for vertical SaaS in healthcare.” 2. “What is the strongest bear case against this thesis? What would make this investment fail?” 3. “Given those risks, how would you modify the thesis to account for regulatory headwinds?” |
| Pivot | An unexpected finding redirects your research. | 1. “What is the market size for AI tutoring tools for K-12 students?” 2. The report reveals the fastest-growing segment is corporate training. 3. “Pivot to the corporate training market. What does the AI-powered training market look like for companies with 500+ employees?” |
Iteration strategies
Start broad, go narrow
Start broad, go narrow
Begin with a landscape question (“What does the market look like?”), then narrow to specifics (“Zoom in on this segment”). This gives you context before you commit to a direction.
Research, then decide
Research, then decide
First ask factual questions (“What are the pricing models competitors use?”). Then ask decision questions (“Which model should I choose given my constraints?”). Separating research from decisions produces better answers for both.
Analyze, then synthesize
Analyze, then synthesize
Run multiple Solve tasks on different aspects of a problem. Use one for market analysis, one for competitive research, and one for pricing. Then ask a final Solve task: “Synthesize these findings into a go-to-market strategy.” Tasks in the same project can reference each other.
Solo first, team second
Solo first, team second
Get the initial analysis yourself and form your own perspective. Then share the report with your team for discussion. This prevents anchoring bias where the team only considers what Solve suggested.
Combine Solve with other capabilities
Solve does not exist in isolation. Connect it with the rest of Rocket for compounding value.| Combination | How it works |
|---|---|
| Solve then Build | Research a market or feature set with Solve, then use those findings to scope a Build task. “Build a pricing page based on the competitive pricing analysis from my Solve task.” |
| Solve then Intelligence | Use Solve to identify key competitors, then set up Track tasks in Intelligence to monitor them continuously. |
| Intelligence then Solve | When Intelligence surfaces a significant change (competitor launches a new feature), create a Solve task to analyze the implications. |
| Solve then Solve | Chain multiple Solve tasks in a project. Market analysis first, then competitive teardown, then pricing strategy. Each task builds on previous findings. |
All Solve, Build, and Track tasks within a project share the same context. You can reference findings from one task in another without re-entering data.
Common mistakes to avoid
| Mistake | What to do instead |
|---|---|
| Asking multiple unrelated questions in one prompt | Split into separate Solve tasks, each focused on one topic. |
| Not providing enough context | Include your stage, audience, constraints, and what you already know. |
| Taking the first result as final | Use follow-ups to challenge, refine, and deepen the analysis. |
| Ignoring the methodology section | Read how Solve arrived at its conclusions so you can evaluate confidence. |
| Using Solve when Intelligence is better | If you need ongoing monitoring, create a Track task instead of re-running Solve. |
What’s next?
Run your first analysis
Put these practices into action with a guided walkthrough.
Market analysis
Apply question-framing techniques to market sizing and trend research.
Competitive teardowns
Frame effective competitive analysis questions using these patterns.