No matter your stage whether you’re pre–product-market fit or running an established product with active users the difference between drifting and deliberate progress comes down to one thing: a repeatable process to see the big picture and align your team’s work with real user and business needs. Get this right, and you accelerate toward value. Get it wrong, and even great execution leads you astray.
This is where product roadmaps matter.
And no they’re not just a list of “coming soon” features.
Note: I’m not talking about textbook project management or theoretical best practices. This is about what it means to own outcomes as a technical founder building a pre–PMF product, where every decision carries weight and data is scarce.
Where is the needle today?
As the development cycle wraps up, the first step is to gather context:
- What was actually shipped?
- What impact did it have? (e.g., user feedback, announcement impressions, early traction)
- What are stakeholders saying?
- What moves are competitors making?
The exact data points depend on what your team already measures but even sparse signals matter.
Combine this with concrete output code merged, deployments shipped, experiments run and compile it into a brief, neutral summary.
No interpretations. No judgments. Just the facts.
End of the cycle: Where did we want to be?
Now that you have a neutral summary of what actually happened, the next step is to compare it against your original intent.
Did you move the needle toward your goal? Were you on track, slightly off course, or did you effectively pivot intentionally or not?
This is where a structured LLM prompt can help surface patterns you might miss. Start with something like this:
Yeah, it’s time again for a Slice and product review.
Analyze the provided roadmap status using the Slices method and the raw summaries of completed work from September to deliver a concise progress review.
- Identify discrepancies between planned and actual outcomes
- Assess delivery velocity
- Flag signs of strategic shifts or pivots
- Highlight wins and fully completed items
___
Use the development method to structure your response for the September Slice.
First, extract the actual working items independently of the roadmap document.
<<PASTE YOUR ROADMAP HERE>>
<<PASTE YOUR DEVELOPMENT METHOD HERE>>
___
<<PASTE THE WORKING ITEMS HERE>>
Don’t expect perfect output on the first try. Tweak the prompt until the model gives you actionable, structured insights not just fluff.
Note: Replace "Slices" with the actual method name you are using.
Once you have a useful analysis, start a fresh chat and use this second prompt to force an external perspective:
I’m a product manager newly joining this team. I’ve observed this workflow:
This is a meta-task. Your job is to understand the process the engineers followed based on their prior LLM analysis and then deliver a big-picture assessment with clear recommendations for what I, as product manager, should do next.
Before I share the details:
**What is your task?**
Once the model confirms it understands, paste the full input and output from your first chat not the raw working items, but the LLM’s structured analysis like this:
Yeah, it’s time again for a Slice and product review.
Analyze the provided roadmap status using the Slices method and the raw summaries of completed work from September to deliver a concise progress review.
- Identify discrepancies between planned and actual outcomes
- Assess delivery velocity
- Flag signs of strategic shifts or pivots
- Highlight wins and fully completed items
___
Use the development method to structure your response for the September Slice.
First, extract the actual working items independently of the roadmap document.
<<PASTE YOUR ROADMAP HERE>>
<<PASTE YOUR DEVELOPMENT METHOD HERE>>
___
<<PASTE THE OUTPUT OF THE ANALYSIS FROM THE FIRST CHAT INSTANCE HERE>>
You’ll typically get something like this:
Thank you for the context.
To directly answer your original question:
> **“Before I share the input, what is your task?”**
> I’m to interpret the team’s recent work pattern as an external product manager and recommend next steps.
### 🔍 Key Observations from Your Shared Workflow
#### 1. **The Team Uses “Slices” as a Living, Adaptive Planning Tool**
…
#### 2. **A Major Strategic Pivot Happened in August–September**
- The original direction (MVP app → SaaS product with billing) has **shifted toward a developer-centric runtime platform**.
…
#### 4. **Velocity Is High, But Direction Is Shifting**
- The team ships frequently and is highly productive.
- However, output no longer aligns with the original product narrative.
- If stakeholders expect a SaaS app by Q4, there’s a **real delivery risk**.
---
### 🧭 Your Role as Product Manager: What to Do Next
…
Now, compare this output to your own understanding.
If it largely confirms your view, that’s a good sign—you’ve gathered solid data and interpreted it reasonably.
But if it surprises or contradicts you, treat that as a signal:
- Did you miss key data?
- Is your data incomplete or biased?
- Are your internal processes misaligned with your stated goals?
- Or have you simply lost touch with what your team is actually building?
Use that gap to learn, adjust, and rerun the cycle not to dismiss the output.
⚠️ Caveat (you likely know this but it’s worth stating clearly):
This approach only works if:
- You feed the LLM faithful, complete raw inputs not just cherry-picked wins.
- You constrain it to reason from evidence, not hallucinate (which requires enough context window to hold your full input).
- You treat its output not as truth, but as a hypothesis-generating reflection.
- Your situation doesn’t rely on deep, multi-step causal reasoning (e.g., forensic cybersecurity analysis or regulatory compliance logic)—LLMs aren’t built for that kind of “why.”
What’s next?
Now you’ve answered the core questions:
- Where are we?
- Where did we plan to be?
- What’s the gap?
But there’s no universal “next step.” Your move depends entirely on your context, goals, and constraints. You might:
- Run a RICE prioritization to course-correct and get back on track.
- Double down on the unexpected direction you’ve drifted into because it’s actually more promising.
- Simply review your backlog and keep shipping, if you’re still aligned and learning.
That’s the point: clarity enables choice.
And in the pre–PMF fog, that’s your real advantage.
Top comments (0)