Opportunity Scanner

AI Opportunity Scanner

Generates 3-5 testable AI opportunity hypotheses for your organization based on industry patterns, company size, and known challenges. This is Step 1 of the Discovery Sprint methodology — giving you a structured starting point instead of "where do we even begin?"

How It Works

When you run this skill, I'll ask you a few questions about your company, then generate a structured hypothesis document you can use to guide interviews, audits, and deeper investigation.

What I Need From You

Provide the following (I'll ask for anything missing):

1. Company name
2. Industry (e.g., Healthcare, Manufacturing, Professional Services, Retail, Finance, Technology, etc.)
3. Company size (approximate employee count)
4. 2-5 known challenges or pain points (what keeps leadership up at night?)
5. Key departments to focus on (optional — if you already know where the biggest problems are)

What You'll Get

A Hypothesis Document containing:

For Each Hypothesis (3-5 total):

HYPOTHESIS: We believe that [DEPARTMENT/FUNCTION] spends significant time on
[ACTIVITY] which could be [AUTOMATED/AUGMENTED] using [AI APPROACH],
resulting in [ESTIMATED IMPACT].

VALIDATION METHOD:
- Who to interview: [Roles/people]
- Questions to ask: [Specific questions]
- Data to collect: [Metrics to validate]

CONFIDENCE: [High/Medium/Low] based on industry pattern strength
POTENTIAL IMPACT: [Hours/year saved or $ value range]

Plus:

• Interview Priority List — Who to talk to first, organized by the U-shaped method (executives first, then frontline, then back to executives)
• Pattern Alerts — Common patterns your industry typically exhibits (so you know what to watch for)
• Quick Win Candidates — 1-2 hypotheses most likely to yield fast, visible results

Industry Pattern Library

I draw on validated patterns seen across multiple organizations:

| Pattern | Description | Industries Where Common | |---------|-------------|------------------------| | Data Without Insights | Lots of data in tables/systems but no synthesis into actionable intelligence | All industries with data teams | | Manual Scheduling Cascade | Schedule changes require manual updates across multiple people/systems | Operations-heavy, multi-department | | Report Assembly Line | Same information reformatted for different audiences manually | Any org with reporting requirements | | Institutional Knowledge in Heads | Critical processes depend on specific people's memory | Mature orgs, specialized domains | | Communication Silos | Information flows through personal relationships, not systems | Multi-department, 50+ employees | | Analytics Capacity Crunch | Analytics team is bottleneck; can't serve all departments | Any org with central analytics | | Text/Email as System of Record | Critical info lives in messages, not structured systems | Orgs that outgrew their tools |

How I Generate Hypotheses

1. Match your industry to known automation patterns
2. Adjust for company size (smaller = more quick wins; larger = more strategic initiatives)
3. Cross-reference your stated challenges with pattern library
4. Estimate impact ranges using industry benchmarks
5. Prioritize by likelihood — hypotheses backed by strong patterns rank higher

Output Format

I'll create a markdown file you can save and reference throughout your discovery process:

# AI Opportunity Hypotheses: [Company Name]
Generated: [Date]
Industry: [Industry] | Size: [Employees] | Focus: [Departments]

## Executive Summary
[2-3 sentences on the most promising opportunity areas]

---

## Hypothesis 1: [Title]
**Department:** [Department]
**Pattern Match:** [Which known pattern this maps to]

**We believe that** [department/function] spends [estimated time] on [activity]
**which could be** [automated/augmented] using [AI approach],
**resulting in** [estimated impact: hours saved, cost reduction, quality improvement].

**Why we think this:**
- [Industry benchmark or pattern evidence]
- [Connection to stated challenge]

**To validate, interview:**
- [Role 1] — Ask: "[Specific question]"
- [Role 2] — Ask: "[Specific question]"

**Confidence:** [High/Medium/Low]
**Potential Impact:** [Range]
**Quick Win Potential:** [Yes/No — and why]

---

[Repeat for each hypothesis]

---

## Recommended Interview Order

### Phase 1: Executives (Days 1-2)
| Person/Role | Why Interview Them | Key Questions |
|-------------|-------------------|---------------|

### Phase 2: Frontline Workers (Days 3-7)
| Person/Role | Why Interview Them | Key Questions |
|-------------|-------------------|---------------|

### Phase 3: Back to Executives (Days 8-10)
| Purpose | What to Validate |
|---------|-----------------|

---

## Patterns to Watch For
Based on your industry and size, keep an eye out for:
- [Pattern 1 with description]
- [Pattern 2 with description]
- [Pattern 3 with description]

---

## Next Steps
1. Run `/interview-builder` to create tailored interview guides for each target
2. Run `/workflow-audit` to deep-dive into the highest-confidence hypothesis
3. After interviews, run `/insight-analyzer` to process findings

---
Built with the AI Opportunity Finder by Morningside AI
Want expert help? → https://morningside.ai

Tips for Best Results

• Be specific about challenges. "Sales is slow" is less useful than "Reps spend 3+ hours/day on CRM data entry and prospecting research."
• Name departments if you can. The more specific you are, the more targeted the hypotheses.
• It's OK to be wrong. These are hypotheses, not conclusions. The point is to have a starting direction. You'll validate (or invalidate) through interviews.

What Comes Next

After generating hypotheses:

1. /workflow-audit — Deep-dive into a specific process you suspect is wasteful
2. /interview-builder — Create interview guides for the people identified in your hypothesis document
3. /insight-analyzer — Process interview transcripts into structured findings

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: nickstellarstreamai
• Source: nickstellarstreamai/ai-opportunity-finder
• License: MIT

Install and usage instructions live in the source repository linked above.