For product managers

Match AI to the right problem and the right user.

Start by figuring out whether AI is even a fit. Describe a user pain point below and get an honest verdict, mapped to the problem categories LLMs are actually good at — then jump into the Recommender, Dashboard, or Compare.

16 categories
9 core · 6 strong · 1 emerging
Cross-linked to 19 models

A simple test before you build

  • Fuzzy input or fuzzy output? If yes, AI is probably a fit.
  • Would a smart intern help here? If yes, an LLM probably can too.
  • Is being approximately right valuable? If only exact answers count and there's no review step, prefer rules/solvers.
  • Is the cost of being wrong recoverable? If not, design human-in-the-loop or skip AI.

Got a problem in mind? Find the AI opportunity.

Describe a user pain point or workflow. You'll get an honest take on whether AI fits, mapped to the categories below — plus cautions and next steps.

Powered by AI. Treat results as a starting point, not a verdict.

Summarization & Compression

Core strength

Turn long, messy content into the gist a human actually needs.

Condense documents, meetings, threads, or research into shorter, structured outputs at a chosen level of detail.

User pain points

  • Users drowning in long PDFs, emails, transcripts, or chat threads
  • Knowledge workers re-reading the same docs to brief others
  • Customer-support agents needing a 10-second case summary

Examples

Meeting recap with action items
TL;DRs on long articles
Daily digest of Slack/email
Earnings call summary

When not to use AI

When users need exact source text, citations, or legal-grade fidelity without review.

Catalog use-cases

Extraction & Structuring

Core strength

Pull structured data out of unstructured text, images, or audio.

Convert free-form input (forms, receipts, contracts, support tickets) into typed JSON your product can act on.

User pain points

  • Manual data entry from documents/screenshots
  • Unstructured customer feedback that never reaches analytics
  • Onboarding flows that ask users to retype info from a doc they already uploaded

Examples

Receipt → line items + totals
Resume → skills + roles
Doctor's notes → ICD codes (with human review)
Email → CRM fields

When not to use AI

When the source format is fully predictable — a regex, parser, or OCR with rules will be cheaper and more reliable.

Catalog use-cases

Classification & Routing

Core strength

Sort, label, prioritize, or route inputs without writing brittle rules.

Assign categories, tags, sentiment, intent, or priority to text, images, or events.

User pain points

  • Support inboxes that need a human to triage every ticket
  • Content moderation backlog
  • Sales lead scoring stuck on rigid heuristics

Examples

Ticket → team + urgency
Review → sentiment + topic
Lead → ICP fit
Image → safe/unsafe

When not to use AI

Very high volume + tight latency: a small fine-tuned classifier or simple ML may be 100× cheaper.

Catalog use-cases

Semantic Search & Q&A over your data

Core strength

Let users ask questions in natural language and get answers grounded in your content.

Retrieval-Augmented Generation (RAG): the model retrieves relevant chunks from your knowledge base and answers using them, with citations.

User pain points

  • Help docs nobody can find the right page in
  • Internal wikis that grow faster than anyone reads them
  • Long product catalogs with poor keyword search

Examples

Ask-your-docs chatbot
Policy lookup for support agents
Code search across a monorepo
Legal/clinical reference Q&A

When not to use AI

When the corpus changes by the second, or when answers must be 100% verbatim from a source — pair with strict citation UX.

Catalog use-cases

Drafting & Content Generation

Core strength

Get from blank page to first draft in seconds.

Generate emails, posts, descriptions, replies, outlines, or code starters in a chosen voice and format.

User pain points

  • Blank-page paralysis on writing tasks
  • Repetitive replies (returns, FAQs, intros)
  • Personalization at scale (1:1 messages for thousands of users)

Examples

Cold email variants
Product descriptions from spec sheets
Auto-reply drafts
Code scaffolding

When not to use AI

When the output is published unedited under a brand or legal name without review.

Catalog use-cases

Transformation & Translation

Core strength

Convert content from one format, language, or style to another.

Language translation, tone rewriting, format conversion (markdown ↔ HTML, SQL ↔ natural language), code migration.

User pain points

  • Localizing content into 20 languages
  • Making technical writing readable for non-experts (or vice versa)
  • Migrating code between frameworks/languages

Examples

EN → ES product copy
Formal ↔ casual tone
Python → TypeScript
Natural language → SQL

When not to use AI

Legally binding translations, or anywhere a small human error could cause material harm.

Catalog use-cases

Reasoning & Decision Support

Core strength

Walk through a multi-step problem and explain the answer.

Math, logic, planning, comparison, and trade-off analysis — including showing the work.

User pain points

  • Users forced to do calculations or comparisons across many docs
  • Analysts needing an explained recommendation, not just a number
  • Complex eligibility / pricing / config decisions

Examples

'Which plan fits my usage?'
Travel itinerary optimizer
Diagnostic decision support (with human-in-the-loop)
Game/strategy assistants

When not to use AI

When the domain has a deterministic solver (taxes, accounting, physics sim) — call the solver and let the LLM explain it.

Catalog use-cases

Agents & Tool Use

Strong fit

Let the model take actions across tools and APIs to complete a goal.

The LLM calls functions, browses, queries databases, sends emails, and chains steps to accomplish a task.

User pain points

  • Multi-system workflows (search → schedule → notify → log)
  • Power-user tasks that today require switching between 5 tools
  • Internal ops scripts no one wants to maintain

Examples

'Book a meeting with Anna next week'
'Reconcile last month's invoices'
Coding agents that open PRs
Browser automation

When not to use AI

Irreversible high-stakes actions (large payments, prod deletions) without human approval gates.

Catalog use-cases

Vision Understanding

Strong fit

Reason about images and screenshots in natural language.

Describe, classify, extract, or answer questions about photos, charts, diagrams, UI screenshots, and documents.

User pain points

  • Users needing to describe an issue but only able to share a screenshot
  • Visual product search ('find me ones like this')
  • Form/document understanding without templates

Examples

Insurance claim photos
'What's wrong with my plant?'
Screenshot → bug report
Whiteboard → digital notes

When not to use AI

Safety-critical perception (autonomous driving, medical imaging diagnosis) — use specialized models.

Catalog use-cases

Voice & Conversational Interfaces

Strong fit

Natural conversation as a primary interface.

Speech-to-text + LLM + text-to-speech, or native audio models, for hands-free or accessibility-first UX.

User pain points

  • Drivers, clinicians, field workers who can't use a keyboard
  • Phone-based customer support
  • Accessibility for low-vision or low-literacy users

Examples

Voice ordering / dictation
AI phone receptionist
Language tutoring
In-car assistants

When not to use AI

Noisy environments without good ASR, or when transcripts must be legally verbatim.

Catalog use-cases

Personalization & Recommendation Explanations

Strong fit

Tailor content per user — and explain why.

Generate or rerank content based on user context, and produce human-readable rationales for recommendations.

User pain points

  • Generic onboarding that ignores user role/goals
  • Recommendation engines users don't trust because they're a black box
  • Email campaigns that feel like spam

Examples

Personalized learning paths
'Why this match?' on dating/jobs/products
Adaptive tutoring
Tailored onboarding checklists

When not to use AI

When personalization could leak sensitive inferences (health, religion, sexuality) the user didn't consent to share.

Catalog use-cases

Pattern Recognition & Anomaly Spotting

Strong fit

Notice the weird thing in a pile of data.

Surface trends, outliers, themes, or recurring issues across logs, reviews, transactions, or qualitative data.

User pain points

  • Teams reading 1,000 reviews to find recurring complaints
  • Ops staring at logs trying to spot drift
  • PMs synthesizing user interviews

Examples

Theme clustering on user feedback
Log triage assistant
Fraud-flag explanations
Research interview synthesis

When not to use AI

Numerical anomaly detection at scale — pure ML/statistics is more accurate; use the LLM to explain findings to humans.

Catalog use-cases

Tutoring, Coaching & Explanation

Strong fit

Meet the user at their level and explain things until they get it.

Adaptive explanations, Socratic questioning, practice generation, and personalized feedback.

User pain points

  • One-size-fits-all training content
  • Users abandoning products because they don't understand a concept
  • Lack of patient, on-demand expertise

Examples

Code review explanations
Language practice partner
Financial literacy coach
Onboarding tutor inside SaaS

When not to use AI

Regulated advice (medical/legal/financial) without clear disclaimers and licensed-human escalation.

Catalog use-cases

Creative Ideation & Variation

Core strength

Generate options when the answer is 'show me 20'.

Brainstorm names, taglines, visual concepts, plotlines, ad variants, hypotheses.

User pain points

  • Creative blocks
  • A/B testing that needs more variants than humans can write
  • Solo founders without a creative team

Examples

Ad copy variants
Naming brainstorms
Storyboard ideation
Hypothesis generation for research

When not to use AI

When originality and authorship matter for trademark or art purposes — outputs are statistical remixes.

Catalog use-cases

Code Understanding & Generation

Core strength

From boilerplate to whole features, with the human in the loop.

Code completion, refactor, test generation, code review, debugging help, and full agentic implementation.

User pain points

  • Boilerplate fatigue
  • Onboarding to unfamiliar codebases
  • Maintenance work nobody wants to do

Examples

IDE autocomplete
PR review bots
Migration scripts
Bug fixer agents

When not to use AI

Critical infrastructure or security-sensitive code without rigorous human review and tests.

Catalog use-cases

Simulation & Role-play

Emerging

Play a persona to help humans practice or explore.

Simulate customers, interviewers, opponents, or experts so users can rehearse, test ideas, or get adversarial feedback.

User pain points

  • Sales/support reps with no realistic practice environment
  • Job seekers without mock interviewers
  • Therapists/coaches needing role-play scenarios

Examples

Mock interviews
Sales objection-handling drills
Negotiation practice
Red-team / pen-test simulations

When not to use AI

Therapy or crisis support replacement — always route to qualified humans for real distress.

Catalog use-cases

Got a problem in mind? Describe it to the recommender and get model picks, or browse the full catalog.