True Path Analytics

A PM’s Guide to Using AI

David — Fri, 26 Dec 2025 19:29:35 +0000

… just a quick hit to provide working links over the holidays. Please excuse the roughness of the design.

1. Getting Started

The first thing is to understand AI PM is just a subset of PM. Many of the tasks are the same, but you’re building AI features or products, and using AI tools even more.

AI Product Management Basics:

Prompt Engineering
Context Engineering (RAG)
AI Evals & Testing
AI Prototyping/Vibe Coding
Agent Workflows

Key Differences from Traditional PM:

Technical depth required
Building AI features + products
Higher expectation of AI tool use

Deep Resources:

2. Prompt Engineering

It’s the #1 skill for great agents + productivity.

Free Guides:

Techniques Grid:

COT	ROLES	EXAMPLES
Few-Shot	Constraints	XML Tags
Chain Prompts	Autonomy	Artifacts
Step-by-Step	Persist	Self-Consistency

Tools:

Anthropic Claude
ChatGPT
ChatPRD

3. Context Engineering & RAG

Vector Databases:

Pinecone
Chromatic
Qdrant

Knowledge Graphs:

Neo4j
GraphRAG

Frameworks:

LlamaIndex
LangChain

RAG vs Fine-Tuning vs Prompting:

Use prompting for simple instructions and general tasks
Use RAG when you need to retrieve specific knowledge or documents
Use fine-tuning for specialized domains with consistent style/format needs

Context Engineering Guide: Step-by-Step

4. AI Prototyping & Vibe Coding

No-code first:

Lovable
Bolt
v0
Replit Agent
Devin

IDE first:

Cursor
Windsurf
GitHub Copilot
Codeium

Others:

Jules
Codex

Infrastructure Tools:

Supabase
Firebase
Clerk
Netlify
Vercel
Railway
DigitalOcean
GitHub

Guides:

5. AI Agents & Agentic Workflows

Agent Platforms:

n8n
Crew AI
Zapier
AutogenAI
Make
LlamaIndex
LangGraph
LangChain
Lindy
Lamini
Haystack
Cassidy
FlowWise

Techniques:

Tool use
MCP
Agent Architectures
ReAct
A2A RAG

Guides:

6. AI Evals, Testing & Observability

Evaluation Platforms:

X (Twitter)
Arize
Braintrust
Weights & Biases

Testing Approaches:

Unit Tests → LLM Judge/Error Analysis → TNF/TPR
Human Eval → Model Eval Train/Test/Dev → A/B Tests

Key Metrics:

Accuracy / Precision / Recall
Latency (P50, P95, P99)
Cost per request
User satisfaction

Virtuous Cycle Diagram: Build → Evaluate → Iterate → Observe → (repeat)

Resources:

7. Foundation Models

Leading Models:

Best reasoning & coding: Claude (Anthropic)
Most versatile: GPT-4
Multimodal leader: Gemini
Real-time data: Perplexity
Long context: Claude
Efficient: Gemini Flash
Open source: Llama
Multilingual: Command R+

Model Types:

LLM (Large Language Models)
LCM (Large Code Models)
LAM (Large Action Models)
MoE VLM (Mixture of Experts Vision-Language Models)
SLM (Small Language Models)
MLM (Multimodal Language Models)
SAM (Segment Anything Models)

8. AI PRDs & Building

Essential Frameworks:

AI Product Strategy Template
AI PRD Structure
Evaluation Framework
Risk Assessment Matrix

Free Templates:

Common Mistakes:

No fallback strategy
Ignoring latency/cost
Building without evals
Overfitting to demos

Key Resource:

Most People Build AI Products Wrong – How to Do It Right

9. Career Resources

Breaking Into AI PM:

Build your AI PM background
Create an AI PM Portfolio
Update your Resume + LinkedIn
Get Referrals to AI PM Jobs
Be Over-Prepared for Unique Interviews:
- a. Vibe Coding
- b. AI ethics + guardrails

Key Guides:

Tools & Communities:

Boost Your CPMs With Our True Path Ad Pilot Project

Jacob Fogg — Wed, 03 Sep 2025 12:54:43 +0000

Our data-driven ad solution can help you boost your CPMs – a problem that many publishers have been struggling with for the past two years.

By better identifying your readers/viewers/listeners, you are better able to compete with the Google/Facebook ad duopoly.

The CPMs listed here – $80 for a common display ad, and $125 for video – are on the high end, yes. But not unattainable.

Fill out the form and schedule a meeting to learn more.

How To Secure Your News Content from AI Scrapers

David — Fri, 07 Feb 2025 21:11:55 +0000

tl;dr version: it’s tricky to protect your work from AI bots, because there are now SO MANY snarfing your creativity to add to their mind-Borg. The standard practice has been to use a robots.txt file to tell them not to scrape your content. Many AI bots do it anyway. So now, there’s a crafty little program that traps the bots into an endless loop and feeds them garbage.

Trends in Publishing 2025

David — Thu, 06 Feb 2025 18:11:18 +0000

It’s always dangerous to make predictions, not least because “the internet is forever,” and we are daily finding out that we are in an unprecedented epoch of daily tumult & change.

Influencers Are Now Legitimate Rivals to News Orgs

In 2024, it became abundantly clear that differences in news consumption had absolutely fractured along generational faultlines. A general, non-exact rule:

The older you are, the more likely you are to consume what we once used to call “Mainstream Media.” That is, newspapers, magazines, cable-TV news.
In the middle lies the generation that grew up on the “blogosphere,” and that still relies on fairly professional news outlets like Politico, the Daily Beast, Huffington Post, Breitbart, etc.
The young, future audiences are into podcasts, TikTok videos, and cross-platform influencers like Mr. Beast, Joe Rogan, Ben Shapiro, etc.

It is imperative that professional news publishers start to try to bridge this gap.

– that ‘young’, future audiences of news media display fundamentally different behaviors and needs to prior generations – 2025 will be the year when publishers attempt to bridge the gap. Perceptions of news journalism are evolving and the competitive field has inexorably changed. We expect publishers to try to evolve their offering set, build awareness with underserved audiences and meet them where they are – collectively placing bets for future monetization opportunities. It will be years before they see returns on their investment.