Prompt engineering

YouTube

Prompt engineering best practices are becoming obsolete

Dylan Davis March 20, 2025

---

Prompt engineering 10

AI tools & automation 7

• Reasoning models make chain-of-thought prompting redundant by default.
• Agentic tools generate their own steps, making explicit step prompts useless.
• Describe what you want — AI knows how to get there better than you do.

Read more →

AI tools & automation

YouTube

AI-powered client proposal workflow: from hours to minutes

Dylan Davis March 18, 2025

---

AI tools & automation 9

Closing techniques 7

• A 5-hour manual proposal was rejected; a 22-minute AI one was accepted.
• Three-tier pricing anchors clients and is generated entirely by AI.
• A self-reviewing system prompt catches gaps before you see the draft.

Read more →

AI tools & automation

YouTube

How to prevent context drift when AI coding with Cursor

Dylan Davis March 13, 2025

---

AI tools & automation 9

Processes & SOPs 6

• Long Cursor sessions cause models to drift from your codebase reality.
• Summarise stuck bugs into a fresh composer session to reset context.
• Three layered documents — spec, blueprint, to-do — keep AI on track.

Read more →

AI tools & automation

YouTube

Using AI to turn meeting notes into follow-up emails in minutes

Dylan Davis March 6, 2025

---

AI tools & automation 9

Automation & tools 6

• A transcript or photo of notes is all the AI needs.
• Poor handwriting still yields 60–70% accurate extraction.
• A custom system prompt locks in your voice and email structure.

Read more →

AI tools & automation

YouTube

Model Context Protocol: the open standard connecting AI to the world

Dylan Davis March 4, 2025

---

AI tools & automation 9

AI strategy & adoption 7

Tech stack & software 6

• AI models are caged — MCP is the USB-C that frees them
• Anthropic open-sourced MCP to close the gap with OpenAI
• Auto-discovery and cloud servers will replace today's manual setup

Read more →

AI tools & automation

YouTube

Automating expense tracking with AI, Google Drive, and Google Sheets

Dylan Davis February 27, 2025

---

AI tools & automation 9

Automation & tools 7

• Drop a receipt anywhere in a folder — AI logs it automatically
• Vision model infers purchase rationale even when receipts don't say why
• PRD-first prompting keeps AI from losing track across build phases

Read more →

AI tools & automation

YouTube

How top AI teams build LLM judges for reliable products

Dylan Davis February 25, 2025

---

AI tools & automation 10

Iteration & feedback loops 7

Automation & tools 6

• Binary pass/fail evals beat gradient scales every time
• Expert reasoning, not just verdicts, is what trains good judges
• Human judges the judge to close the quality loop over time

Read more →

AI strategy & adoption

YouTube

Why successful AI companies obsess over evaluations

Dylan Davis February 20, 2025

---

AI strategy & adoption 9

Iteration & feedback loops 7

• You can't improve a multi-step agent without knowing which step fails.
• Binary yes/no criteria beat subjective rating scales every time.
• Start with AI-written unit tests before touching eval infrastructure.

Read more →

Closing techniques

YouTube

Using ChatGPT voice mode to rehearse high-stakes conversations

Dylan Davis February 18, 2025

---

Closing techniques 8

AI tools & automation 7

Resilience & grit 6

• Assign AI a buyer persona to rehearse sales pitches safely.
• A trigger phrase pauses roleplay for instant mid-session coaching.
• Iterative Socratic questions beat one-shot AI advice for self-reflection.

Read more →

AI tools & automation

YouTube

Practical techniques to improve RAG retrieval without complexity

Dylan Davis February 13, 2025

---

AI tools & automation 9

Iteration & feedback loops 6

• Beginner-mode fundamentals beat most advanced RAG techniques.
• Chunking at meaning boundaries, not arbitrary character counts, transforms retrieval.
• Metadata filters combined with re-ranking cut noise from retrieved results.

Read more →

AI tools & automation

YouTube

A five-step process for building production-ready AI apps

Dylan Davis February 11, 2025

---

AI tools & automation 10

MVP & prototyping 7

• A living markdown checklist keeps AI on track across the entire build
• Test-driven development creates a self-correcting micro reinforcement loop
• Dictating ideas beats typed prompts — typos never matter to the model

Read more →

AI tools & automation

YouTube

A structured three-step process for building apps with AI

Dylan Davis February 6, 2025

---

AI tools & automation 10

Processes & SOPs 7

MVP & prototyping 5

• Why letting AI take control makes you lose hours to circular errors
• Tests written before each feature create a self-correcting AI feedback loop
• Handoff prompts between sessions prevent context drift from derailing builds

Read more →

Automation & tools

YouTube

Automating meeting notes with AI transcription and CRM logging

Dylan Davis February 4, 2025

---

Automation & tools 9

AI tools & automation 8

• Voice memos and Zoom calls auto-transcribed, summarised, and filed instantly
• Claude Haiku extracts names and action items — no manual parsing needed
• A markdown checklist keeps AI-assisted Cursor builds on track phase by phase

Read more →

AI tools & automation

YouTube

Let AI write your prompts: the 80/20 approach to prompt engineering

Dylan Davis January 30, 2025

---

AI tools & automation 9

• AI writes better system prompts than most humans can
• Anthropic and OpenAI both offer free built-in prompt generators
• No API credits? Any free chat model can do the same job

Read more →

AI tools & automation

YouTube

How to prompt reasoning models for better outputs

Dylan Davis January 28, 2025

---

AI tools & automation 10

Prompt engineering 9

• Your ChatGPT habits actively hurt performance in reasoning models.
• A six-section prompt structure unlocks far higher output quality.
• Embed a writing diff in the system prompt to clone your style.

Read more →