How hyper-specific prompts improve image and model edits

What do JSON and conversational AI have in common? They are the glue behind ordering coffee, booking flights, and talking to support. In our tests, about 1 out of 3 replies missed the intent until we enforced structured JSON outputs. In this episode, Danny Thompson and Leon Noel break down how to move from “cool demo” to production systems that route, escalate, and self-audit reliably.

SITE https://www.programmingpodcast.com/

💡 Sponsor: Level Up Financial Planning

Changing careers or increasing your income? Get financial clarity with Level Up Financial Planning—helping early and mid-career tech professionals secure their financial future. Visit LevelUpFinancialPlanning.com for a free consultation!

https://www.levelupfinancialplanning.com/

Stay in Touch:

📧 Have ideas or questions for the show? Or are you a business that wants to talk business?

Email us at dannyandleonspodcast@gmail.com!

Danny Thompson

https://x.com/DThompsonDev

https://www.linkedin.com/in/DThompsonDev

www.DThompsonDev.com

Leon Noel

https://x.com/leonnoel

https://www.linkedin.com/in/leonnoel/

https://100devs.org/

📧 Have ideas or questions for the show? Or are you a business that wants to talk business?

Email us at dannyandleonspodcast@gmail.com!

What you’ll learn

- Why freeform paragraphs fail backends and how JSON fields fix routing

- A simple schema pattern: department, sentiment, confidence, reply

- Confidence floors that trigger automatic retries before users ever see a response

- Context windows: why rules are read every call while context gets dropped

- MCP basics and how domain context avoids bad translations and metaphors

- Where voice agents work today (predictable conversations) and where they do not

- Practical tool choices for text, code, and voice workflows

- Real labor impacts, retention insights, and reskill advice

- Salary negotiation quick hits: the two lines that matter

Chapters

0:00 JSON as the glue + the 1-in-3 miss

0:30 Intro & episode promise

1:10 Quick defs — JSON / NLG / NLU / MCP

3:00 Why structured JSON beats paragraphs

7:36 Confidence scores & auto-retries

9:02 Sponsor

11:34 Prompts for image/video models that actually work

15:01 Context windows & durable rules

16:32 Repo trees, PRDs & dev logs to reduce spin

20:02 MCP in practice, local dialects & domain knowledge

26:03 Voice agents, predictable vs unpredictable conversations

32:43 Voice mode as a research partner & model picks

33:01 Jobs impact, retention stories & reskilling

37:10 Conversational AI 101, coffee shop flow to backend

40:05 Connectors & phone/drive-thru stacks (Agora, 11 Labs)

46:04 Real-world rollouts, employee retention boost

48:13 Call centers & debt collection case study

51:27 Predictable vs messy conversations — where AI fails

53:24 Career CTA, learn JSON, MCP, voice stacks

57:01 Ask Danny And Leon A Question

1:07:10 The Developer's Guide To AI