Ep 0521 min
Context Engineering
Most agent failures aren't model failures — they're context failures. A coding agent spends a weekend modernizing dead code, and we unpack the skill that decides whether an agent ships: context engineering.
The podcast
The PromptsBuddy Podcast
Each episode, we sit with someone who uses AI in their real job: designers, founders, teachers, support leads, engineers. We take apart the prompts and workflows they actually rely on. No hype. No stage demos.
Ep 0448 min
The support team that writes its own AI policy
Why support prompts are policy documents, how they get reviewed, and the one rule that stops agents from promising ship dates.
Ep 0352 min
What analysts actually do with models all day
The unglamorous truth of AI in analytics: the SQL is the easy part. The hard part is getting three executives to agree on what “active” means.
Ep 0245 min
Designing with a critic that argues back
Using models as critique partners rather than generators — and why the work gets better the moment you stop asking for designs and start asking for arguments.
Ep 0134 min
Losing prompts in a Notes app
Why PromptsBuddy exists, what a community-run prompt library should and shouldn't be, and the three rules we start with: tested, attributed, versioned.