~/talk

Beyond Better Prompts: Prompt Engineering for Production AI

links:none on file
slides:none on file

Argues that every AI output requires evaluation against concrete project standards, shows using Claude, Codex with project rule files (.md) and saved prompt templates, demonstrates testing for missing fields, edge cases and conflicting instructions, and quantifies fix strategy as fix one prompt line at a time then retest until the footer or feature appears. Covers reusable templates that save time but still need validation and enforces security practices like using GitHub secrets instead of pasting API keys.

AI-written summary · about

  1. 0:00Introduction to Beyond Better Prompting
  2. 1:43Prompting vs Prompt Engineering
  3. 3:51Why Every AI Response Needs Evaluation
  4. 5:54Evaluating Results Against Project Standards
  5. 8:01Building Reusable Prompt Templates
  6. 12:49Using .md Files for Project Rules
  7. 14:37Giving the AI Context and Examples
  8. 19:20Testing and Evaluating What Matters
  9. 23:57Fixing Prompt Drift One Change at a Time
  10. 27:04Prompt Security and API Keys
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.