~/talk

Prompting Is Not the System: Context, Contracts, Reliable Agent

links:none on file
slides:none on file

A content pipeline is built to auto-create posts but an empty draft slips into production because the prompt alone is insufficient; the concrete fix splits the agent into six layers: versioned context (v3 vs v4 mismatch, content hashed and timestamped), a code-enforced contract with human in the loop for high‑risk actions, output validation against that contract, retries limited to two with an idempotency key and state machine, a minimal core prompt, and purpose‑based eval. The new pipeline publishes thread, blog and newsletter and rejects wrong‑brand posts.

AI-written summary · about

  1. 0:00Intro and the content pipeline scenario
  2. 1:00Why fixing the prompt isn't enough
  3. 1:40Splitting the agent into layers
  4. 3:25Context: versioned, current information
  5. 4:43Contract: permissions and human in the loop
  6. 7:18Output: validating against the contract
  7. 9:01Retries, idempotency keys and recovery
  8. 12:05The prompt itself: keeping only the core
  9. 14:39Eval: measuring purpose, not format
  10. 16:14Six questions and final takeaways
~/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.