~/talk

From Scripts to Solvers: Building Agentic AI Systems in Python That Think and Do

slides:none on file

Argues that replacing brittle scripts with model-driven agents yields faster prototyping and fewer bugs, citing a measured 10x faster feature cycle at AWS; demonstrates Python-first stacks including Strands, Bedrock/AgentCore and a Python SDK plus CLI for deployment, observability and IAM isolation; shows patterns — agents-as-tools, swarms, graphs, meta‑agents — and gives templates that claim 60–70% of production glue is ready to reuse while warning 40% of GenAI projects fail without these engineering guardrails.

AI-written summary · about

  1. 0:00Introduction and speaker intro
  2. 2:10Agentic AI vs traditional scripts
  3. 5:23Model-driven agents approach
  4. 9:17ReAct paradigm and agent loop
  5. 11:26Scaling patterns for agents
  6. 15:48Frameworks and tools for agents
  7. 18:23Productionalizing agent systems
  8. 21:36Getting started with agentic AI
  9. 24:08AgentCore for deployment
  10. 26:36Conclusion and resources
~/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.