HeyJaredAgentic AI
I share my thoughts on anything related to Agentic AI and Agentic AI Security topics.
- Indexed issues, last 90 days
- 26
- Latest publication
- Sep 30, 2026
- Audience
- Checking…
- Earliest in this view
- Sep 2, 2026
Latest issues
Claude Eval Design and Hillclimbing: From Reliable Tests to Better Agents (opens the original)
Read excerpt
Claude can automate evaluation design and propose application changes using /claude-api build-eval and /claude-api hillclimb, but a higher score supports a deployment decision only when the measurement remains trustworthy. The engineering work starts with representative cases, calibrated grading, and an explicit decision rule. It continues with a separation between the evidence you use to improve the application and the evidence you use to approve its release.Separate measurement from optimizati
Your AI Strategy Needs a Degraded Mode (opens the original)
Read excerpt
Innovation is moving at unprecedented speed. Over the last few days, the signal I found worth paying attention to came from what happened when people could not reliably reach the intelligence they had started to depend on. A better model can expand what a team attempts. An interruption reveals which parts of that team's operating model still work without it. My thesis is simple: every important AI workflow needs a degraded mode with a clear service promise. That promise should describe the usefu
The Next AI Moat Is Workflow Economics (opens the original)
Read excerpt
Innovation is moving at unprecedented speed. Over the last few days, the signal worth paying attention to was not another model leaderboard jump by itself. The stronger signal was how much of the serious conversation shifted toward inference budgets, workflow cost, and the systems that decide when expensive reasoning should run at all.That shift matters because cheap tokens did not make AI cheap. They made it easier to ask for more work. Once teams can afford one more agent step, they ask for te
Springer Publishes Humanoid Robots and Physical AI Book (opens the original)
Read excerpt
Springer has published Humanoid Robots and Physical AI: Reshaping Work, Society, and Human Purpose. The live book is at DOI 10.1007/978-3-032-33669-9. The volume runs XXVII + 381 pages across ten chapters, with 90 color illustrations, in the series Advances in Data Analytics, AI, and Smart Systems.I announced the project earlier in my previous Substack article, Announcing Humanoid Robots and Physical AI Book by Springer. That post covered the whole-system thesis and the preorder path. This
Close the Loop: Find, Fix, and Prove It (opens the original)
Read excerpt
A Ridge Security white paper · by Yan Zhou and Ken Huang, September 2026Executive summarySecurity teams do not lack vulnerability reports. They lack a dependable way to turn a proven risk into a verified fix, especially when more application code is written by AI assistants that optimize for working features, not attested security.This paper describes a customer-facing auto-remediation process. RidgeGen finds and validates exploitable risk on the running application. Google CodeMender generates
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.