SSMAgentic EngineeringA live, agent-powered briefing
Prepared for Gary Chan · Chief Information Security Officer · SSM Health

Software that acts, not just answers.

Agentic engineering is the shift from AI that responds to prompts to AI that pursues goals — systems that reason, use tools, write and run code, check their own work, and complete multi-step tasks with a human in the loop. This page is itself an example: a live agent is embedded here. Ask it questions — or tell it to restyle this page, generate imagery, even replace the video with one it makes on the spot.

Watch the briefing webinars

The premise

An LLM stops being a chatbot and becomes an operator: it plans, calls tools and data, observes results, and iterates toward an outcome.

Why now

Tool calling, reasoning, evals, and protocols like MCP matured together in 2023–2025 — turning a research idea into deployable enterprise software.

Your lens

New capability is also a new trust boundary. Governance, least-privilege access, and human oversight separate leverage from exposure.

What "agentic" actually means

Plain-language definition

An agent is an LLM that directs its own process to reach a goal.

In a traditional workflow, developers wire the steps in code. In an agentic system, the model decides the steps: it chooses which tools to call, reads what comes back, corrects course, and keeps going until the task is done — or hits a guardrail you set.

Anthropic's widely-used framing draws the line cleanly: workflows follow predefined paths; agents dynamically direct their own. The discipline of building, constraining, and evaluating those systems reliably is agentic engineering.

"The most successful implementations use simple, composable patterns rather than complex frameworks."— Anthropic, Building Effective Agents, Dec 2024

Framed for a healthcare security leader

Capability vs. hype

The durable signal is benchmarked task completion (SWE-bench, τ-bench), not demos. Evaluate agents on verified work.

The new trust boundary

MCP and tool-calling are where an agent touches data and systems — exactly where least-privilege and auditing belong.

Human-in-the-loop by design

The mature pattern is constrained autonomy: agents propose and act within scopes; people approve consequential steps.

ROI with governance

Value shows up when agents run inside a governed "mesh" — identity, permissions, observability — not as ungoverned point tools.

The centerpiece · Watch & learn

Hear it from the people building it.

Pick a talk — it plays right here. Every video was verified as real and embeddable. (Tip: ask the agent to "replace this video with an AI-generated one.")

✓ 7 talks · embeds verified

Why it matters: The canonical framing of agentic AI. Ng's four design patterns — reflection, tool use, planning, multi-agent — are the vocabulary every vendor now uses.

Source: Sequoia Capital · Open on YouTube ↗

Select a talk

Behind the build

This briefing built itself.

Agentic engineering isn't just the subject of this page — it's how the page was made. From one plain-English request, an AI agent researched the field and verified every source, wrote and deployed this site, provisioned its own cloud hosting and a least-privilege deploy credential, and built the live assistant you're using now. The full prompt-by-prompt story is a genuinely good read.

Read the build story →

Capability vs. hype

What's actually real today — measured, not demoed.

The honest read for a decision-maker: coding and tool-use agents have moved from novelty to measurable, fast-improving capability — while reliability, oversight, and governance remain the gating factors for enterprise deployment.

Where it lands in a health system

Agentic workflows map cleanly onto healthcare's multi-step work.

Prior authorization, documentation, revenue cycle, IT operations, and patient access are exactly the tool-heavy, multi-step processes agents are built for — and exactly where PHI raises the governance bar. Illustrative use cases, not endorsements of specific tools.

The CISO's checklist

Governing agents is an architecture problem, not an afterthought.

If agents can act, the questions a security leader asks shift from "what did the model say?" to "what is the model allowed to do, as whom, with what data, and who approved it?" A practical frame:

The real arc

From a research idea to deployable software — in about three years.

Every milestone is dated to its first publication and links to a primary source.

Who is building this

The organizations and people shaping the field.

Organizations

People

Read the primary sources

The documents behind the claims.

Papers, standards, and enterprise reports — each link checked to resolve.

In their own words

What the field's leaders are actually saying.

Real, attributed quotes — speaker, venue, and date — each linked to where it can be verified.

Generated live, by the agent

AI Studio

Anything the embedded agent generates — images (Imagen 4) or video (Veo) — appears here. Ask it: "generate an AI image of a secure healthcare data mesh," or "make an AI video for the hero."

Nothing generated yet — open the agent (bottom-right) and ask it to create something.

Traceability

How this briefing was sourced.

Researched before written. Every webinar, paper, and quote traced to a primary source and link-checked.

Verified

  • All 7 webinar embeds confirmed real and embeddable via YouTube oEmbed.
  • All papers/standards link to primary sources (arXiv, Anthropic, MCP spec, DeepLearning.AI, McKinsey) and were checked to resolve.
  • All quotes are verbatim and precisely attributed, each linked to its source.

⚑ Flagged — confirm before circulating widely

  • Bot-blocked pages: OpenAI's "SWE-bench Verified" post and the NEJM AI article returned automated-access blocks; URLs are real/corroborated — open in a browser. The NEJM AI piece is sponsored content.
  • X/Twitter quotes: the two Karpathy quotes are from X (blocks automated fetch); wording well-attested — click through.
  • AI-generated media on this page is produced live by Google Imagen/Veo at your request and is illustrative — not a real recording of any person or event.
✦ The agent noticed