Skip to content
Sign in
Artwork for The Agentic Enterprise: a practitioner's guide to building agentic systems
Technology

The Agentic Enterprise: a practitioner's guide to building agentic systems

Agentic AI Practitioner

The Agentic Enterprise is a practitioner's guide to building agentic systems — for executives and practitioners who carry the accountability for making AI work in production.

AI agents are moving from demo to production, and the gap between the two is where the real work lives. Each week, hosts Alex and Jordan break down what it actually takes to design, deploy, and operate agentic AI inside real organizations: choosing the right work to automate, architecting for reliability, governing with trust, and measuring what matters. Technical enough to act on, never lost in the weeds.

Play
Open in
  • 7 episodes
  • Avg 5 min
  • English

Episodes 7

NewestOldestLongest
All7Unplayed7In progress0Played0
  • Friday · 9 min

    Episode 5 - Architect the System (Track A)

    Every agentic system is really nine layers — whether you designed them or not. In this episode, Alex and Jordan walk all nine through a real war story: an invoice agent that worked in the pilot, then paid twelve thousand dollars to the wrong vendor in week three of production. The agent did everything it was told. The problem was everything nobody told it. The nine layers: the handoff (experience), orchestration, decision intelligence, integration, context and memory, the data foundation, the model layer, security and trust, and observability — with governance cutting across all of them. The thesis: the layers aren't the hard part. The boundaries between them are. Two skipped decisions — nobody defined what the agent may conclude, nobody owned the data it read — cost twelve thousand dollars. Plus, a beat for the product managers: you don't need to draw all nine layers yourself, but you need to know which layer your requirement lives in. This is Track A, Episode 1 — the System track: how you build it. New here? Start with Episode 1: Beyond the Demo, or catch the Two Tracks interlude for the full map of where the show goes from here. Monday move: take your most important pilot and draw the nine layers on a single page. For each layer, write the one decision you actually made. Where it's blank, that's your architecture debt.

  • Friday · 2 min

    Two Tracks: The System and the Product

    Episode 4 asked what to build. Episode 5 asks how to build it. This is the bridge between them. In this short interlude, Alex and Jordan announce the show's new structure: two tracks running in parallel. Track A — The System. How you build it: architecture, data, evals, governance. Starts with Episode 5: Architect the System. Track B — The Product. What you build and why: the brief, version-one scope, metrics before building, shipping to people who don't trust it yet, and knowing when to kill it. Why two tracks? Because product managers are becoming builders and builders are becoming product thinkers — and the old handoff between them doesn't survive contact with agents. Every system episode now carries a beat for the PM; every product episode carries a beat for the builder. New here? Start with Episode 1: Beyond the Demo.

  • Wednesday · 7 min

    Episode 4 - Agentic Product Approach

    Most agentic pilots don't die from bad engineering. They die because nobody wrote down what "working" means. In this episode, Alex and Jordan take the product line: the agent is a product, not a project. It has users, an owner, and a definition of done. In this episode: - The product brief: one paragraph answering four questions before anyone maps a process - Users are plural: the end user, the supervisor, and the auditor, and why all three belong in the brief - Define what good looks like first: accuracy, speed, and escalation rate, picked while you're still honest - Version-one discipline: the most powerful list in the brief is what the agent will not do yet - Name one owner: every agentic product that survives has one, and every one that dies was owned by a slide - Then dive into the process anyway: end to end across the silos, because the agent inherits whatever you don't map The Monday move: take one use case and write the one-paragraph product brief. Who uses it, what job it does for them, how you'll know it worked, and what's not in version one. Then trace the process it sits on, end to end. If you can't do both on one page, you've found your first problem.

  • Wednesday · 2 min

    Introduction - The Agentic Enterprise

    Before you listen to a single episode, listen to this. Two minutes on what The Agentic Enterprise is, who it's for, and the playbook we're building together. In this episode: Why this series exists: cutting through the AI agent hype for practitioners The gap it lives in: what works in a demo versus what survives in production Why practitioners: the people who feel the consequences when agents fail Where it comes from: more than twenty years in the field, hundreds of systems built across consulting, technology, and banking The season goal: a complete practitioner's playbook, one episode and one Monday move at a time Your first move: start with Episode 1, "Beyond the Demo" — it begins with the most abused word in the industry right now: AI Agent.

  • September 22 · 7 min

    Episode 3 - Map before you build

    Where do the agents go in — and where do the humans stay in charge? Alex and Jordan lay out the map-before-you-build discipline for placing every step before a single bot is built. In this episode: Start with evidence: process mining and system logs — if the map doesn't surprise you, you mapped the brochure Walk the real process: documented versus real, with the SMEs who live in it Decision logic: deterministic gets encoded as workflow; interpretive gets AI assisting the human first Supervision and risk: the agent proposes, a person disposes — with risk and legal as co-designers Map as contract: every agent insertion point gets a test The Monday move: pick one process, map the real current state with two people who do it daily, then mark three things on the future state: where agents go in, where humans stay in charge, and what risk and legal need to see. One page.

  • September 21 · 6 min

    Episode 2 - Choose the right use case

    Which processes deserve an agent — and which should stay deterministic? Alex and Jordan lay out a four-dimension scorecard (value, variability, risk, feedback) for making that call honestly. In this episode: Price the counterfactual: the business case starts with what the work costs today Variability: why invoice processing breaks rule-based systems — the variability never stops Risk: supervised agents, the agent proposes and the human disposes Feedback: the quiet pilot-killer — no verifiable outcome means no trust Three processes scored live: complaint triage, financial close, contract review The Monday move: score your top three candidates. Under 12 stays deterministic, above 15 makes the shortlist

  • September 18 · 5 min

    Episode 1 - Beyond the Demo

    Everyone's demo looks agentic. Almost none of them survive production. In this opening brief, Alex and Jordan ask what makes a system genuinely agentic — goal pursuit, tool use, adaptation to feedback, bounded autonomy — and when a simpler workflow is actually the smarter choice. You'll get the agency test: four questions to run any "agentic" project through before you commit, the real cost of agency in tokens, latency, and operations, and the Monday-morning move — start deterministic, add agency only where variability hurts. Hosts: Alex and Jordan. Content created by Agentic Practitioner.

Showing 1–7 of 7 episodes