Enterprise AI Summit 2026
who it's for
engineering managers, platform engineers, ai/ML engineers, software architects, devops engineers, security engineers, product managers
topics
agentic software factory patterns; chief of staff agent implementations; automated code review pipelines; adversarial code assurance; token budgeting and cost optimisation; flow framework for delivery speed; SDLC controls for agentic systems; AI-powered resiliency testing; Temporal orchestration for write intents; model risk assessment and governance
| title | author | length |
|---|---|---|
| Wheelhouse and Counting House: Two ways to put models to work | Steve Yegge | 22m |
Two production patterns: a 50-agent Wheelhouse software factory that ships about 2,000 commits a week, costs ~$10–12k/month in inference (22 Claude Max… | ||
| Output to Outcome: When Agents Outrun the Org Chart | Mik Kersten | 24m |
Presents Flow Framework data from hundreds of enterprise value streams using Jira GitHub GitLab and ServiceNow exports to show where AI speeds delivery and… | ||
| The System Pokes Back | Elisabeth Hendrickson | 24m |
CircleCI data from 28.7 million CI workflows shows a small cohort ships faster while most slow down because AI increases PR size and creates merge congestion… | ||
| The 5 Fatal Mistakes of Enterprise AI Deployment | Joe Beutler | 30m |
Five predictable deployment errors and concrete countermeasures: copying a peer (BNY built ELISA, launched 2024 → ELISA 2.0 Jan 2025) vs. build where it truly… | ||
| Controlled Acceleration: Evolving SDLC Controls for an Agentic World | Khalid Elsawaf | 25m |
Morgan Stanley breaks manual reviews into focused, reusable agent skills that run in developers’ IDEs and CI/CD, turning code review (previously 50% of a… | ||
| Fireside With Jitesh Ghai and Gene Kim | Jitesh Ghai, Gene Kim | 27m |
A chief-of-staff agent named Ziggy uses Claude Code to stitch calendar, Salesforce, ERP, HCM, Confluence and customer sites so it delivers meeting briefings… | ||
| Now What? | Justin McCarthy | 24m |
A team claims to read their last line of code July 2025 and shows a working software factory that replaces human coding by designing an outer loop and heavy… | ||
| Agentic AI and Code Reviews: Patterns and Case Studies | Randy Shoup, Michelle Gill | 25m |
AI-generated code rises 19% to 57% in three quarters, and top teams now move 9x faster than the median. The presentation lays out concrete patterns: small… | ||
| Our Journey to Agentification | John Rauser | 27m |
Describes a working Magellan AMOS: a knowledge base, control plane API, prompt files, skills and plugins, plus a browser extension, E-ink information radiator… | ||
| Building The Chief of Staff Agent 80x Faster | Philipp Göllner, Gene Kim | 18m |
Five people build an OpenClaw chief of staff in six weeks by handing Jira tickets to an orchestrator agent (Claude) on top of a DevOps foundation with 6,000… | ||
| Who Gets to Fly First Class? Value per Token in the AI Factory | Jeremy Eder | 25m |
Argues that AI code generation requires hard limits: Red Hat institutes per-engineer token budgets and a centralized AI gateway to route work to the cheapest… | ||
| The Tech Stack Below TPS | Art Smalley | 23m |
A vertical tech stack at Toyota runs from Toshiba T3100/J3100 with DBase 3 spare‑parts apps in 1989 to modern cloud → GitHub Actions → Vercel → Supabase… | ||
| GenAI Adoption, Challenges & Anti-Patterns | Topo Pal | 26m |
GenAI speeds tasks from months to hours yet breaks assumptions: a software bill of materials dashboard that took five days plus three weeks to production a… | ||
| AI-Driven Organizational Value | Jeff Gallimore, Topo Pal | 25m |
Shows why rising AI adoption and token spend lift productivity metrics but not P&L, arguing freed capacity is a capital allocation choice among harvest… | ||
| Adversarial Code Assurance as a Way Back to the Paved Road | James Wickett | 23m |
Claims that AI coding agents introduce logic flaws like IDOR and broken authorization not caught by classic scanners and that DryRun runs 600,000 code reviews… | ||
| It's a Feature, Not a Bug: Making Sure Code You Didn't Write Does What You Meant | Andrew Stellman | 23m |
An open source workflow called Quality Playbook reconstructs intent from docs, chats, and issue threads, turns that intent into IEEE‑style requirements, checks… | ||
| From Fire Drill to Operating Model | Dustin Warner | 27m |
NRC Health rebuilds a flagship survey platform with three people, 90 days, AI‑first using Opus 4.5 models and daily co‑design, reaching feature parity and full… | ||
| Scaling Confidence Through AI-Powered Resiliency Testing | Christina Yakomin | 24m |
Vanguard moves from counting tests to improving them: AI interprets API specs and produces executable scripts, then configures load using production throughput… | ||
| Going Founder Mode in a Big Company | Michael Angelo Rivera, Jean-Gabriel Doyon | 22m |
A handpicked six‑engineer team gets a CEO mandate, flies to a Vancouver kitchen-table sprint, and ships roughly 30,000 commits and 5,000 merge requests in two… | ||
| Architecture Driven AI Engineering | JD Black | 25m |
Describes a five‑phase agentic software and IT lifecycle that enforces architecture-as-code via SysML v2, traces requirements into automated Gherkin acceptance… | ||
| Minutes Matter: Fielding Edge AI for Personnel Recovery in 6 Weeks | Kevan Mordan, Kenny Slater | 24m |
Built a TAK plugin that detects and labels buildings on overhead imagery, ships in six weeks with six people, and runs fully on aging S20/S23 Android phones… | ||
| Previously Impossible | Owen Parker, Kurtis Cochran | 26m |
A 250‑person kidney pathology lab rebuilds core workflows and builds greenfield AI: automated HL7 billing correction intercepts and rewrites messages to… | ||
| Inspect the House, Not the Neighborhood: What Actually Makes an AI Model Risky | Nicky Pike | 23m |
A fake Hugging Face model hits 244,000 downloads by faking an OpenAI repo and ships malware in a setup script; JFrog finds ~100 models with malicious payloads… | ||
| Everyone's Building Now: Thrive Market's AI Adoption Journey | Marya Caples, Michael Winslow | 28m |
Claude license arrives in February with no framework and teams build forward: an Ingredient Vetting Portal uses Google Apps Script + Google Sheets to replace… | ||
| Opening Remarks — Day 1 | Gene Kim, Andy Ramirez | 15m |
Claim that agentic coding reshapes orgs like DevOps but 100x bigger and faster, backed by concrete outcomes: a pair-programming session produces a working… | ||
| Closing Remarks — Day 1 | Gene Kim, Andy Ramirez | 04m |
Organizers claim AI is 100× bigger and 100× faster than the DevOps era and say that changes are reshaping teams and roles across the organization. They ask… | ||
| Opening Remarks — Day 2 | Gene Kim, Andy Ramirez | 10m |
Reflects on limits of the DORA metrics while claiming orders‑of‑magnitude gaps between measured productivity and felt “agentic” speed, recounts winning a… | ||
| Closing Remarks — Day 2 | Gene Kim, Andy Ramirez | 14m |
Announces a third novel called Pandora Project and shows a working LLM wiki called IT Rev MCP that ingests every talk, paper and 64,000 Slack messages plus… | ||
| nothing matches | ||