NDC Sydney 2026
2026-04-22..2026-04-24
Sydney, Australia
[NDC Sydney 2016, NDC Sydney 2017, NDC Sydney 2018, NDC Sydney 2019, NDC Sydney 2020, NDC Sydney 2022, NDC Sydney 2024, NDC Sydney 2026]
| title | author | length |
|---|---|---|
| Fine-Grained Authorization: The Missing Piece in Agentic AI Security | Shivay Lamba | 57m |
Shows how to enforce document‑level permissions for RAG and agent workflows using OpenFGA plus LangChain and vector DBs (demo uses Chroma). Compares… | ||
| Spec-Driven Development: The Fast Track to 10x? | Jerry Nixon | 01h 13m |
Claims a spec-first workflow that cuts delivery time by up to 10x and treats a formal specification as the single source of truth. Demonstrates a concrete… | ||
| The Next Steps to Becoming a Space-Faring Civilization | Richard Campbell | 52m |
DART proves kinetic deflection works: DART changed orbit by >30 minutes after a 500 kg impactor at 6.6 km/s sprayed ~1,000 tonnes of debris. Falcon 9 now flies… | ||
| It's Time To Talk About Signals | Julian Burr | 52m |
Explains what signals are, builds a working demo of a reactive system in 30 lines of JavaScript, and shows how signals track subscribers, compute derived… | ||
| Industrial Strength Testing for Complex Software | Ashley Mannix | 01h 08m |
Seq is a self-hosted diagnostic server with a Rust DB engine (now larger than its C# UI) built by a four-person team and in production for over 13 years in… | ||
| Get a Grip on your Telemetry using the OpenTelemetry Collector | Adam Gardner | 01h 03m |
OpenTelemetry Collector becomes the middle layer that turns raw, timestamp-less log lines into structured records, adds host/resource attributes, uplift… | ||
| Designing technology for dirty gloves | Leanora Horne | 59m |
Human-centered design starts with hours of field observation on real sites with virtual reality mine simulation and workshop mockups, then prototypes: three… | ||
| Skill Degradation: An Empirical Analysis of 400+ AI‑Generated Security Fixes | Pedram Hayati | 41m |
Systematic review of 400+ AI-generated patches for real vulnerabilities shows concrete outcomes: many patches either fail to fully remediate or introduce… | ||
| Building fun and creative messaging experiences on WhatsApp | Michelle "MishManners" Duke | 01h 01m |
Live demo of a WhatsApp image-to-art pipeline that actually runs: users send a photo to a Twilio webhook, the app downloads Twilio-hosted media, forwards the… | ||
| AI Agents That Don’t Suck: How to Build Ones That Actually Drive Business Value | Robert Koch | 56m |
Quartzip builds a voice onboarding agent using WebRTC, Cloudflare, Kubernetes and a pipeline that moved from Google Gemini multimodal to transcription +… | ||
| Pwned with Purpose: Where Motives Meet Mayhem | Troy Hunt | 01h 01m |
Aggregates show 974 breaches and ~17.5 billion records and illustrate motives: ideological leaks (Ashley Madison), revenge-as-a-service gone wrong… | ||
| Platform Engineering in the age of Generative AI | Will Velida | 51m |
Start by inventorying developer tools, codifying onboarding steps and standardising environments so AI has consistent context; replace ad hoc bash scripts with… | ||
| One Team’s Journey to Using AI Without the Hype | John Bristowe | 57m |
Bottom-up adoption at Octopus lets developers experiment with Copilot, Claude, Cursor, Gemini and others rather than forcing a single tool. Teams generate… | ||
| Meditations on Code As Art | David Whitney | 47m |
Argues that code can be intentionally artistic by manipulating language, structure and runtime to convey human expression, and surveys historical artifacts… | ||
| From Pair to Peer Programmer | Aaron Powell | 59m |
Argues that AI has shifted from autocomplete to chat assistants to full cloud agents, and shows concrete workflows: prompt patterns, CLI integrations, and… | ||
| Distributed Databases: What Could Possibly Go Wrong? | Heather Downing | 40m |
Distributed databases fail because of concrete tradeoffs and physics not platitudes: a DNS glitch inside DynamoDB on Oct 20, 2025 makes Dynamo unreachable for… | ||
| Building Responsible Autonomous AI Agents: Principles, Patterns, and Practices | Will Velida | 51m |
Shows a concrete agentic system called BioTracker that ties Fitbit/Wyze data into a Claude-backed chat API, a 12-tool MCP server, and a GitHub Copilot SDK… | ||
| Are LLMs good software engineers? | Anthony Shaw | 55m |
Argues LLMs are not reliable software engineers: they are probability machines that rush into implementations, often reinvent the wheel, and ignore rules… | ||
| 10 tips to level up your ai-assisted coding | Aleksander Stensby | 01h 00m |
Claims that model quality jumps around Opus 4.5/4.7 make AI actually write production code; recommends using the Claude Code harness with its million-token… | ||
| Keynote: Your Agents Are Smart. Your Data Model Isn’t | Chris Auld | 58m |
Argues that explicit ontologies are the missing semantic contract so agents stop autocompleting policy and actually enforce rules, showing a pharmaceutical… | ||
| nothing matches | ||