Every episode, every framework.
24 episodes of agentic workflows, knowledge systems, ROI benchmarks, and hard lessons — from operators who shipped.
Telstra Glitched This Morning: DR, Backhoes, and Agents Up the Creek
Mobile/Telstra friction the morning of the show opens into outage stories, sovereign AI, and Dave's vanished ChatGPT project with Notion as backup. Richard on untested LLM failover in business agents and the backhoe redundancy lesson; Dave on Hermes for the podcast; Matt on observability that acts.
Access, Audit, and Control Are the Product. Harness Bias, GLM 5.2, and the Local Hardware Boom.
Harness guardrails steer LLM answers before the weights do. Episode 24 opens on Richard's LinkedIn pushback on ethical-AI bias narratives, chatgpt.com versus API differences, and self-contained RAG where you only corrupt yourself. Matt's spine: access, audit, and control are becoming the product. News and economics cover GLM 5.2, GPT 5.6 limited preview, Claude Sonnet 5, local hardware growth, token spend comparisons, deterministic workflows versus agent loops, Richard's concentric ring rule, and build-versus-buy on dashboard mirrors and CRM maintenance.
Smart Models Do The Wrong Thing Silently. Why Your AI Agent Just Made You Dumber.
Smart models do the wrong thing silently. The smarter the model gets, the sharper the human's judgment has to be — and almost nobody is investing in that judgment layer. Episode 23 anchors on the Rouse Hill IRL debrief, the deepfake video-call scam where the victim was the only real human, Perplexity CEO Aravind Srinivas's line that the model is no longer the product, and Anthropic's agentic-coding persistent-returns-to-expertise paper. Dave's 32-agents-to-zero-productivity parable, Richard's bank-spreadsheet $40M/$140M caution, the baoyu comic-consistency anecdote, and the Roobot wearing different hats reframe on repo Claude Code plus hats vs fifty agents per project carry the practical corollaries. Enterprise translation covers Microsoft Agent 365, Copilot as harness, Claude Tag in Slack vs Salesforce Agentforce, and the on-prem-RAG pendulum swing.
Two Markets, Two Stacks. Why Your Solo AI Won't Survive The Enterprise Audit.
Anthropic pulled Fable five days into its release after a US government escalation over a jailbreak, and the panel reads the rug pull three ways: as hijack marketing (Savio's Indian-cinema parallel), as an iPhone-moment marketing coup (Dave's Apple G4 reference), and as a real safety-versus-export-control fight. The bigger conversation is the two-market split the Fable story made obvious. Individual productivity (Claude CoWork, Hermes, Antigravity, the personal AI OS) is real but is no longer the product. Enterprise, government, and mid-market buyers need a governed, sovereign, decentralised, audit-ready stack, and that is where the margin and the durability live. New guest Savio Francis from StarFCM has been building for that second market for 16 years. His flagship product Theos ships as an AI native environment that sits above the existing OS, lands as a sovereign in-a-box for ISO 27001 and SOC 2 customers, and targets the data-friction and knowledge-friction taxes that the personal AI OS does not even see. Plus: the Fable 72-hour lived-experience, OpenRouter Fusion as the sub-fable multi-model workaround, Cursor being absorbed by SpaceX AI, the cybersecurity time-to-exploit collapse from six weeks to thirty seconds, and the IRL event at the Australian Brewery in Rouse Hill.
The Model Is the Battery. Pick Your Poison.
Two-person show, just Dave and Matt. The token rug pull is now scheduled. Anthropic is offering Fable at 2x Opus burn rate until 22 June, then it is extra-usage billing only. From there the conversation opens up into the real story of the week: the harness is the product now, not the model. Kimi, Mimo, the Chinese labs and Minimax are all racing for the same layer. Dave walks through his actual daily driver stack: Hermes profiles, Perry White personas, M3 at $20 a month, Telegram as couch interface. Matt brings the hands-off build reality check: 48 hours of Droid Missions produced magical output and nothing that worked. They land on three operating principles: the human SOP and the agent SOP are not the same, ambient context is what humans have that prompts do not, and adoption requires a use case not a licence.
Stop Building Agents. Start Building Judgement Around Them.
OpenAI ships SharePoint-style internal Sites inside Codex. Employees are already shipping unsecured Lovable and Replit links. The panel lands on the reframe of the year: models are no longer the product, the harness is. Dave walks through his full refactor journey from ChatGPT projects to Hermes soul files and skills, and explains why a $10 a month Minimax m3 plan is now enough to do most of the work. Returning host Joanna Jones joins the panel from Western Australia, where she is now backing a statewide AI education push with the WA Chamber of Commerce.
Your AI Subscription Is Already Too Expensive. Here's What Comes Next.
Covers AI agent harnesses, rate limits and silent failures, sovereign/local AI infrastructure, enterprise adoption challenges, and the upcoming IRL event in Sydney.
It's Not If, It's When: The Backup You Don't Have
Railway went dark for three hours. A ransomware crew took an ERP offline for weeks — and there were no backups. When it happens to you, do you have a recovery protocol, or just a hope?
Everyone's Running AI. Nobody's Getting More Done.
Your whole team is using AI. You're generating more than ever. So why isn't anything shipping faster?
Anthropic Just Spent $1.5B to Replace Us. Five AI Operators Respond.
Anthropic announced a $1.5B JV with Wall Street to deliver AI consulting at scale. Five independent operators discuss what that actually changes for SMBs — and why the answer is less than you think.
Vibe Coding Removes the Typing. Not the Engineering.
608% ROI. 4.2 days down to 6.8 hours. One small manufacturing team. Richard brings the case study that answers the question most operators are afraid to ask.
Vibe Coded. No Security. Dead in 72 Hours.
A founder vibe-coded a SaaS. Launched Friday. Dead by Sunday. How hard is it to get security right when you've written zero lines of code yourself?
The Jury of 12: Why You Still Need Humans In An Agent Stack
Richard's surfing in Indonesia. Nataliya from LeadMark AI joins — enterprise change manager by day, SMB AI embedder by night — with the framing this panel's been circling for months: every 'AI implementation problem' is a change management problem in a tech t-shirt.
Tokenomics: Why Your $120 AI Plan Is About to Break
Pull the loose thread of the Claude Code source leak and you end up unpicking the whole economics of AI subscriptions. Is a $120 plan or $65 worth of API tokens the better bet once the maths is run?
Was This Built for a Previous Reality?
Your calendar missed a public holiday. Your most trusted JavaScript library just got backdoored. Your CFO's two-week paper report just got replaced in five minutes. What do all three have in common? They were built for a previous reality.
Expert in the Loop: AI File Recovery, $1.50 Personal Agents
Richard's back. Marno's personal AI runs 72 tasks a day for $1.50. Matt locked down OpenClaw with secure defaults. Dave recovered a corrupted voice recorder file using Claude Code in under an hour. And we debate whether SaaS is dead or just getting reshuffled.
To Claw or Not to Claw: Dave Ditches Google
Dave finally pulled the trigger on Claude after Google Gemini trashed his quotas mid-session. Marno went full AI OS — calendar, email, invoicing, all through a Discord bot. Matt ingested Alex Hormozi's entire content library. NVIDIA just announced NemoClaw + OpenShell.
Change Management in the Age of Agents
Dave and Matt are joined by Amber and Jo to deconstruct the reality of 'AI Operating Systems' — from deploying autonomous farm robots in regional WA to building compartmentalized AI agencies that parse SOPs to self-correct.
Stop Using Web UIs: Why LLM APIs Are 10x More Accurate
The crew dives deep into the infrastructure realities of Sovereign AI — including why the future of data centers might literally be in orbit. Plus the massive performance differences between standard AI web interfaces and direct LLM APIs.
The Chainsaw Paradox: Why Your New AI Tools Are Making You Slower
Why is it that the more AI we use, the busier we seem to get? Welcome to the 'Chainsaw Paradox.' Having the best tools won't save you if you're still hacking at the trees with the engine off.
Your AI Agent Can Be Hacked While You Make Coffee
Your AI agent is running. You step away to make a coffee. By the time you're back — your API keys are gone, your files are exfiltrated, and a hacker you never saw is inside your system. Richard Webbe joins the cast.
Just-In-Time Interfaces: Why Your Next App Won't Have Fixed Buttons
What if your software interface changed based on what you needed to do — right now, in this moment? No fixed dashboards. No predetermined layouts. Just contextual, dynamic interfaces generated on demand.
AI 'Context Rot' Explained: Why Your Agents Get Dumber
Is your AI actually learning, or just rotting? We dismantle the 'stateless' nature of LLMs and how relying on long chat threads leads to 'context rot' — a digital dementia that degrades your results.
Start a New Chat — What 3 AI Operators Actually Use It For
The very first episode. Dave, Matt, and Marno pull back the curtain on how real operators are leveraging AI in the wild — the shift from prompt engineering to context engineering, and how to build infrastructure that isn't entirely rented from big tech.