What is an AI Harness? | Mid-Market AI | Episode 107

What is an AI Harness?

$200 billion invested in AI. 6% meaningful impact. The gap has a name -and it's not the model.

In this episode, Ariel Jalali breaks down the most practical concept in AI right now: the harness. The infrastructure layer that sits between your business and the raw model - and the reason most AI projects work in a demo and die in production.

You'll learn the formula every operator needs to know (Agent = Model + Harness), why nearly half of enterprises are completely blind to what their AI agents are doing inside their own systems, and the difference between single player and multiplayer AI- and why jumping between them without a harness is the fastest way to become a cautionary tale.

Ariel also covers why you probably picked the wrong size model (not the wrong vendor), what that's costing you at scale, and the land grab happening inside Claude Code and Codex that most mid-market companies haven't noticed yet. Plus real examples from a specialty food manufacturer and a home health operator already running harness-grade AI -without ever calling it that.

If your AI experiments haven't turned into results, this episode is the answer.

Mentions: Mitchell Hashimoto on engineering the harness, Andrej Karpathy on agents as the new customer, Gartner's 40%+ agentic project cancellation risk, and BCG's 2026 research on companies stuck in deploy mode.

Mid-Market AI is produced by Paragon Technology Solutions. Paragon puts Chief AI Officer-led data & AI engineering capabilities inside PE-backed and mid-market companies.

Paragon - Managed Intelligence Provider (MIP™)

Transcript

SPEAKER_00 0:06

What is an AI harness? I know it sounds kind of naughty, but I assure you it isn't. What it actually is and why it determines whether your AI project succeeds or dies in production is probably the most important thing I will explain on this show so far. You're listening to Mid Market AI. I'm Ariel Jalali, CEO of Paragon. We're a managed intelligence provider. We put chief AI officer-led data and AI engineering capabilities inside PE-backed and mid-market companies. A few times a week, I get on here and I cut through the noise for the operators and the investors who need field experience rather than conference slides. Quick note on today's episode. I'm going to speak to a few different people at once. If you've got a portfolio company or you're a CEO and technology makes your eyes glaze over, stay with me. I got you. If you're a PE operating partner or a fund-level AI person, there's something in here for you too. And if you're an MSP or channel partner, try to figure out how AI fits your practice. Don't go anywhere because the harness is actually your golden opportunity. I've been doing this long enough to know how these episodes can sometimes land a bit arrogantly, so I'm gonna say this up front. I'm not here to tell you that Silicon Valley has yet again figured something out and you need to catch up. I'm here to tell you the opposite. The manufacturers, the home health operators, the distributors, service companies, the companies in private equity mid-market portfolio, they're already living these buzzwords. They built exception routing that runs without a human touching it. They have inventory alerts that fire purchase orders automatically. They have care scheduling logic and staffing scheduling that matches staff to customer and patient needs across dozens of variables. They didn't call it AI infrastructure, they didn't call it a harness, they just called it Tuesday. Silicon Valley is in a theoretical tower right now, wondering what enterprise AI looks like in the real world. You are the real world. They need you more than you need them. So when I use terms like harness, governance layer, optimization API, I'm not bringing you new ideas, I'm just giving you the vocabulary for what you already built or are in the process of building, so you can do it more intentionally, at scale, and with governance. And so you can tell that story to an acquirer who will pay a premium for it. You are the men and women in the arena. This episode is your briefing. There's a pattern around these AI buzzwords, and once you see it, it becomes hard to unsee. Every single one landed on your desk as a board agenda item before anyone explained what it actually meant. The pressure to have an answer always came before the tools came to form one. It started with generative AI or Gen AI. The moment the general public got their hands on Chat GPT and they realized that an AI could create amazing things, not just sort things into buckets. Then came prompt engineering, the craft of how you talk to a model. Then context engineering, not just what you ask of the AI, but what you load into the model's memory before you ask it. Then agentic AI and AI agents, models that can actually take actions, run tasks, call other systems, do things, not just say things. And now we're at the harness. Every one of those was real. Everyone was overhyped for about 18 months before it just became how things work. The harness is going through that cycle right now, and the difference is the harness is the actually the one that determines whether any of the others actually work. It's the most practical concept in AI right now, and it has the worst name. The term came from a guy named Mitchell Hashimoto who built HashiCorp and created Terraform. He published a post describing a habit he had developed while working with AI agents. Every time an agent made a mistake, he engineered a permanent fix into the agent's environment. He called that engineering the harness. Within weeks, OpenAI and Anthropic both published pieces expanding on the idea. One engineer's blog post led to an industry vocabulary in just under a month. One quote reframes this entire conversation, and it comes from Andre Karpathi, the former head of AI at Tesla, who co-founded OpenAI. I feel he's one of the most credible voices in this field. He said this in March. The customer is not the human anymore. It's the agents acting on behalf of humans, and this refactoring will probably be substantial. Let's sit with that for a second. The customer is not the human anymore. We will come back to exactly why this sentence makes the harness non-negotiable. The cleanest formula in AI right now, AI equals model plus harness. The model is the AI, the brain that reasons and generates. The harness is everything else. I'll be honest with you, I've been trying to give people a clean, stable definition of the harness, and an honest answer is this. The definition keeps moving. Six months ago it was the orchestration layer around the model, then it absorbed the runtime, now it's absorbing the cloud infrastructure itself. Every vendor is rebranding their piece of it. So instead of what it is, here's what it does, because that part doesn't change. The harness is whatever sits between your business and the raw model, making sure five things happen. The data gets in, the right outputs get out, someone is accountable for what happens in between. You can see what your agents are doing, and you can change any piece of it without rebuilding everything else. Five functions. One, governance, two, routing, three, memory, four, integration, and five, control. If something in your AI stack is doing those five things, well, that's your harness. Whatever anyone's calling it this week. If nothing is, that's why the demo worked and the production environment didn't. That's why the board is asking questions that you can't perhaps answer yet. Think about a new employee, brilliant, capable day one, they don't know where everything is. You wouldn't hand them the keys to your production database, giving them no trading, no guidelines, no manager or mentorship, and say, go figure it out. But that's exactly what most companies are doing with AI. They wire the model directly into their data, point it to a task, and then they wonder why it doesn't work reliably. The harness is the onboarding, the structure, the context. Governance is the manager who sets the rules, routing is the team who leads and assigns the right task to the right person. Memory is the institutional knowledge they build over time. Integration is making sure that the work actually lands somewhere useful and controls the ability to redirect them, correct them, or swap them out if something better comes along. Five functions, one job, which is to make the AI reliable inside of your real business. Now back to Karpathi, because I think it really changes the stakes on everything. Automated traffic on the internet is growing now at eight times faster rate than human traffic. Eight times. The CloudFrear CEO put it this way: if a human task visits five data sources, the AI agent is doing that same task visit times 5,000. By next year, bottom agent traffic is projected to exceed all human traffic online. So what does that mean for your company? Your systems are increasingly being used not by your employees or stakeholders who are human clicking around, but by AI agents acting on behalf of humans or teams, running at machine speed, at machine volume, mostly silently. And nearly half of enterprises right now, 48.9%, are completely blind to that. Machine to machine traffic, they can't monitor what their agents are doing inside their own systems. They can't tell a legitimate agent from a malicious bot or a swarm. That's not a model problem, that's a missing governance and control function, two out of the five big ones. When a primary user of your systems is an AI agent instead of a human, the harness doesn't just become more important. It becomes the only thing standing between your operations and complete invisible chaos. A human makes a mistake, you catch it. An agent or an agent swarm makes a mistake at machine speed at machine volume with no one watching it, and nearly half of companies have no idea that it's even happening. For the PortCo CEO, the harness is why your AI experiments haven't turned into fruitful results. Not because the AI is bad, more because nobody built the structure around it. For the PE operating partner, the harness is the difference between the demo that works and a system that runs reliably at 2 in the morning when nobody's watching in a measurable way. For the MSP channel partner, governance and control. Two of the five big functions are exactly where you already live. The harness is your natural expansion. Let's talk about single player mode versus multiplayer mode. This frame is going to matter enormously for mid-market operators over the next 18 to 24 months and onwards. Today, when most people use AI at work, they're in single player mode. You have your agent, it helps you do your job, you ask it to draft something, summarize something, research something, one person, one model, one conversation, or a number of chat threads that it that you're having one-on-one with your AI agent. Karpafi is not in single player mode anymore. He said that in March he hasn't typed a single line of code since December. He runs 20 AI agents in parallel. He's not using AI, he's orchestrating it. That's what multiplayer looks like at the frontier. In multiplayer mode, your department has an agent, not you personally, your entire team does. That agent coordinates work across the whole group, knows what everyone is working on, it routes tasks, it escalates exceptions, and any person on the team can step up and orchestrate, give the agent direction, redirect it, hand it off, pick up where it left, and uh it's not one person's tool anymore, it's really the team's operating system. If we extend that one level further, your sales agent coordinates with your finance agent, your operations agent talks to your supply chain agent, agents orchestrating agents, that's the agentic enterprise. Single player mode is forgiving. If your AI agent gives you a bad answer, you can catch it, you're in the loop. The blast radius of the mistake is relatively small. Multiplayer mode is not forgiving. When agents are coordinating work across a team, routing decisions, triggering actions in your ERP, sending outputs to your customers, the blast radius of a bad output is enormous. Gardner is already saying that over 40% of agentic AI projects are at risk of cancellation by next year, specifically because governance and observability aren't in place. That's the multiplayer cliff. Rush to multiplayer without a harness, and you're the cautionary tale. The harness is the governance layer that makes multiplayer safe, and without it, multiplayer mode is chaos with the budget. With it, it's your competitive advantage. For the PE operating partner, the companies in your portfolio that get to multiplayer mode safely with a real harness underneath are the ones that show operational leverage that AI promises. The ones that skip the harness are the ones that you'll be cleaning up afterwards with compounding technical debt, data debt, and process debt. The number that should rephrase the number that should reframe every AI conversation you have with your board, global investment in AI has crossed over 200 billion. That's probably going to change by the next episode. Things are moving fast. And only 6% of organizations report meaningful bottom line impact. Nobody has published a study that says the harness is specifically why, but every time we get called in when one of these pilots is going sideways or is struggling or is hallucinating, we tend to see the same thing. The data going into the model was the outputs went nowhere, there was no exception handling, nobody owned the environment, nobody defined what failure looked like, nobody built the controls. That's not the model failing, that's nothing around the model. All five functions or some portion of them missing at once. The pattern is always the same. The POC works in a controlled environment with a single player mode developer with a clean sample data, someone watching carefully, then the model performs beautifully. Or it fails predictably. Leadership got excited, the board slide looked great, and then they tried to roll it into production and everything falls apart. What they didn't account for is that the POC typically costs 15 to 25% of what actual production costs are. The demo proves the idea works, production proves that it works reliably, securely. What they didn't account for, the POC typically costs just 15 to 25% of what production actually costs. The demo proves the idea works, production proves it works reliably at scale with real users on data that's messier than the sample set. Most companies scope for the demo and skip the 70% of the hard problems, the data cleanup, exception handling, integration, governance. The data problem is real and it's expensive. 68% of failed AI projects underinvest in data foundations. They discover quality issues an average of 5.2 months into development after the budget is committed and the board is excited and the vendors are paid. And when they finally address it, data remediation costs 2.8 times the original project budget, nearly three times on top of what they already spent. For an established mid-market company, Azure Shop, multiple ERPs, data accumulating for 15 plus years across systems that don't talk to each other. This is not a hypothetical. This is just another day. And for the manufacturers and distributors in PE portcos right now, there's a specific version of this that is particularly brutal. Tariffs broke demand planning, not the people, the cycle time. Supplier costs shift overnight, freight lanes reprice weekly, the forecaster planning team built on Monday is wrong by Tuesday. One large retailer reported costs up 20% year over year from tariffs alone, many more. Traditional demand planning assumed stable inputs for months at a time. That world is gone. The companies surviving margin compression are the ones whose data is watching signals in real time, modeling scenarios, routing decisions before the window to act closes. That's the data latency problem. We call that the typical thermostat problem in terms of system archetype challenges. And it's really a harness problem when you get down to it. The second failure mode is one nobody talks about because it feels embarrassing in hindsight. Nobody gets fired for choosing GPT or Claude. It's the safe call, the brand name, the thing you can defend in a board meeting. It's the same instinct that drove people to say nobody gets fired for buying IBM for 30 years. But at production volume, you pointed a frontier model or more to your monthly cloud bill for a task that a smaller, cheaper, purpose-built model handles better and faster. On domain-specific tasks, a fine-tuned small model, or what we call an SLM, achieves 94% accuracy on contracts versus a frontier model's 87%. The smaller model is not just cheaper, it's more accurate on the narrow job. And it's 10 to 30 times cheaper to run. Small language models now dominate six out of eight major enterprise use cases on a cost efficiency basis. So you didn't pick the wrong vendor, you just picked the wrong model size. And nobody built the harness routing function that would have told you that or given you the ability to swap when you figured it out. Third, and this one connects specifically to every Microsoft shop listening right now. Most of you are in Azure M365, probably have copilot running or in conversations about it. And that's the right foundation. Azure is actually ideal for a harness. Your data stays in your tenant, your security posture is already there, your IT team knows the environment. The question is not whether to use Azure. The question is whether you've built the harness layer inside it. A copilot license is not a harness. Copilot is a model with a thin wrapper. Doesn't govern your data across systems and it doesn't route between models. It gives you the full audit trail and you don't own the architecture. The question is not whether to use Azure. The question is whether you've built the harness layer inside it. A copilot license is not a harness. Copilot is a model with a thin wrapper. It doesn't govern your data across systems, it doesn't route between models, and it doesn't give you the full audit trail, and you don't own the architecture fully. The harness is what protects your Microsoft investment. It lets you take advantage of wherever Microsoft goes next or the underlying tools or models without rebuilding from scratch every time they ship something new. There's also a data sovereignty point that PE operating partners need to hear. When you run an AI agent with no harness, model API wired directly into your data, outputs going wherever, you're functionally letting a third party touch your operational data. Every query, every document, every context load, that's your business intelligence going through someone else's infrastructure. Acquires are starting to ask about AI architecture and technical due diligence. We do a lot of it. This is true. And a company with a clean harness has a defensible answer. A company with a naked model API wired to their production database, not so much. Two examples from actual portfolios, especially food and beverage manufacturer, every batch run, every QC flag, every shift change historically meant somebody reading a report, deciding what to escalate, routing the exception manually. A full-time job, just managing the queue. Then they built a system that monitors production line data, detects the anomaly, cross-references specific spec tolerances, and routes the exception to the right person with context, before it becomes a line stoppage or recall. They didn't call it a harness, they called it their exception management system. They built it because their margins demanded it. A home health operator, two of the most painful workflows in the sector, both already running without humans in the loop. Claims management, where agents monitor payer portals, catching the denial the moment it hits, pulling the patient record, identifying the fix, resubmitting within hours instead of days or even minutes. That's cash flow. That's days, sales outstanding. That's a metric the PE sponsor tracks weekly. Care staffing. A caregiver calls out, patients needs change. Once a certification lapses, the system reroutes automatically, surfaces the exception to the human that need human intervention, keeps the schedule intact. Neither company called what they built a harness, they just called it survival. Now we have a word for it. Something is happening right now that almost nobody in mid-market is paying attention to. Claude Code and OpenAI Codex started as coding tools. Your developers probably think of them that way still. A really powerful assistant that writes code, but that's not what they are anymore. They are full agenc platforms, model, harness, and now getting into cloud infrastructure where your agents can actually run, all bundled together, all under someone else's roof. Anthropic builds the model, Anthropic builds the harness around it. Now Anthropic is providing the cloud environment where the agent executes. Same story at OpenAI with Codex. They started at the model layer, moved up into the harness layer, and now they're moving down into the infrastructure layer, going vertical, fast, owning as much of the stack as possible. And you don't blame them given that they're startups in hyperscale mode. Microsoft is actually running the same play through Azure. Salesforce just announced Headless 360. It's the same play from the enterprise SaaS side. Jensen Wong and NVIDIA has been saying for two years that the application layer captures the most value. Everyone heard him. Everyone is now acting on it. Microsoft is running the same play through Azure, although they have a more diversified data platform play, not just the AI model harness. Salesforce just announced Edless 360. It's the same play from the enterprise SaaS side. Jensen Wong at NVIDIA has been saying for over two years that the application layer is the one in the five-layer cake that he says captures the most value. Everyone just heard him. Everyone is now acting on it. The mid-market risk. Your portcode developer got approved to use cloud code. What actually got approved without anyone realizing it was a dependency on an external regent runtime that now touches your production systems, your code, your data, your business logic, running an anthropic set on the mid-market risk. Your port code developer got approved to use cloud code, anthropics infrastructure. Not your Azure tenant, not your governed environment, theirs with their audit trail or no audit trail at all. That's not a criticism of Cloud Code or Codex. They're excellent tools. Your people should be using them. The question is where they run and who are. Owns the layer around them. When Anthropic changes their pricing and they have and they will, when OpenAI changes their terms and they have and they will, when every one of them gets acquired or better tool emerges, or your PE sponsor asks in due diligence who owns your AI infrastructure, what is your answer? If your agents are running in someone else's cloud inside inside of someone else's harness, they do, not you. When open AI changes their terms and they have and they will, when one of them or both get acquired, or a better tool emerges, or your PE sponsor asks in due diligence who owns your AI infrastructure, what is your answer? If your agents are running in someone else's cloud inside someone else's harness, they do, not you. This is where the two-door principle becomes a business decision, not a technical one. The winners in AI over the next three years won't be the ones who pick the right AI model. They'll be the ones who can change their mind most often. In 2026, in 2027, next year, every year as models keep improving, vendors keep shifting, and prices keep changing. Two-doors mean your data, your environment, and your architecture belongs to you. The models that run inside are interchangeable. For example, Microsoft updates Copilot, you slot it in. A better model comes along, you slot that in too. You have a workflow that needs several models involved for certain subcomponents of that workflow, you can do that as well. If a smaller specialized model does your invoice or order classification better and cheaper, you can swap it in or swap it out without rebuilding anything. One door is always left open. That's not by accident, that's good design philosophy. What we at Paragon have been building and calling it the reference architecture. Technically we call it the MIPRA, which stands for Managed Intelligence Provider Reference Architecture. I know, we need better names in AI. But this is what the AI industry is now calling the harness. It's just a buzzword that caught up to us. We didn't build it because of a trend, we build it because clients kept needing it. Five functions governance, routing, memory, integration, control. Four layers in an actual architecture. Layer one is your data store. This is your memory, your AI's filing cabinet, except that it's yours. It's organized and only you have the key. Not the vendor's cloud, your Azure environment, or AWS bedrock, governed inversion. That's your institutional memory, the thing that lets your AI get smarter over time because it remembers what happened last quarter or last month, not just what's in this conversation or chat. Azure Blob, Azure SQL, Azure Fabric, it's already there. The harness is what governs it and how AI talks to it. What's important about the operational data store is more the uses of the data rather than sources of the data. Unlike a data warehouse where the goal was to get every pipe flowing in and build these perfect representations of data, the operational data store is actually built one automation at a time, or what we call minimally viable operational data. Layer two is the analysis engine, and this is the part that handles governance. It's a gatekeeper that cleans and prepares your data before it even touches AI. The most skip layer in almost every mid-market deployment that I've seen. Everyone wants to jump into the fun AI model part, but 68% of failed projects never even assess their data before committing. Dirty data in, wrong answers out, no matter how smart the model is, the analysis engine is also your security layer. It sanitizes inputs. Nothing untrusted ever gets near the model. For MSP partners, this is where you plug in. You already govern the data access. This is a natural extension. Layer three, what we call the model engine or the model jukebox, handles routing. The ability to pick the right AI for the right job and switch when needed. Not every task needs a frontier model. Some tasks need Claude, some need codecs, some need an open source model, some need an SLM that you've tuned, some need a smaller specialized model running inside your own Azure environment, no external calls, no token costs. The Jukebox is model agnostic by design. This is where two-door principles live inside the architecture. You turn a dial, you don't rebuild a system. Cloud code slots in, codec slot in, they run inside your governed Azure environment, your tenant, your security posture, your auto trail, not anthropics, not open AIs. Full power of those tools within your own architecture underneath. There's also an availability concern. In the last two months, we've all seen these models go down randomly. That's unacceptable for a production environment. You also want to have some failover models just for redundancy and availability purposes. Layer four, the automation API, or what we call the optimization API, it gives you integration and control. The one control door that outputs leave through. We call it shipping the goodies. Your AI makes a decision or produces a result, and it goes exactly where you say it goes. It can go into your ERP, your SaaS, your legacy system, your BI dashboard, your email system, your workflow. Not everywhere at once. One gate, one audit trail. This is also what keeps your humans in the loop. High stakes outputs route to human for approval before anything happens, especially in compliance-driven environments. Remember that nearly 50% of the companies blind to their own agent traffic. This is the answer to that problem. Every output is tracked, every action is logged, you own the record. That's what we call MIPRA deployed inside your Azure or AWS environment. When we're done, you own it, swap the models in the jukebox without rebuilding your integrations, change vendors, bring in a different team, the architecture is yours. One more thing, model drift. As agents run longer, more complex tasks, hundreds of steps, maybe even millions, multi-day workflows, models can start to go sideways, following instructions less precisely and taking shortcuts. Without a harness, you don't even know what's happening. With a harness, you detect it and correct it before it even touches production. Building a harness requires skills that are generally hard to hire and retain, and most mid-market companies don't have them. A harness needs a data engineer running your pipelines, a harness engineer, a role that barely existed 18 months ago, sitting at the intersection of platform engineering, ML engineering, and security architecture, a security specialist who understands this specific context, and an integration engineer who connects outputs to your actual business systems. Four specialized roles for a company that just finished writing a job wreck for an AI engineer. Singular. That's a sobering list. BCG's 2026 research described it well. Most companies are stuck in deploy mode. Handing out AI2 licensing without changing the workflows. This is like giving a Formula One car to someone driving on city streets. The power is there, the infrastructure just can't support it. That's the gap, not the model. Everyone has a model now. The gap is the harness, and the harness requires a team and the skill profile that most mid-market companies can't realistically build internally fast enough on any reasonable timeline. For channel partners and MSP partners, this is your opening. The harness is the managed AI infrastructure service your clients need and cannot build themselves. At Paragon, this is what MIP delivers. It's our managed intelligence provider solution, the team and the architecture without the hiring cycle. It's a CTO-led harness team deployed inside your Azure or AWS environment. When the engagement is done, you own the architecture, you've built the institutional knowledge. And if you're you want to have your internal team take it from there, you totally can. So here are three questions that tell you immediately when you have a harness problem. One, where does your AI's data come from and who owns that environment? If the answer is the vendor's cloud or the AI platform cloud or I'm not sure, that's a flag. Two, if your AI vendor changed their pricing tomorrow or shut down or went offline, how long would it take you to rebuild or even notice? If the answer is a long time or we'd have to start over, that's a flag. Three, is there a human who reviews outputs before they trigger an action in a production system? The answer is not really, that's a flag. Three flags mean you're running on a model with no harness. Fine for single-player experimentation or hacking, not fine for anything you're counting on to run the business, and definitely not fine when you're moving towards multiplayer mode and agents, not humans, where they are the primary users of your system. At Paragon, we help companies go from three flags to zero using a crawl, walk, and run approach. Get the data foundation right, then the routing layer, then the agents. MIP is how we deliver all of it. Links are in the show notes if you want to talk through what this looks like for your company. The buzzword cycle, generative AI, prompt engineering, context engineering, agentic AI, harness engineering, each one real, each one eventually table stakes. The harness is the one that determines what the other ones actually work inside a real company at scale or not. $200 billion invested so far and growing exponentially, but only 6% meaningful impact. The money seems to be going in, the harness is why the results aren't coming out the other side. The food manufacturer whose quality exceptions route themselves didn't need a keynote to tell them it was a good idea. The healthcare operator whose claims management process runs without a human didn't need to read about it in an industry or VC newsletter. They built it because their operations demanded it. That's you. You've been building the harness without knowing what it's called. Now you have the vocabulary and the architecture, and now also the team available to scale what you've already started. Get the harness right and the model almost doesn't matter. Get it wrong, and the best AI in the world won't save your PLC from going kaput in production or your agents from running wild in the dark. Next episode, we're going headless. Salesforce just rebuilt their entire platform so agents can run it without a human ever touching a screen. Open AI dropped a model native harness. Uh Karpathi said it himself: apps shouldn't even exist. It should be just APIs and agents talking to them directly. The market caught up to that idea this week. That's episode two of the series, and we're calling it headless. Send this to one person, a Portco CEO who's frustrated at their AI experiments that haven't paid off, an operating partner who's trying to figure out why their companies keep hitting a wall. Or an MSP channel partner who knows that their clients need AI help but isn't really sure where to start. I hope you're outside on a walk right now. Go enjoy it. And I guarantee you the AI space will have changed by the time you get back. Cheers.