Stay Updated

New tutorials, tips, and Atlassian insights. No spam, unsubscribe anytime.

L
LeanZero

An approachable expert helping teams simplify their Atlassian ecosystems. Sharing knowledge and building community, one solution at a time.

Services

  • Atlassian Migrations
  • AI Implementation Advisory
  • Forge App Development

Company

  • Blog
  • Contact

Community

  • Join Discord
  • Support this site

© 2026 LeanZero. All rights reserved.

Privacy Policy|Terms of Service|Service Level Agreement|Trust Center
  1. Home
  2. Services
  3. Ai Advisory

AI Implementation Advisory

Practical guidance for teams looking to use AI effectively. I focus on implementation that works, not hype or vendor marketing.

  • Local and cloud solutions that respect your data privacy
  • Economical models that don't require enterprise budgets
  • Practical workflows that augment your team, not replace them

The Noise vs. The Reality

You can't open a news source without someone declaring AI either the future of everything or the downfall of humanity. The media has made a complete mess of understanding what AI actually is and what it can practically do for teams.

Meanwhile, actual teams are trying to figure out how to use these tools without wasting money on expensive subscriptions, compromising their data security, or getting caught in vendor lock-in.

The problem most teams face:

  • Overwhelming options with unclear differentiation
  • Vendor-driven narratives that serve their business, not yours
  • Fear of data leaving your infrastructure
  • Skepticism from team members who've been burned by hype

What I actually deliver:

  • Clear understanding

    What these tools are, what they aren't, and where they fit in your workflow

  • Practical implementation

    How to set up models that work for your specific needs and constraints

  • Cost-effective approaches

    Options that don't require enterprise licensing or expensive cloud credits

  • Data sovereignty awareness

    Understanding when local models make sense versus when cloud options are appropriate

A Different Approach to AI Models

I don't push the latest marketing hype. I focus on models that are practical, economical, and can be deployed in ways that make sense for your team.

Local Deployment

Run models on your own infrastructure. This approach gives you complete control over your data and eliminates ongoing API costs.

  • Data never leaves your infrastructure
  • No per-token costs or API limits
  • Works offline for air-gapped environments
  • Investment in hardware vs. ongoing subscription

Cloud Solutions

When appropriate, cloud options provide access to more powerful models without the need for specialized hardware investment.

  • Access to larger, more capable models
  • No hardware requirements or maintenance
  • Scale as needed without capacity planning
  • Transparent cost structures when understood correctly

The right choice depends on your specific requirements, regulatory environment, and budget. I help you understand both options and make an informed decision that aligns with your constraints.

LM Studio & Model Context Protocol

LM Studio has become my primary tool for working with local models. It provides a straightforward interface for downloading, managing, and running a wide variety of open-source models without requiring extensive ML expertise.

More importantly, I'm an advocate for the Model Context Protocol (MCP) - a standard that enables AI assistants to connect with external tools, APIs, and data sources in a structured way. This moves beyond simple chat interfaces and enables actual workflow automation.

Practical MCP Example

I've built and open-sourced an MCP Document Processor that helps AI agents work with document formats more effectively. It extracts text, recognizes structure, pulls metadata, and can create documents with styling options.

View the source code

What This Means For You

  • Practical implementation

    I use these tools daily. I'm not reciting documentation - I'm showing you what actually works.

  • Custom integrations

    Understanding MCP means I can help you connect AI to your existing tools and workflows.

  • Local-first approach

    I can show you how to achieve significant value without sending your data to third-party services.

  • Real experience

    I've built tools, debugged issues, and found workarounds. That's different from reading a blog post.

Augmentation, Not Replacement

There's a narrative that AI will replace developers or make teams obsolete. I take a different view. AI is a tool that, when used properly, augments human capability.

Better Articulation

Use AI to clarify your thoughts, structure arguments, and communicate more effectively. Your expertise remains - the tool helps you express it better.

Result Orientation

Focus AI on specific outcomes. Define the problem clearly, use the tool to explore solutions, and apply your judgment to select the best path.

Human Judgment

AI generates options. You decide. Understanding the tool's limitations keeps you in control and prevents blind reliance on outputs.

What This Looks Like In Practice

When I use AI, I'm not having it write my code or compose my emails. That's lazy and produces mediocre results. Instead, I use it to:

  • Explore architectural options and identify trade-offs
  • Generate boilerplate code that I then review and adapt
  • Brainstorm potential solutions to complex problems
  • Get unstuck when I'm blocked on a particular implementation
  • Structure documentation and technical writing

The output always passes through my judgment. I understand what it's doing, why it's doing it, and whether it makes sense for my specific context.

This Is For Teams Who:

Are skeptical but curious

You've heard the hype and you're not buying it, but you suspect there might be something useful underneath.

Value data privacy

You work in industries or environments where sending proprietary data to third-party services is not acceptable.

Need practical outcomes

You're not interested in theoretical discussions. You want to know how to actually use these tools to get work done.

Have constrained budgets

Enterprise licensing fees and expensive cloud credits aren't in your budget. You need options that make financial sense.

Want to build capability

You're not looking for a one-off fix. You want to understand how to integrate AI into your team's workflow sustainably.

What I Don't Promise

✕

That your team will become AI experts

I provide the brain dump and guidance. Whether your team runs with it is up to them.

✕

Instant productivity gains

Learning curves exist. Adoption takes time. I don't sell magic pixie dust.

✕

One-size-fits-all solutions

Every team is different. What works for one might not work for another. I help you find what works for you.

✕

That AI will solve all your problems

AI is a tool. It can help with some things, make others worse, and has no bearing on most issues.

What I Actually Promise

An effective brain dump of what I've learned through practical implementation. Clear explanations of options, honest assessment of trade-offs, and guidance that's grounded in real experience rather than marketing materials.

Whether that's valuable to you is your call. I don't push sales - I have enough work from referrals and ongoing engagements. I do this because I believe teams need better guidance than what the industry currently provides.

What We'll Cover

Every engagement is different, but here's what typically gets addressed as part of the advisory process.

Assessment & Strategy

  • Evaluating your current workflow and identifying opportunities
  • Understanding your data privacy and compliance requirements
  • Assessing hardware capabilities and budget constraints
  • Creating a roadmap that fits your pace and priorities

Model Selection & Setup

  • Comparing models based on your specific use cases
  • Setting up LM Studio and configuring model downloads
  • Understanding model sizes, quantization, and trade-offs
  • Benchmarking performance on your hardware

Practical Implementation

  • Setting up development environments with AI tooling
  • Integrating with existing tools via MCP
  • Building custom prompts for specific workflows
  • Creating reusable templates and automation patterns

Team Adoption

  • Addressing skepticism and building trust
  • Training team members on effective prompting
  • Establishing guidelines and best practices
  • Creating a culture of responsible AI use

Investment

Let's have a conversation. I don't have fixed packages because every situation is different.

What Affects Engagement Scope

  • Team size and number of stakeholders involved
  • Technical complexity of your environment
  • Whether you need ongoing support or a one-time setup
  • How much implementation vs. how much advisory you need

Typical Engagement Patterns

One-Day Intensive

Deep dive into your situation, hands-on setup of local models, practical demonstrations, and documentation of next steps. Good for teams ready to move quickly.

Multi-Week Engagement

Initial assessment followed by weekly check-ins. Implementation support, troubleshooting, and iterative refinement. Good for teams that want sustained guidance through the adoption process.

Monthly Advisory

Ongoing strategic guidance for teams that are already using AI but want to optimize their approach. Focus on advanced patterns and emerging opportunities.

I'm not trying to upsell you or create dependency. My goal is to get you to a point where you're self-sufficient. If you need me again later, great. If not, that's also a successful outcome.

The best way to figure out what makes sense is to have a conversation. No pressure, no sales tactics. Just a discussion about your situation and whether I can help.

Atlassian & AI Expertise, Made Personal

Whether it's migrations, Forge app development, or practical AI guidance, I'm here to help. The best way to start is by asking in community.

Start a ConversationJoin the Community

Or check out my open-source MCP Document Processor to see what I've built.