AI that works alongside your team, not instead of it.
I help companies add AI to their daily work: AI handles repetitive steps, while your people check the results and make the decisions.
Simple, practical, human-first
- 01
Map the workflow
Watch how the work really gets done and where time is lost.
- 02
Pick the right tasks
Hand AI the repetitive, rule-based steps. Keep people on decisions.
- 03
Design the handoff
Define what AI does, what a person checks, and how errors get caught.
- 04
Measure and refine
Track time saved and accuracy, then improve the setup with your team.
Teams buried in busywork
- 01
Report and data-heavy work
Teams that copy numbers between documents, templates, and spreadsheets.
- 02
Inbox-heavy teams
Customer emails and requests that pile up and eat the day.
- 03
Meeting-heavy teams
Notes, action items, and follow-ups that never quite get done.
Case studies
Lab report entry: from manual entry to human review
Lab reports had to be typed, value by value, into an Excel template to check contaminant levels. I implemented an LLM-based workflow to handle the data entry. Now I upload the report and check the resulting data and Excel file, correcting anything that needs attention.
- 01
AI fills it in
Upload the report in seconds. The LLM extracts the data and prepares the Excel template.
- 02
A person checks
I spend around 1–2 minutes checking the data and spreadsheet, correcting anything that needs attention.
- 03
Ready to use
The reviewed spreadsheet is ready for the next step: checking contaminant levels.
Timings are from my own workflow: uploading takes seconds, followed by around 1–2 minutes of review. AI processing time is additional. Results vary by document and setup. Every report is still checked by a person.
Customer inbox: first-draft replies, ready to review
Support teams answer the same questions all day. AI reads each incoming message, sorts it, and drafts a reply from the company’s own approved answers.
- 01
AI sorts and drafts
It tags each message and writes a reply using your approved answers.
- 02
A person reviews
Your team edits, approves, or takes over the tricky cases.
- 03
Customers get answers
Faster, consistent replies, with people on the conversations that matter.
A working prototype built with sample data, not yet used by a client.
Meetings: clear recaps and action items, ready to send
After every meeting, someone has to write the notes, list the tasks, and chase everyone. AI turns the meeting transcript into a summary and a task list with owners.
- 01
AI summarizes
It pulls out the decisions and drafts a task list with owners.
- 02
A person confirms
The organizer checks it for accuracy and anything sensitive.
- 03
The team acts
Everyone gets a clear recap and knows what happens next.
Shown as an example of how I’d approach this for your team.
A roleplay bot for a Discord community
I directed AI-assisted development to build a functional roleplay bot for a community server. AI wrote the code; I guided the work and shaped the experience.
A practical example of turning an idea into a working tool through AI-assisted development.
I started with a task
I wanted off my plate.
Manually entering lab-report data showed me how much of a working day can disappear into repetitive tasks. Building an AI workflow for it changed how I approached the work.
That’s what I want to help others explore: practical ways to use AI, grounded in an actual need. I bring hands-on experience directing AI tools and building workflows, with people checking the results and making the decisions.
Ways we can work together
- 01
AI workflow audit
Find the tasks in your team’s week that AI can take on safely.
- 02
AI workflow setup
Build and test a simple solution that fits how your team already works.
- 03
Team onboarding
Train your people to check, correct, and get the most from their new workflow.
A few things you might be wondering.
Do we need to know anything about AI?
No. We can start with the way you work today and a task you’d like to make easier. You don’t need a technical brief or a particular tool in mind.
Will AI send emails or make decisions on its own?
The proposed workflows centre on assistance: preparing data, highlighting information, and drafting responses. You or your team review and approve the work. Any automation beyond that would need to be explicitly agreed.
What about sensitive company information?
Before choosing a tool, we need to understand what information the workflow uses and your organisation’s requirements. Tool access, data handling, and what may be shared should be agreed before using company data.
Can we start with just one task?
Yes. One repetitive task is a useful place to start. It gives us something concrete to test, improve, and assess before considering a wider rollout.
Have a task that eats your team’s time?
Tell me about it and we’ll see if an AI workflow fits.
founder@joinhq.org →