Prompt Engineering for the Whole Team

Aki Wijesundara

AI Advisor | Google AI Accelerator Alum

Manu Jayawardana

Exited AI Founder | Founder, TAI Labs

One Prompt Standard for the Whole Team — In Four Hours

Your team already has Claude access - but everyone prompts differently and gets inconsistent results. The same task takes five people five ways, and the good prompts live in one person's head. In four hours, on your team's own real work, that changes.

The math: teams that adopt AI properly run 25.1% faster on AI-suitable tasks - about 2.5 hours back per person, every week - which compounds into a 5.3× annualized ROI (Harvard Business School × BCG; U.S. BLS labor data). Break-even is ~28 minutes saved per person per week.

Proven on real teams. The same shape of session we ran for Modern Health, where Product, Ops, Design and Engineering each shipped a working build on their own data in a single day; MPB, 5× faster listing throughput; and Type B Digital, operator output lifted 2.5×.

One date, your whole team. Bring two people or twenty, no cap on numbers. Nobody experiments alone - everyone walks out on one setup and one shared way of working. Everyone walks out on one shared prompt standard and a library the whole team uses.

Want this shaped around your team's stack, headcount and dates? Email us and we'll scope a custom session. Email us or book a call here.

What you’ll learn

Every role leaves with prompts that actually save time and a shared house style for using AI well.

Turn a fuzzy request into a clear, repeatable prompt
Give AI the context, examples, and format it needs to get it right
Fix a weak answer by changing the prompt, not the tool

Build prompts for sales, ops, support, and leadership tasks
Save the ones that work so the team stops starting from scratch
Agree on a house style for how your team writes prompts

Cut a recurring task from an hour to minutes with one good prompt
Spot which of your tasks AI should and should not touch
Leave with three prompts each person will use on Monday

Workshop agenda

Before the day: Discovery call (1 hour, free)
We meet your team, find the tasks that eat the most time per role, and shape the day around your real work.
Hour 1: What a good prompt is made of
The handful of parts that separate a vague ask from one that gets the answer right the first time.
Hour 2: Prompt your own work
Each person takes a real task from their week and turns it into a prompt that works, with us in the room.
Hour 3: Build the team library
We collect the prompts that worked, refine them together, and set a shared style so they stay reusable.
Hour 4: Hard cases and edge work
We tackle the messy prompts that did not work yet, debug them live, and lock the patterns that fixed them.
After the day: Office hour
A follow-up session to refine prompts and add new ones as the team uses them in daily work.

Learn directly from Aki & Manu

Aki Wijesundara

Contact

AI Advisor | Educator | Google AI Accelerator Alum

Manu Jayawardana

Contact

AI Advisor | Founder, TAI Labs

See all products from TAI Labs

Who this workshop is for

Team leads who want consistent, high quality AI use across every role, not a few power users.
Operators rewriting the same prompt every day and getting different results each time.
Founders who want the whole team prompting well by the end of one day.

What's included

Live sessions

Learn directly from Aki Wijesundara & Manu Jayawardana in a real-time, interactive format.

One booking covers your whole team

No need to buy a seat per person. After you book, we schedule the session around your team's timeline, and you can bring as many people as you like, with no cap on team size.

Free 1-hour discovery call

We find the time-draining tasks per role before the day begins.

4 hours of hands-on teaching

Everyone prompts their own real work, coached live, not by watching demos.

A team prompt library

The prompts your people wrote, organised by role and ready to reuse.

A shared prompt standard

An agreed house style so prompts stay clear and consistent across the team.

Follow-up office hour

We refine and add prompts as the team puts them to work.

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Testimonials

Engineers improved the real systems they ship every day, and left with production-ready Claude integrations and a reusable AI playbook.
WireApps
AI-first engineering agency, 50+ engineers. Six-week cohort.
In a single on-site day, Product, Ops, Design and Engineering each shipped a working build on their own real data, using Claude Code and MCP.
Modern Health
Global mental health platform (Lyft, EA, Ancestry). On-site workshop.
A two-day cohort delivered 5x faster listing throughput and 14 production tools shipped on the team's own systems.
MPB
The world's largest used-camera marketplace. Two-day cohort.
Over a five-day cohort the team shipped 8 client-ready automations and lifted operator output 2.5x.
Type B Digital
Strategy consultancy. Five-day cohort.
I sent my team through this training for upskilling, and the results have been remarkable. Within weeks, they became much more efficient at building automations and deploying AI agents at work. This program bridges the gap between theory and practice and it’s had a real impact on our productivity.
Aamir Faaiz
CEO of Bayseian
The AI training approach is outstanding. Our team learned to build practical AI solutions that we could implement immediately in our educational platform. The hands-on methodology made complex AI concepts accessible to our entire development team.
Kavi T.
CEO of Tilli Kids / Stanford PhD