Business Owners
You sign off on the spend and want to see what your team will actually use on Monday morning. Day 1 gives you the language; Day 2 gives you a working system you can defend to the board.
The 2-Day Applied AI Workshop
From AI curiosity to a working system your team built — in two days.
Day 1 teaches your team how to work with AI — prompting, iterating, challenging outputs, picking the right tool. Day 2 turns that skill into a real MVP: a RAG system, a fine-tuned model, an agent, or a WhatsApp lead engine, built on your data.
Replies within working hours · No obligation · Scoping call is free
For business owners & team leads
Which track solves your business problem?
You don’t need to know what “RAG” means. You just need to know which of these sounds like your biggest pain — we’ll map it to the right build during a free scoping call.
“We get WhatsApp enquiries but no one has time to reply properly”
Maps toWhatsApp Lead Engine
“My staff keep asking the same internal questions over and over”
Maps toRAG Knowledge System
“AI writes our content but it sounds wrong for our market”
Maps toFine-Tuned Model
“Every month, one person merges numbers from three systems into a spreadsheet by hand”
Maps toAgentic Workflow
Who should attend
The room works best with these four seats filled
Mixed teams get the most out of the two days — the Day 1 prompts are accessible to anyone who writes, the Day 2 build needs engineers who can read code.
HR & L&D Leaders
You own the upskilling mandate and need training that produces visible, reportable outcomes — not another attendance certificate.
Operations & Sales Managers
You own the workflows being automated — especially WhatsApp. Your input during scoping decides whether the engine qualifies real leads or imaginary ones.
Team Leads & Managers
You coordinate the people who’ll use the AI day-to-day. The two days give you a shared vocabulary across your team and a working MVP that real workflows can move onto.
For business owners & operations managers
You don’t need to code. Day 1 is designed so that anyone who writes emails or manages processes can participate. Day 2 is where your technical team (or ours) builds the working system. You bring the business context; we bring the engineering.
Workshop architecture
Day 1 teaches you to work with AI.
Day 2 puts that skill into a real build.
The workshop is sequenced the way the work actually goes: learn the tool, then ship something with it. Day 1 is the same for everyone — Day 2 is your chosen capstone.
Day 01 · Foundations
How to work with AI
Prompting, iteration, and the AI-powered tools that have actually changed how work gets done.
D1-AMWorking with AI
D1-PMFrom prompt to working output
Output:shared prompting playbook · working AI-built app · evaluation checklist
Day 02 · Build
Ship the MVP
Pick one capstone track. Apply Day 1 skills to build a working prototype on your data.
CT1RAG Knowledge System
CT2Fine-Tuned Model
CT3Agentic Workflow
CT4WhatsApp Lead Engine
Output:working MVP your team built · production roadmap
2 days: foundations + MVP build4 capstone tracks to pick fromengineer-led, on your data
Day 1 · AI Foundations
The skills your team needs before any AI project is worth starting
The same Day 1 for every team, regardless of industry or capstone. No ML theory, no code-heavy prerequisites — just the prompting, iteration, and tool-selection skills that decide whether AI is useful or a waste of credits.
Working with AI
Day 1 · MorningThe problem
Your team has used ChatGPT a few times, maybe tried a copilot, and still treats AI like a clever search box. The result is shallow outputs, wasted credits, and a quiet suspicion that the tools aren’t as useful as the demos suggest.
What your team practices
A working shared vocabulary for what AI can and can’t do — and a hands-on tour of the tools that have changed the most: Lovable, Genspark, Cursor, and the prompting patterns that actually move the needle on output quality.
Topics covered
- What’s inside an LLM, in plain terms — capabilities, limits, failure modes
- Prompting guides: system prompts, few-shot, role assignment, chain-of-thought
- AI-powered tools landscape: when to use Lovable vs Genspark vs Cursor vs raw chat
- Hands-on tour: each participant drives the same task across multiple tools
You leave with
- Shared prompting playbook, written by your team
- A small app built end-to-end with an AI app-builder
- Working notes on which tool fits which kind of work
From prompt to working output
Day 1 · AfternoonThe problem
A single prompt is rarely the answer. The first response is a draft, not a deliverable — and most teams stop too early, ship hallucinations, or give up because the model "didn’t understand" what they wanted.
What your team practices
A repeatable loop for turning rough prompts into usable outputs: draft, critique, refine, verify. Participants push back on the model, demand sources, and learn to spot when an answer sounds confident but is wrong.
Topics covered
- Iterative prompting: generate → review → refine → repeat
- Challenging the model: asking for evidence, demanding alternatives, spotting hallucinations
- Structured output: schemas, formats, and forcing the model to be useful
- Evaluation: how you know it’s good enough to ship
You leave with
- A refined, multi-turn prompt that solves a real team problem
- Evaluation checklist your team can reuse on any AI output
- Before/after examples of the same prompt, iterated properly
Day 2 · Choose your capstone
Four MVPs. Pick the one that matches the outcome you want.
These are the four builds we’ve shipped the most often. Pick one during scoping — Day 2 is built around it. If none fit, the Custom Integration tier takes the same skill and applies it to whatever you need. Same principle as Day 1: the work has to ship. Every capstone ends Day 2 with a running MVP, code your team owns, and a roadmap to take it further.
CT1Day 2 · Build
RAG Knowledge System
Ground AI answers in your own documents — policies, SOPs, product catalogues — with a working retrieval pipeline that cites its sources.
When to pick it:Pick this track when your team keeps saying "the model doesn’t know our stuff" and your knowledge lives in PDFs, wikis, or shared drives.
What your team builds & walks away with
What your team builds: A retrieval pipeline over your real documents: chunking, embeddings, search across your documents, and a grounded answer layer that cites where each claim came from. By the end of Day 2, you have a system your team can demo internally the following Monday.
You leave with:
- Working RAG pipeline (code is yours to keep)
- Source-cited answers on your documents
- Failure-mode checklist for evaluating retrieval quality
CT2Day 2 · Build
Fine-Tuned Model
When prompting hits its ceiling and your outputs still look wrong. Train a small open-source model on your examples and measure whether it actually beats the baseline.
When to pick it:Pick this track when prompting gets you 80% there and the last 20% is the same correction on every output — tone, format, or domain language the base model keeps missing.
What your team builds & walks away with
What your team builds: A real fine-tuning run on a small open-source model: dataset preparation from your examples, training, and a side-by-side comparison so you can see the improvement against the prompted baseline. Measured, not vibes.
You leave with:
- Fine-tuned model on your task
- Side-by-side comparison so you can see the improvement
- Decision framework: when to prompt, when to RAG, when to tune
CT3Day 2 · Build
Agentic Workflow
Single prompts can’t run your processes. Real work is multi-step — look up, decide, act, check, escalate — and a working agent turns one prompt into a real automation.
When to pick it:Pick this track when a real workflow in your team needs more than one step and you want automation that knows when to stop and ask a human.
What your team builds & walks away with
What your team builds: A multi-step agent wired to the AI tools and patterns from Day 1: the assistant can use your tools, plan steps, and recover from errors, with human-in-the-loop checkpoints at the steps where mistakes are expensive.
You leave with:
- Working agent with tool use
- Guardrail and escalation patterns
- Architecture sketch for production hardening
CT4Day 2 · Build
WhatsApp Lead Engine
Your customers already live on WhatsApp, but enquiries arrive at all hours and qualification depends on whoever happens to be holding the phone. Leads leak every week.
When to pick it:Pick this track when inbound enquiries are coming through WhatsApp and the bottleneck is response speed or consistent qualification — not demand.
What your team builds & walks away with
What your team builds: An end-to-end lead qualification flow on WhatsApp: capture the enquiry, qualify it with an AI layer grounded in your offers, route hot leads to sales, and log everything for audit.
You leave with:
- Lead qualification flow, end to end
- Routing rules and sales handoff
- Audit trail you can show management
Engagement options
Straightforward pricing, scoped in writing
Three ways to work with Byte Forge. Every engagement is confirmed with a written quote after a scoping call — no surprises.
Open enrolment
Individual Seat
Join a scheduled public workshop cohort
RM 1,900/ pax
- Full 2-day workshop — Day 1 foundations + Day 2 capstone
- Workshop materials & starter code
- Certificate of completion
- 30-day post-workshop Q&A channel
Most engagements start here
In-house delivery
Team Workshop
Delivered at your premises or remote, scoped to your systems
RM 14,800/ team · up to 15 pax
- Everything in Individual Seat
- Pre-workshop scoping on your data & use cases
- Day 2 capstone chosen during scoping
- Post-workshop progress report for L&D
- Roadmap session with your in-house team
Workshop + build
Custom Integration
Workshop, then we build the real system with you
Customscoped quote
- Everything in Team Workshop
- Production RAG, fine-tuning, or agent build-out
- WhatsApp lead engine deployment
- Handover documentation & knowledge transfer
- Optional monthly retainer
// indicative pricing — final quote follows the scoping call, in writing
What does my team actually walk away with?
Every team leaves with three things: a shared prompting playbook written by your own people, a working MVP from your chosen Day 2 capstone — a RAG knowledge system, a fine-tuned model, an agentic workflow, or a WhatsApp lead engine — and a 30-day follow-up channel so the learning sticks after the room empties. Engineers take the build pattern back to production; non-technical participants take the prompting and evaluation habits back to their day-to-day work.
Before day one
How we scope your workshop
The two days land harder when the exercises are built from your reality. Here’s what happens between “yes” and the first morning.
Discovery call
Thirty minutes on WhatsApp or a call. We learn your team composition, your industry, and what’s driving the AI push — budget pressure, competition, or a board mandate.
Systems & data audit
A lightweight review of what you already have: document stores, CRM, WhatsApp Business setup, cloud accounts. We identify what’s usable on day one and what needs prep.
Use-case selection
Together we pick the capstone track — RAG, fine-tuning, agent, or WhatsApp lead engine — based on business value and achievability inside a two-day build.
Syllabus tailoring
We reweight the Day 1 prompts and exercises around your industry. Heavy on customer enquiries? WhatsApp-leaning examples throughout Day 1. Mostly internal docs? RAG-leaning.
Environment setup
One week before, every participant gets a setup checklist — accounts, tooling, and sample data prepared so the first morning starts with building, not installing.
Book the two days that will still be paying off next year
Message us your team size and your target month — we’ll reply with available dates and a scoped quote within two working days.
// replies within working hours · no obligation · scoping call is free