AI Builders Guild
Shipping AI that holds up in production.
Demos are easy; production is not. Members here run models against real users, real costs and real failure modes: hallucinations in front of customers, bills that grow faster than revenue, and latency on a mobile network.
Open to every member. Join now and help shape what it builds next.
What we work on
Four problems define this community’s work right now. Every sprint, review and essay here comes back to one of them.
Retrieval and grounding
Getting a model to answer from your own documents and data, and to say so when it does not know.
Evaluation
Test sets, graders and regression checks so a prompt change never silently breaks what worked yesterday.
Cost and latency
Caching, smaller models and batching, so an AI feature pays for itself on a real network.
Agents and tool use
Letting models act through tools and APIs safely, with limits, logs and a human in the loop where it matters.
Questions we are working through
No one has settled these yet. They come up in every sprint, and members argue them out in essays and reviews.
- When is fine-tuning worth it, and when is better retrieval the real answer?
- How do you evaluate an assistant whose answers have no single right version?
- What should an agent never be allowed to do without a person approving it?
Our impact
- AI & ML essays published on TechOps News
- 2
- Systems in AI we have built and shipped
- 2
Shipped in AI
- SeraSupport Automation · Kenya · 2024
Conversational support across email, chat, and WhatsApp, trained on the client’s knowledge base.
80% tickets auto-resolved2M+ messages / month - RafikiConversational Banking · Nigeria · 2024
A WhatsApp-native banking assistant for balances, transfers, and support, grounded on core-banking data.
68% queries self-served900k active users
From the field
All AI & ML essays · 8 min of reading- Start with the decision, not the modelMost AI projects that stall were never wrong about the model. They were vague about the decision the model was meant to improve. How to start from the decision, with a worked example.
- Your first model should be boringStart with the simplest model that could work. It ships sooner, it is easier to explain, and it tells you whether anything fancier is worth it.
Your first build
New members pick one of these for their first month. Each is small enough to finish and real enough to show an employer or an investor.
A grounded document assistant
Answer questions from a set of PDFs, cite the passage each answer came from, and refuse when the answer is not there.
- RAG
- Embeddings
- Evaluation
An evaluation harness
Score an LLM feature against fifty real questions on every change, and fail the build when quality drops.
- Testing
- Python
- CI
A WhatsApp support bot
Handle the ten most common customer questions over WhatsApp and hand everything else to a person.
- LLMs
- Webhooks
- Systems
Words you will hear
New here? These come up in your first week. Plain meanings, no jargon.
- RAG
- Retrieval-augmented generation: looking up relevant documents first, then having the model answer from them.
- Hallucination
- A confident answer the model made up. The main thing evaluation exists to catch.
- Context window
- How much text a model can read at once, including your instructions and the documents you pass in.
- Eval
- A repeatable test of model quality: fixed inputs, expected behaviour and a score.
Who you will meet
- ML and backend engineers shipping AI features
- Data scientists moving into LLM work
- Founders building AI systems
- Researchers who want their work used
How the community runs
- Every week
Build sprint
Bring a real problem from your work in the sector. Leave with progress, reviewed by people who have shipped the same thing.
- Every week
Office hours
Drop in with a model that will not converge, a regulator question or a hiring decision. Practitioners answer.
- Every month
Demo day
Members show working systems to the community, mentors and invited investors. Demos, not decks.
The team behind it
Lead the AI Builders Guild
We are looking for experienced practitioners to lead this community: host one session a month, review members’ work and shape what it builds next.
Tell us about your workJoin the AI Builders Guild
One payment of $15 makes you a member for life: every community, its sprints, reviews and events. No subscription.