01
Conversational interfaces
Domain-tuned chat and voice systems with proper retrieval and a paper trail you can audit.
Applied AI, engineered for the
specifics of your business.
CustomLabs is a small studio of senior engineers who design, build, and ship production AI systems: agents, integrations, retrieval, document pipelines. Less talking. More working software.
- 01 Agents & automation
- 02 Retrieval & search
- 03 Document pipelines
- 04 Integrations
- 05 EvalsAn eval suite is a versioned set of test cases that measures whether outputs are good. & observabilityObservability captures traces of every prompt, retrieval, tool call, and response for debugging.
Services / 01
Four disciplines.
Four disciplines.
One outcome: it ships.
#
Every engagement is scoped to put a working system into your production environment: eval-tested, yours to own, shipped in weeks, not quarters.
01
AI Integrations
We embed models and agents into your existing stack, with retrieval underneath. Built on the boring infrastructure that production demands.
LLM opsVector DBWebhooksAuth & SSO
02
Custom Development
Bespoke applications and agents engineered for your specific operational reality. Production-grade and yours to own.
AgentsInternal toolsAPIsEval suites
03
Strategy & Architecture
Honest, technically literate roadmaps. We tell you what's worth building and where buying beats building.
AuditsArchitectureROI modellingVendor review
04
Readiness & Diligence
We assess your data and infrastructure, then the process that has to carry them. You get a written, defensible plan your board, your CTO, and your team can act on.
Data auditRisk registerPilot planKPI design
Proof / 02
Results from real engagements. #
Anonymised write-ups from shipped client work: the problem, what we built, and the measured outcome.
$1.4M Undisclosed re-platform cost surfaced
“The demo was real. The production system behind it wasn't. Two weeks saved us from finding that out after close.”Partner, Growth Equity · A growth-equity firm
12% → 3% Field hallucination rate
“The difference wasn't a better model. It was finally being able to measure when the model was wrong.”Head of Clinical Operations · A mid-market healthtech
-41% Cost per resolved request
“We stopped negotiating from weakness. Switching providers is now a config change, not a project.”VP of Engineering · A Series B fintech
Capabilities / 03
We ship the boring parts well. #
Demos are easy. Production is the work. We build the unglamorous parts: retrieval, guardrails, evals, observability. That's what keeps the impressive parts holding up six months after launch.
02
Agentic workflows
Tool-using agents that run real operations — book, route, file, decide — with deterministic fallbacks and human-in-the-loop where it matters.
03
Document & data extraction
Structured outputStructured output constrains a model's response to a defined schema instead of free-form prose. from invoices and contracts at production scale and cost.
04
Evaluation & observability
Eval suites and trace pipelines, so quality stops being a vibes check and starts being a number.
Process / 04
From first call
From first call
to handover.
#
Every engagement follows the same shape, sized to the problem. You'll always know what's happening, what's next, and what it costs.
- 01 ~half a day
Discovery
A short, structured working session. We map the problem, the data, and the constraints — and tell you honestly whether it's worth building at all.
- 02 ~3–5 days
Brief & estimate
You get a written brief: scope, architecture, risks, and an estimate you can hold us to. No surprises buried in week six.
- 03 ~2–6 weeks, shipping weekly
Build & ship
We build in your environment and demo working software every week. Systems go to production as early as sensibly possible, not at the end.
- 04 ~1 week
Handover
Documentation, runbooks, eval suites, and a team that understands what it now owns. Yours to run: no vendor kill-switch.
Studio / 05
A small studio of senior engineers.
A small studio of senior engineers.
The people you brief do the work. #
You've seen the demo that dazzled and then died in production. CustomLabs works the other way: senior engineers embed with your team and put a working, eval-tested AI system into your environment in weeks, not a slide deck, not a demo. The people you brief do the work.
Resources / 06
We think in production, and publish it. #
Working notes from real engagements, plus free tools to scope your own work before you commit budget.
What Actually Moved in the EU AI Act's 2026 Deadline Change
Regulation (EU) 2026/1744 pushed the AI Act's high-risk deadline to December 2027. What moved, what didn't, and why the old schedule still pays off.
Read →Prompt Injection Is a Data Problem: A Threat Model You Can Ship Against
Prompt injectionPrompt injection is untrusted input crafted to override a model's system prompt or task. can't be filtered away: the model can't reliably tell instructions from data. Here's the actual threat model and the controls that hold up.
Read →Why Your AI Agent Works in the Demo and Stalls in Production
An agent that nails the demo stalls in production because reliability compounds across steps. Here's the math, the real failure modes, and how to ship anyway.
Read →AI Cost Calculator
What AI actually costs to run in production — not the sticker price.
Model your cost →AI Readiness Scorecard
A fast, honest read on whether your data, infra, and process are ready to ship AI.
Take the scorecard →Architecture Picker
Which system shape you should actually build, from seven questions about the problem.
Pick your architecture → Guides / 07
Twelve guides. Read one front to back. #
Every one of these started as a client engagement. We wrote them down so the next team doesn't pay to learn the same thing twice.
The Applied AI Handbook
Six stages in the order a real project meets them. Start here if you're still deciding what to build.
AI Security Review
The questions InfoSec, privacy and procurement will ask. Answer them early and the review stops being the thing that kills your launch date.
The Agentic Delivery Playbook
How we run delivery with a fleet of coding agents, including the parts that went wrong.
The Eval Stack
How to know the system works before it ships, and which dashboard numbers are quietly lying to you.
The Agent Tool Interface
Agents fail at the interface far more often than at the model. This is how to design that interface.
Choosing an AI Delivery Partner
How to interrogate any AI delivery partner, us included. It ends with the cases where we're the wrong call.
The AI Cost Model
Where AI spend actually hides, and the 24 levers that move it. Read this before the invoice does the explaining for you.
The AI Governance Layer
The standing regime that has to hold a year after the security review passed. Prove who's accountable and how the system actually behaves.
The AI Release Path
You can't diff a model change like a code diff. This is how to ship one anyway: gated and reversible.
The Agent Adoption Playbook
The pilot worked. This is how the other 179 engineers actually start using it, and how you prove it happened.
MCP in Production
MCPMCP is an open standard for connecting LLM applications to tools and data sources. standardizes the wire format. Identity, the catalog, and the trust boundary are still yours to build, and this is how.
Context Engineering
A well-designed tool still fails if the window around it is unmanaged. What to budget, compact, isolate and log at every step of a long run.
Work / 08
We ship our own software, too. #
The studio funds and runs its own products. Same discipline we bring to client work, in production, under our own name.
Live Agent orchestration
CodeHerder
Command your fleet of coding agents.
A coordination platform for running many AI coding agents across machines and repos. It gives real-time visibility, collision-free tasking, and per-task cost tracking from one dashboard.
Coming soon Cost intelligence
CostMon
One trusted number for all your spend.
Aggregates billing from every cloud and AI provider into a single normalised view, for engineering and finance teams tired of a dozen billing consoles.
Live Developer directory
FreeTier
Ship on a budget.
A curated directory of 590+ cloud, SaaS, and developer tools with substantial free tiers. Compare what's genuinely free before committing to a paid plan.
Live API directory
greatapis
A field guide to the programmable web.
A curated directory of 1,500+ APIs across 51 categories, with auth type and HTTPS/CORS readiness flagged for each. Find and compare APIs fast.
Coming soon AI assistant
Beemy
The super-organized version of you.
A contextually aware AI personal assistant that triages email and Slack, then drafts replies in your voice. It automates recurring reports, with strict work and personal silos.
Live Managed hosting
CustomHosted
Hosting, run like a utility.
Managed hosting run like a utility. Static sites on a global CDN, or dedicated instances at fixed monthly pricing, with transparent pricing and no lock-in.
Coming soon Cloud cost automation
Reserver
Reserved Instances, managed properly.
Connects to your AWS accounts and matches Reserved Instances to running usage. It tells you exactly what to buy next, then turns that purchase into a button or a scheduled rule.
Coming soon Document extraction API
txtfetch
Any document in. Clean text out.
Turns PDFs, Office docs, HTML, email, and scans into clean plain text over one HTTP endpoint. Built for LLM ingestion and RAGRetrieval-Augmented Generation (RAG) retrieves relevant passages at query time and feeds them into an LLM's context. pipelines, with no parsers to maintain.
Coming soon Small-business admin
BizBinder
Your whole business, one binder.
Light job management and invoicing for people running a small business. Scheduled invoices, plus a client book that remembers everything, without the enterprise bloat.
Questions / 09
Before you write the brief.#
The questions we get asked most, answered plainly: no hedging, no marketing copy.
01 How do engagements usually start?
With a discovery session, not a sales call. We map the problem, the data, and the constraints, then send a written brief and estimate. If the scope is still fuzzy after that, we'll sometimes run a small paid discovery phase first rather than guess. See the Process page for the full shape of an engagement.
Link to this answer: How do engagements usually start?02 How much does this cost, and how long does it take?
It depends on scope, so we quote ranges, not a fixed price, once we understand the problem. Most first engagements ship a production slice within a few weeks. The budget ranges on the contact form are a reasonable starting point for sizing your brief.
Link to this answer: How much does this cost, and how long does it take?03 Who owns the code and the models?
You do. Everything we build is documented and observable. We hand it over at the end of the engagement. We're consultants, not vendors with a kill-switch.
Link to this answer: Who owns the code and the models?04 Do you use our data to train models?
No. Your data stays in your environment. We build on top of it, not off it.
Link to this answer: Do you use our data to train models? Contact / 10
Tell us what you're
Tell us what you're
actually trying to do.
#
The best briefs are short, specific, and a little too honest: the constraint, the deadline, the failure mode you're worried about. Tell us where your pilot is stuck and we'll write back with a real answer, not a sales sequence.
What happens next
- 01We read your brief
- 02You get a considered reply
- 03A short call if it's a fit
Every brief gets a reply.