ProductiOS · Android · Web
Daily skill game
One codebase to iOS, Android and web. Both stores, server-side daily draw, scheduled push.
Consumer apps
AI product development and engineering
Moher designs, builds and ships AI products for companies that need them in production. Agents, LLM applications, RAG and evals, in your repository from the first commit.
- 01 Scope and price in one week
- 02 Production by week three
- 03 You own the code and the cloud
- 04 Senior engineers only
1// tools/refund.ts
2
3export const refund = tool({
4 description: "Refund an order after a policy check",
5 input: z.object({ orderId: z.string(), amount: z.number() }),
6 approval: "required_over_100",
7 run: async ({ orderId, amount }, ctx) => {
8 const order = await ctx.db.order(orderId);
9 assertPolicy(order, amount);
10 return ctx.payments.refund(order, amount);
11 },
12});
PR #48ready to merge
Add refund tool with approval gate
- Typecheck and lintpassed
- Eval suite214 of 214
- Cost per request$0.0031
- Prompt injection setpassed
Tracerun 7f3a
- retrieve_policy118 ms
- get_order64 ms
- draft_reply842 ms
- human_approvalrequired
Models and platforms we ship on
- Anthropic
- OpenAI
- Google Gemini
- AWS Bedrock
- Vercel
- Supabase
- Postgres
- Expo
Engineering services
What we build
Nine ways in, one standard. Every engagement ships running software with evals, cost tracking and traces wired before the second feature.
AI product engineering
Full-stack AI products built, evaluated and shipped to production
Learn more →AI agents
Tool-calling agents with approval gates and full audit trails
Learn more →LLM applications
Copilots and LLM features with model routing and cost control
RAG and AI search
Retrieval and AI search with citations and permission checks
Evals and reliability
Eval harnesses, red teaming and guardrails for LLM systems
AI integration
AI wired into your CRM, ERP and back office
Mobile AI apps
Native iOS and Android AI apps shipped through both stores
AI data infrastructure
Data pipelines, fine-tuning datasets and model serving infrastructure
Already have a team, or need one
AI engineering team, retained
Fractional AI CTO and a retained engineering team. Senior engineers who join your standups, own a roadmap and stay accountable to the same eval and cost numbers.
How a build runs
From scope to production in three weeks
One thin slice goes live end to end first, with auth, logging, evals and cost tracking. Everything after that widens a road that already carries traffic.
- Week 1
Scope
One working session, then a scope document: what ships, what does not, the architecture, the data it needs, how it will be evaluated, what it costs. No sixty-page discovery invoice.
- + Scope doc
- + Architecture and data map
- + Fixed price or rate plus ceiling
- Week 3
Thin slice
One real path end to end: auth, model calls, tracing, cost tracking and the deploy pipeline. Everything after is widening a road that already exists.
- + Live URL
- + CI on push
- + Cost per request model
- Weekly
Widen
Features land behind evals and tracing. A change that regresses accuracy, latency or cost does not merge.
- + Eval suite
- + Traces and dashboards
- + Weekly one-page readout
- Any time
Hand over
Runbooks, architecture notes, a working local environment, the eval suite and a walkthrough with whoever inherits it. The exit is written into the agreement on day one.
- + Runbooks
- + Local env
- + Named owner
Engineering standard
Every build ships with
Most AI projects do not fail on the idea. They fail on retrieval quality, evaluation, cost per request and who carries the pager. We put that layer in first.
How we handle data and access →Your repository from commit one
Code, cloud accounts and model keys live in your org. Nothing sits behind our login.
Typed end to end
TypeScript or typed Python, schema-validated model output, no stringly typed glue.
Eval suite in CI
Every pull request runs the regression set. A change that drops a score does not merge.
Cost per request on every PR
Token spend and latency budgets are tracked like test coverage.
Traces and observability
Every model call, tool call and retrieval is logged and replayable.
Security boundaries
Scoped credentials, PII handling, prompt injection tests, human gates on irreversible actions.
Runbooks and a local environment
A new engineer can run it on day one. Handover is a walkthrough, not a zip file.
The exit in the contract
Keep us running it or take it in house. Both are written in from day one.
51
production repositories
5,844
commits shipped
2
app stores we publish to
12
industries built for
Counted from our own repositories, August 2026.
Selected work
Shipped and running
Client names stay under NDA. The shapes, stacks and outcomes do not.
PlatformInfrastructure
Attribution spine
First-party click tracking, offer routing, s2s postbacks. Built once, inherited by every surface.
Media & publishing
ProductiOS · Android
Hardware companion
Native mobile for a physical-product use case. Offline-first data model, both stores.
Consumer apps
Engagement models
Three ways to work with us
01
Build
Fixed scope. We design, build and ship it; you own the output outright and run it yourself.
You know what you need built.
02
Operate
Retained. We run and stay on call for what we built, reported against eval, uptime and cost numbers.
You need it built and kept running.
03
Partner
Equity or revenue share on a product we build with you. Selective, and we say no often.
You want an engineering partner, not a vendor.
Frequently asked questions
Something else? Email t@moher.ai and an engineer will answer it.
What does Moher do?
Moher is an AI development and engineering company. We design, build and ship AI products for other companies: agents, LLM applications, RAG and search, eval harnesses, integrations into existing systems, and native mobile apps. The deliverable is running software in your repository.
How is Moher different from other AI development companies?
We put the boring parts first. Every build ships with an eval harness in CI, a cost-per-request model, traces, and runbooks, and it runs in your cloud accounts from the first commit. Most AI projects fail on retrieval, evaluation and cost, not on the idea. That layer is our daily work.
How fast can you start?
Scope in one week. A thin slice of the product is usually live in production by week three, then we widen it in weekly increments measured against the eval suite.
Who owns the code?
You do, from the first commit. Repositories, cloud accounts, model provider keys and domains are in your name. You could end the engagement on a Friday and ship on Monday.
Which models and platforms do you build on?
Claude, GPT, Gemini and open-weight models, chosen per task on cost, latency and eval results. Typical stacks are TypeScript or Python, Postgres with pgvector, Vercel or AWS, and Expo for native mobile.
What does an AI development project cost?
A scoped first build typically runs $40,000 to $150,000 depending on integrations, data work and how many surfaces ship. Retained engineering is a monthly rate. You get a fixed price or a rate with a ceiling in the scope document before any work starts.
Do you build mobile apps?
Yes. Native iOS and Android through both app stores, sharing a codebase with web where the product allows it.
Do you compete with your clients?
No. We build for your market, never in it, and we decline engagements that would place us opposite a client in their own category.
Tell us what you need built
Four quick questions and an email. An engineer reads every brief and replies within one business day with next steps, and a written scope follows within a week.
- Written scope and price within a week
- Production deploy by week three
- Your repo and cloud from the first commit
- Senior engineers only, no account managers
Start a project
Step 1 of 5
Got it. An engineer is reading your brief.
You will hear from us within one business day, usually sooner. If it is urgent, email t@moher.ai.