Skip to content
galenry.
Solutions

AI Product Development

Most AI projects stall between the demo that impressed everyone and the version that has to survive real users, real data and a real bill. We build for the second one from the start.

How the engagement runs

Agreed before we start, not discovered later. You own everything we produce, whether or not you continue with us.

  1. 01

    Ground truth

    Eval set + baseline score

  2. 02

    Retrieval

    Working retrieval + accuracy figure

  3. 03

    Generation

    Answering system + escalation path

  4. 04

    Production

    Live system + runbook

Starts with
Discovery
You get
Running system + runbook
Shape
Fixed scope or retainer
When this applies

You are probably here because

If none of these sound familiar, this may not be the practice you need. Tell us what is actually happening.

  • 01

    A prototype that works in a demo but not on real data

  • 02

    No way to tell whether a change improved anything

  • 03

    Model spend that nobody can predict or cap

  • 04

    An AI feature nobody trusts enough to put in front of customers

What it covers

What a production AI system needs

Not all four land in every engagement. We scope to what the problem actually needs.

01

Retrieval that stays grounded

RAG over your own content with citations and a confidence threshold, so the system escalates instead of inventing an answer.

02

Agents with a boundary

Tool-calling loops with a spend ceiling, an allow-list, and human approval before anything irreversible.

03

Evaluation before deploy

A fixed eval set that every prompt or model change is scored against, so regressions are caught before a user finds them.

04

Model routing and fallback

The right model per task rather than one for everything, with a fallback path when a provider degrades.

Evidence

What we can point at

Including where we cannot. An unproven claim is worth less to you than a stated limit.

01

An AI assistant live for a client, checked before it speaks

Appooppanthaadi: Appu answers from the live catalogue, and a second pass verifies every figure against source data before a reply is shown

See it
LIMIT

One published client AI engagement, not a portfolio

Most of our production AI experience is in products we run ourselves. That is real experience, but it is not the same as a shelf of client references. Ask us what we have and have not done.

What you will know

Questions this answers

If you cannot answer these about your current system, that is usually where we start.

Will this hold up when a thousand people use it at once?

What does it cost per request, and what stops that running away?

How do we know a prompt change made things better, not worse?

What happens when the model is wrong?

The work

How the engagement runs

Indicative, not a template. The shape holds; the depth of each phase moves with the problem.

01

Ground truth

We collect the questions your system actually has to answer and turn them into a fixed evaluation set. Nothing gets built until we can measure it.

You get

Eval set + baseline score

02

Retrieval

Your content is chunked, embedded and indexed, then tuned until the right passage comes back for the questions that matter. Citations from day one.

You get

Working retrieval + accuracy figure

03

Generation

Prompting, tool access and the confidence threshold that decides when to escalate. Every change scored against the eval set before it lands.

You get

Answering system + escalation path

04

Production

Spend caps, rate limits, observability and the runbook your team uses when something looks wrong at 2am.

You get

Live system + runbook

Defaults

What we reach for first

Not the only things we work with: the ones we default to unless there is a reason not to.

Models

  • OpenAI
  • Anthropic
  • Open weights

Retrieval

  • pgvector
  • Pinecone
  • Hybrid search

Runtime

  • Next.js
  • Node
  • Streaming

Operations

  • Evals
  • Tracing
  • Spend caps
Start

Tell us what you’re trying to build

An idea, a stalled project, or a system that has outgrown its architecture. Send it over and we’ll tell you where we would start and whether we’re the right team for it.

Response time
Within one business day
First call
30 minutes, no deck

Prefer to write first? Send the brief and we’ll come back with questions before we come back with a proposal.