Skip to content

AI development services

AI development, from strategy to MLOps. We build agents, models and the integrations that put them to work in your company.

AI development, from strategy to MLOps. We build agents, models and the integrations that put them to work in your company.

Consulting.

Where AI pays off in your company, what it needs from your data, and what to build first.

  • A ranked list of use cases
  • A data-readiness check
  • A first build scoped
Example ranking · an illustration of the format, not a client's use cases
  1. 1 Support answers drafted from your help centre Clear documents, high volume
  2. 2 Sales call notes written into your CRM Repetitive work, easy to check
  3. 3 A demand forecast for your busiest products The data exists, the value is clear

AI development services · The AI pipeline · 1 of 6

Consulting. Where AI pays off in your company, and what to build first.

What it is

AI consulting decides where AI is worth building in your company before anything is built. We look at your processes and your data, rank the use cases by what each can return and what it needs, and scope the first build so its result can be measured.

What we do

  • Rank the use cases
  • Check what they need from your data
  • Scope a first build

How we do it

  1. InterviewThe people who know the work, and the data behind it.
  2. RankEach use case by what it can return and what it needs.
  3. Check the dataWhether it exists, is clean and may be used.
  4. ScopeThe first build, and how its result will be measured.

What you get

  • A ranked use-case list
  • A data-readiness note
  • A scoped first project

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

AI development services · The AI pipeline · 2 of 6

Generative AI. Assistants and AI features built on your documents and your product.

What it is

Generative AI is software that writes, answers and summarises from your own material. We build assistants over your documents that cite their sources, and AI features inside your product, each tested against examples you approve before it reaches your users.

What we do

  • An assistant over your documents
  • Answers that cite your sources
  • AI features in your product

How we do it

  1. Gather the sourcesThe documents and data the assistant may read.
  2. Build and groundAnswers that cite the passage they come from.
  3. EvaluateReal questions from your team, scored before release.
  4. Release in stagesFirst to a small group, then to everyone.

What you get

  • The assistant and its code in your repository
  • An evaluation set and its scores
  • A runbook for your team

Stack and tools

  • Model APIs
  • Embeddings
  • Vector search
  • Evaluation sets

Proof

Read the story: Kuest AI, an AI tutor that teaches step by step

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

AI development services · The AI pipeline · 3 of 6

Agents. Software that takes actions in your systems, inside the limits you set.

What it is

An agent is software that takes actions in your systems: it reads a task, calls the tools it is allowed to call and records every step. We build each agent inside a harness of permissions and limits that sit outside the model, with a person approving the steps you choose, so the agent can only do what you have set.

What we do

  • Map the task: its steps, the systems it touches, and where a person approves.
  • Build the tools the agent may call, each with its own permission.
  • Set the limits on data, spend and scope, enforced outside the model.
  • Log every step, so your team can replay what the agent did and why.

How we do it

  1. Scope the taskThe steps, the systems and the decisions a person keeps.
  2. Build the toolsEach tool the agent may call, with its own permission.
  3. EvaluateAn evaluation set from your own cases, scored before release.
  4. Release in stagesFirst a person approves every action, then only the exceptions.
  5. Watch and improveTraces, alerts and a regular review of what it got wrong.

What you get

  • The agent and its tools in your repository
  • A permission map
  • An evaluation set and its scores
  • A trace of every run
  • A runbook for your team

Stack and tools

  • Model APIs
  • Tool calling
  • Sandboxes
  • Tracing
  • Evaluation sets

Proof

Read the story: Jeriko, a team of personal AI agents

Related

Agents for your company. Tell us the task and the systems it touches. We reply within one business day.

AI development services · The AI pipeline · 4 of 6

Document and vision AI. Reading documents, images and video with AI.

What it is

Document and vision AI reads what your company receives as files: forms, invoices, contracts, scanned pages, images and video. We build systems that pull out the data you need, turn scans into text you can search, sort images by what is in them and find the moments in a video you name, each checked against examples you approve.

What we do

  • Pull data from forms, invoices and contracts
  • Turn scanned pages into text you can search
  • Sort images and find what is in them
  • Search video for the moments you name

How we do it

  1. Collect examplesReal documents, images or video from your work.
  2. Build the readerA model that reads them, checked against your examples.
  3. Review the doubtfulA person checks what the model is unsure of.
  4. ConnectThe results flow into the system that needs them.

Questions

Can a person check the results?

Yes. Anything the model is unsure of goes to a review queue, and a person decides before it moves on.

What kinds of documents can you read?

Forms, invoices, contracts, scanned pages, images and video. We test on examples of yours before we build.

What you get

  • The extraction pipeline in your repository
  • An evaluation set and its scores
  • A review queue for your team

Stack and tools

  • Document parsing
  • Optical character recognition
  • Vision models
  • Evaluation sets

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

AI development services · The AI pipeline · 5 of 6

Integration. AI connected to the systems you already run.

What it is

Integration puts AI to work inside the systems you already run. We connect a model to your applications, your data and your single sign-on, choose the model that fits each task, and measure its cost and response time so the feature stays affordable as use grows.

What we do

  • The model that fits the task
  • Single sign-on
  • Cost and response time measured

How we do it

  1. Map the systemsWhere the feature lives, and what it reads and writes.
  2. Choose the modelScored on your task for quality, cost and response time.
  3. ConnectThrough your APIs and your single sign-on.
  4. MeasureCost and response time watched once it is live.

What you get

  • The integration code in your repository
  • A cost and response-time report
  • A runbook for your team

Stack and tools

  • Model APIs
  • API gateways
  • Single sign-on
  • Monitoring

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

AI development services · The AI pipeline · 6 of 6

MLOps. Models released, measured and kept working.

What it is

MLOps keeps models working after launch. We build the pipelines that train, evaluate and release a model, a registry that versions each one, monitoring that watches it in production and retraining when the data moves, with every release reversible.

What we do

  • Pipelines
  • A model registry
  • Monitoring
  • Retraining
  • Versioned releases with rollback
  • Model cards

How we do it

  1. Build the pipelineTraining, evaluation and release, written as code.
  2. Register each modelEvery version kept with its data and its scores.
  3. Release with a rollbackA new version replaces the old only once it passes.
  4. MonitorQuality and drift watched in production.
  5. RetrainWhen the data moves, through the same gates as before.

Questions

Can we roll back a model?

Yes. Every release is versioned, so the previous model can return when a new one does not hold up.

How do you know a model has drifted?

Monitoring compares live inputs and results with the test set, and alerts your team when they move apart.

What you get

  • The pipelines in your repository
  • A model registry
  • Monitoring and alerts
  • A model card for each release

Stack and tools

  • Pipeline orchestration
  • Model registries
  • Experiment tracking
  • Monitoring
  • Evaluation sets

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

Inside an agent: the harness. The model is one part; the harness around it decides what the agent may do.

AI development services · Inside an agent: the harness

The agent harness. Everything around the model that decides what an agent may do.

What it is

An agent harness is the software around a model that decides what the agent may do: the tools it may call, the permissions on each, the context it may read, where it runs, the steps a person approves and the log of every step. We build the harness first and the agent inside it, so its limits hold whatever the model answers.

What we do

  • Name every tool the agent may call
  • Set each tool's permissions outside the model
  • Run the agent in a sandbox, apart from your systems
  • Put a person before the steps you choose
  • Write every step to a log your team can replay

What you get

  • The harness and its tools in your repository
  • A permission map
  • A replayable trace of every run

Stack and tools

  • Tool calling
  • Sandboxes
  • Policy enforcement
  • Tracing

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

Models. Four ways to put a model to work, and what each asks of you.

Use a hosted model A provider's model, used through its API.
What you need
An account with the provider, and terms that fit your data.
What you own
Your prompts, your evaluation set and the code around the model.
When it fits
When a general model already does the task well enough.
Run an open model Open weights on infrastructure you control.
What you need
Servers or a cloud account with suitable hardware.
What you own
The deployment, and where your data goes.
When it fits
When your data must stay in your own environment.
Fine-tune a model A base model trained further on your examples.
What you need
Good examples of the task, and a way to score them.
What you own
The tuned weights, where the base model's licence allows.
When it fits
When prompting alone does not reach your quality bar.
Train your own A model trained on your data for one task, such as a forecast or a classifier.
What you need
Enough labelled data for the task.
What you own
The model and its training code.
When it fits
When the task is narrow and the data is yours.

AI development services · Models · 1 of 4

Hosted models. A provider's model, used through its API, with your data's terms checked.

What it is

A hosted model is a provider's model you use through its API, with no servers of your own to run. We choose between providers by scoring them on your own evaluation set, check each provider's terms against your data, and measure the cost and response time of every call.

What we do

  • Choose by your evaluation set
  • Check the provider's terms
  • Measure cost and response time

How we do it

  1. Build the evaluation setReal examples of the task, scored the same way.
  2. Compare providersEach model scored on your set.
  3. Check the termsWhere your data goes, and whether it may be kept.
  4. MeasureCost and response time at your volume.

What you get

  • A comparison of providers on your evaluation set
  • The integration code in your repository

Stack and tools

  • Model APIs
  • Evaluation sets
  • Prompt management
  • Usage monitoring

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

AI development services · Models · 2 of 4

Open models. Open weights, run where your data already lives.

What it is

An open model is a model whose weights you run yourself, on servers or a cloud account you control. It suits work whose data must stay in your environment. We choose the model by your evaluation set, deploy it on your infrastructure and measure its quality, cost and speed.

What we do

  • Choose an open model by your evaluation set
  • Deploy it on infrastructure you control
  • Measure its quality, cost and speed

How we do it

  1. ShortlistOpen models whose licence fits your use.
  2. ScoreEach on your evaluation set.
  3. DeployOn your servers or your cloud account.
  4. MeasureQuality, cost and response time under load.

What you get

  • The deployment as code in your repository
  • An evaluation of the models you considered

Stack and tools

  • Model serving
  • GPU infrastructure
  • Evaluation sets
  • Monitoring

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

AI development services · Models · 3 of 4

Fine-tuning. A base model trained further on examples of your task.

What it is

Fine-tuning trains a base model further on examples of your task, so it answers in your format and your domain. It is worth it when prompting alone does not reach your quality bar. We prepare the examples, train, and score the tuned model against the base model on your evaluation set.

What we do

  • Prepare examples of your task
  • Train the base model further
  • Score it against the base model

How we do it

  1. Collect examplesGood examples of the task, checked by your team.
  2. TrainThe base model trained further on them.
  3. ScoreThe tuned and the base model compared on your evaluation set.
  4. DeployOnly if the tuned model does better.

What you get

  • The tuned weights, in your name where the base model's licence allows

Stack and tools

  • Training frameworks
  • GPU infrastructure
  • Evaluation sets
  • Model registries

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

AI development services · Models · 4 of 4

Machine learning. A model trained on your data for one task: a forecast, a ranking, a classifier.

What it is

Machine learning here means a model trained on your data for one narrow task: a forecast, a ranking or a classifier. We prepare the data, train and evaluate the model, and deploy it with the pipelines that keep it current as your data changes.

What we do

  • Prepare your data for one task
  • Train and evaluate the model
  • Deploy it with pipelines that keep it current

How we do it

  1. Frame the taskWhat the model predicts, and how it will be judged.
  2. Prepare the dataLabelled, cleaned and split for training and testing.
  3. Train and evaluateCandidates compared on data they have not seen.
  4. DeployWith the pipeline that retrains it as your data changes.

What you get

  • The model and its training code
  • An evaluation report
  • A retraining pipeline

Stack and tools

  • Training frameworks
  • Feature stores
  • Experiment tracking
  • Model registries

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

Evaluation: release gates. Every model passes the same checks before it reaches your users.

Release gates
GateWhat we measureHowThresholdRunsMethod
Task qualityWhat we measureAnswers correct on your test setHowScored against a labelled set you approveThresholdSet with youRunsEvery build
GroundingWhat we measureEvery answer cites your sourcesHowEach sentence traced to a retrieved passageThresholdSet with youRunsEvery build
SafetyWhat we measureHarmful and off-policy requests refusedHowRed-team prompts and jailbreak suitesThresholdSet with youRunsBefore release
PrivacyWhat we measureNo personal data leaves its boundaryHowRedaction tested on seeded recordsThresholdSet with youRunsEvery build
LatencyWhat we measureFast enough for the taskHowResponse time measured under loadThresholdSet with youRunsBefore release
CostWhat we measureAffordable at your volumeHowCost modelled at your expected volumeThresholdSet with youRunsBefore release
DriftWhat we measureStill right next monthHowLive inputs compared with the test setThresholdAlert level set with youRunsIn production

AI development services · Evaluation

Evaluation. Every model passes the same gates before it reaches your users.

What it is

Evaluation is how a model earns its release. Every model passes the same gates: task quality on a test set you approve, grounding in your sources, safety against adversarial prompts, privacy on seeded records, latency under load, cost at your volume and drift once it is live. Each gate's method is written down and runs the same way every time.

How we do it

  1. Build the test setLabelled examples of your task, approved by you.
  2. Set the thresholdsOne for each gate, agreed with you before work starts.
  3. Run on every buildTask quality, grounding and privacy, as the code changes.
  4. Run before releaseSafety, latency and cost, on the release candidate.
  5. Watch in productionLive inputs compared with the test set, so drift is caught.

Questions

How do you evaluate a model before launch?

Against the release gates on this page: task quality, grounding, safety, privacy, latency, cost and drift. We agree each threshold with you before work starts, and a release candidate that misses one waits until it passes.

What you get

  • A report of each gate's result for every release candidate

Related

Get started with Etheon Tell us your use case and timeline. We reply within one business day.

From the Lab. Research behind the way we build AI.

  • How we build an AI agent, in five steps

    An agent is software that takes actions in your systems. We build it in five steps, inside limits held outside the model, with a person where it matters.

  • Which AI model should we use?

    The one that does your task best at a cost you can carry. We score candidate models on your evaluation set and choose by quality, cost and response time.

  • What the Etheon Lab works on

    The Etheon Lab studies what makes AI software safe to ship: evaluation, guardrails, observability, safe releases and governance.

Questions. What buyers ask before an AI project.

Against the release gates on this page: task quality, grounding, safety, privacy, latency, cost and drift. We agree each threshold with you before work starts, and a release candidate that misses one waits until it passes.

Get started with Etheon

Tell us your use case and timeline. We reply within one business day.

Data

Pipelines, platforms and BI

Explore Data

Cloud

Cloud, DevOps and SRE

Explore Cloud