SOPHIA XT
Services

Models, data and
software, built for your problem.

We design language models, create the data they learn from, and build the software they run in. The same people do all three, so the model and its training set are made for each other. When AI is the wrong answer, we say that first.

What we do

One team for the model,
its data and its tools.

01

Custom models

We design a model for your task and train it from random weights on hardware we own or rent. XE5 shows the pattern: a new skill is a new specialist, so adding one does not disturb the others. Cassandra T1 shows the open end: 1.33B parameters, weights public.

02

Training data

Going from 237 to 2,611 examples did nothing for our models. Adding the right kinds of examples did. We build supervised sets by construction family and anchor-masked corpora, and we have built corpora from SEC filings in the US and Canada.

03

Software for LLMs

Assistants that answer from your own records and cite the row they read. MCP servers with scoped tokens. Agent tooling that runs coding agents in separate worktrees. We ship our own platform, Sophia Stack X, with 53 MCP tools, and run assistants in client systems.

How a model gets made

Corpus in,
report out.

Pick a stage. The training stage uses anchor-token masking, our method, with a DOI and 504 published generations behind it.

What we do

We train from random weights, or adapt an open model, on hardware we own or rent. Anchor-token masking keeps the tokens that matter, such as names and part numbers, intact while the rest is masked, which is the method behind our 1.67× held-out result.

What you get

A checkpoint, the training log and the configuration that made it.

Anchor tokens (orange) stay fixed. The model has to fill the masked ones (▯). Illustrative tokens

1.67×held-out gain of anchor-token masking over random masking, 95% interval 1.51 to 1.85
504generations published, losing arms included
3models trained from scratch
Before and beside the model

We will tell you when
it should not be AI.

01

Workflow audit

Before we build, we map the workflow and say where AI helps and where it does not. A process change, a dashboard or an API integration is often cheaper than a model, and we recommend it when it is.

02

Automation

Integrations, routing and dashboards that remove a manual step. This is ordinary software work and we do it without a model when no model is needed.

03

Agentic workflows

Several narrow agents with checks between them. Constellation is our own design: six lanes and an arbiter that abstains when the margin is thin and hands the decision to a person.

How an engagement runs

Four steps, in this order.

01

A call

You describe the task and the data. We say whether we can help and what we would need.

02

A written scope

What a correct answer looks like, the held-out examples we will score on, and what we will deliver. Written before any training.

03

The build

Data, training and evaluation as in the pipeline above. You see the failures along with the wins.

04

Handover

The weights, the data, the training configuration and the report are yours. We can run it for you or leave it with your team.

Client work is private. What we publish is our own research.

Start

Describe the task.
Thomas reads it.

SOPHIA XT is the AI lab of 3 Point Forward. If the problem is a business problem first, 3 Point Forward can define it with you and we build what the plan needs.