Skip to main content

Dev Station Technology

AI Development

spaCy development services for text that needs structure

We have no published spaCy build. Our AI product reads service pages, job adverts and careers posts through a Claude-compatible API, and we say plainly where a trained pipeline would help.

0Published builds on spaCy
3.8.18Marked latest, 26 Oct 2026
3.8.16Released 24 August
3Text sources Sales OS reads
What we build

What we would take on with spaCy

Entity extraction

Names, equipment and dates pulled from text into fields.

Pipelines behind an API

A FastAPI service that runs a trained pipeline.

Evidence for each field

The sentence that produced a value kept next to it.

Upgrades

Moves onto the 3.8 line.

Architecture

Where spaCy would sit

A pipeline in front of the account brief
Text
Service pagesCrawled from a domain
Job advertsEquipment named in posts
Reading
spaCy logo
spaCy pipelineWhere it would sit
Claude-compatible APISales OS, today
Output
Graded briefScore and evidence per axis

Illustration. A dashed outline marks where the technology would sit. We have no published build on it.

Releases

Recent spaCy releases

The latest spaCy 3.8 releases
24 August

spaCy 3.8.16

A maintenance release.

26 October

spaCy 3.8.17

A build-configuration release.

26 October 2026

spaCy 3.8.18

Marked latest on GitHub.

Source: spaCy releases on GitHub, checked 6 November 2026. The release headers show day and month, and the asset timestamps give 2026 for 3.8.18.

Builds

The closest builds we can show you

Sales OS account research product built by Dev Station
AI product, in-house

Sales OS

The engine crawls a site, reads service pages, job adverts and careers posts, and writes a graded brief with the evidence beside each score.

40 accountsAbout 26 hours of reading a week replaced by 40 credits
TruckFleet Labs dispatch console and driver app built by Dev Station
Logistics, fleet operations

TruckFleet Labs

A Python 3.13 back end with telematics ingest and PostGIS.

38Drivers on the app by week three
Fit check

When spaCy is the right call

Pick spaCy when

  • You need fields pulled from a lot of text
  • The same extraction must run every time
  • Text must stay inside your own servers

Look elsewhere when

  • You need a published spaCy build to inspect, which we do not have
  • A language model API already reads your text, as in Sales OS
  • You have few examples to learn from
Stack

What spaCy usually sits beside

Python logoPython
PyTorch logoPyTorch
Docker logoDocker
scikit-learn logoscikit-learn
TensorFlow logoTensorFlow
Apache Airflow logoApache Airflow
FAQs

What buyers ask first

Which spaCy version is current?

spaCy 3.8.18, marked latest on GitHub and released on 26 October 2026. Version 3.8.17 came out the same day and 3.8.16 on 24 August.

Do you have a published spaCy build?

No. We say so on the first call and show the nearest work, which is Sales OS, which reads service pages and job adverts through a model API.

How does spaCy get a trained pipeline?

You install spaCy, then download a trained pipeline, for example with python -m spacy download en_core_web_sm.

Who owns the code and the cloud accounts?

You do, from the first commit. Repositories and cloud accounts stay in your name.

Tell us what your text has to give you

Thirty minutes on your documents, your fields and your spaCy version. No sales pitch.

Let's Talk