W.01
Headless Wagtail
Wagtail as a content backend feeding Next.js, SvelteKit or native mobile. REST or GraphQL, preview mode, ISR, image renditions, and AI features sitting in the same domain model.
Our practice
Services we actually do.
Four practices, one team. We move in small, senior squads — usually one lead engineer plus a specialist. Everything we ship is production-ready Python: typed, tested, observable, and easy for your team to take over.
01 / Flagship practice
Wagtail builds editors actually enjoy.
Editor-first publishing platforms in Wagtail — StreamFields, custom blocks, headless GraphQL/REST, multi-site, multi-language, and AI-assisted editorial tooling. We've been contributing to Wagtail since 2015.
W.02
Multi-site & multi-language
One Wagtail install backing many public sites in many languages, with editorial workflow, translation review, and accessibility checks built into the publishing flow.
W.03
StreamField & custom blocks
Block-based content modelling that gives editors flexibility without compromising your data model. Custom choosers, validators, block-level previews and rich admin panels.
02 / Django product engineering
Django backends, done properly.
Greenfield Django backends and rescue work for existing monoliths. We've shipped Django since 2012 — domain modelling, DRF / async APIs, background workers, multi-tenant patterns, and migration strategies that don't break production.
D.01
Greenfield Django builds
Typed models, sensible DRF, async views where they earn their keep, Celery for the rest. Clear domain boundaries, proper tests, infrastructure-as-code from day one.
D.02
Monolith rescue & modernisation
9-year codebases brought back to life without big-bang rewrites. We untangle migrations, kill circular imports, add typed boundaries, and ship in small, safe steps.
03 / Platform & MLOps
The boring foundations that make AI dependable.
Infra, CI/CD, evals in CI, prompt versioning, cost & quality dashboards, on-call runbooks. The unglamorous work that turns a clever prototype into a production system your team can sleep through the weekend on.
P.01
API design & integration
Versioned REST and GraphQL APIs, webhook architectures, third-party integrations, OpenAPI specs and developer docs that don't lie. We build APIs that outlive the project that asked for them.
P.02
Technical site audits
Independent review of your existing Django or Wagtail platform — performance, security, architecture, editorial workflow, and a prioritised remediation plan you can actually execute against.
04 / Applied AI & LLM engineering
Applied AI & LLM engineering.
We treat LLMs as just another dependency — typed inputs and outputs, deterministic tests, evals on every PR, and a clear story for cost, latency and failure. The result is AI features your team can own, debug and improve.
A.01
Retrieval-augmented search & chat
pgvector or Pinecone, hybrid BM25 + dense, query rewriting, citation-grounded answers. Wired into your existing Wagtail or Django models — no parallel content store.
+ citations
A.02
Agents & multi-step workflows
LangGraph-style state machines, tool calling against your real services, human-in-the-loop, structured streaming. Memory, recovery and observability baked in.
streaming
A.03
Evals, guardrails & safety
Offline eval suites, regression tests in CI, prompt versioning, PII redaction and red-team harnesses. Ship LLM changes with the same confidence as any other deploy.
CI-gated
A.04
AI-assisted editorial tools
Wagtail dashboards for content teams — drafts, tone-matching, translation, alt-text, SEO suggestions, asset tagging. Editors stay in control; the AI does the grunt work.
editor-first
A.05
Private / on-prem deployments
Llama, Mistral, Qwen and friends on your own GPUs or VPC. We handle vLLM, batching, quantisation and the security paperwork. Suitable for regulated and public-sector clients.
vpc · on-prem
Got a brief in mind?
Let's scope it.
Discovery
2-week fixed-price sprint · £8k
Build squad
Rolling 4-week cadence · £15–25k / month
Audit
3–5 day independent review · from £2,500