A small, senior UK studio specialising in Wagtail editorial platforms and Django backends — with applied AI woven in where it actually helps. Publishers, universities and the public sector trust us to ship software their teams can own.
We're a Wagtail and Django specialist studio. AI isn't the headline — it's the layer we add when it genuinely improves the editor experience or reader outcome.
Editor-first publishing platforms built in Wagtail — StreamFields, custom blocks, headless GraphQL/REST APIs, multi-site, i18n, and AI-assisted editorial tooling that keeps editors in control. The platform publishers and universities reach for.
Greenfield Django backends and rescue work for existing monoliths. Domain modelling, DRF / async APIs, background workers, multi-tenant patterns.
RAG search, agents, structured output and evals — wired directly into your Wagtail and Django models. AI that earns its place, with full observability.
Solid infra, CI/CD, evals in CI, prompt versioning, cost & quality dashboards — the foundations that make everything dependable.
Two-week sprints to de-risk an idea: architecture, build-vs-buy, model selection, eval plan, cost envelope, and a roadmap your team can execute.
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.
pgvector or Pinecone, hybrid BM25 + dense, query rewriting, citation-grounded answers. Wired into your existing Wagtail or Django models — no parallel content store.
LangGraph-style state machines, tool calling against your real services, human-in-the-loop, structured streaming. Memory, recovery and observability baked in from day one.
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.
Wagtail dashboards for content teams — drafts, tone-matching, translation, alt-text, SEO suggestions and asset tagging. Editors stay in control.
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.
Reference numbers from live deployments
Indicative patterns rather than case studies — specifics under NDA. Happy to share real examples on a discovery call.
Hybrid retrieval across articles, images and video. Cited answers in the publication's voice, editor dashboards for tone & bias review, and fail-soft fallback to classical search.
Replace the BDR first-touch with a Django-hosted agent that reads CRM, books meetings and writes recap notes. Human-in-the-loop for anything above a confidence threshold.
One Wagtail install backing multiple public sites in multiple languages, with AI-assisted translation review and accessibility checks. WCAG 2.2 AA from day one.
Internal tool that turns every prompt change into a tracked release — offline evals, shadow traffic, drift detection and per-prompt cost. Confidence to ship LLM changes like code.
Untangle migrations, kill circular imports, move to async-first DRF, add typed boundaries between domains. No big-bang rewrite — just a year of small, safe steps.
Most engagements run on a fixed-price discovery, then a rolling 4-week build cadence. You always own the code, the prompts and the evals.
Stakeholder & user interviews, architecture and data audit, model + tooling selection, eval plan & cost envelope.
End-to-end vertical slice with real data and real users. Eval suite v1 in CI. Demo & go/no-go decision.
Production Django / Wagtail, observability + cost dashboards, pair with your engineers, runbooks & on-call.
Knowledge transfer sessions, eval & drift monitoring, quarterly model refresh, retainer or hand back the keys.
We're taking on 2 more projects for Q3. Reach out before slots fill.