Projects using Claude in LondonProjects using Claude in London
Cover image for I built a working AI
I built a working AI recruitment screening demo that shows how a hiring team can use AI without handing over the final decision. The flow is simple: A job spec goes in. Candidate profiles are screened against a weighted guideline. Each candidate gets a score, band, evidence quotes, and risk flags. Then everything stops at a human review queue. No auto-rejects. No silent ATS updates. No “AI decided this person is out”. The system includes: Candidate pipeline table Evidence-based screening view Human review queue Approve / reject / snooze decisions ATS deployment plan Audit log for compliance n8n workflow export with a human-in-the-loop Wait node Optional live Claude screening path The important part is the architecture: deterministic logic owns the workflow, gating, state and audit trail. The AI helps with judgement and screening, but the human owns the final decision. Built with Next.js, TypeScript, Claude API, n8n workflow architecture, and a gated ATS sync pattern. This is the kind of system I like building: AI that makes the work faster, but still respects the places where people need control. Shorter Version I built an AI recruitment screening pipeline with a human approval gate. It screens candidates against a rubric, shows evidence quotes and risk flags, then routes every candidate into a review queue before anything reaches the ATS. No auto-rejects. No silent updates. Human-in-the-loop by design. Built with Next.js, TypeScript, Claude API and n8n workflow architecture.
1
56
Cover image for Cascade
Cascade Daily branded video · agency quality, agency throughput, without an agency Most brands ship video like it's expensive. One every two weeks, a long approval chain, four-figure cost per finished asset. The competitor next door is shipping daily and the maths feels impossible, until you look at what the workflow actually costs. Cascade is the whole video pipeline as one system. Topic in. Finished, captioned, posted video out. Script written in your voice from your positioning docs. Voice rendered against a cloned brand voice. Talking-head avatar lip-synced to the audio. Subtitles styled to your brand. B-roll, meme cuts, and music laid in. Posted directly to YouTube, TikTok, and Instagram with the right aspect ratio per platform. Five minutes of wall-clock time per finished video. What you get Daily branded video output without a video team Consistent brand voice across every script, every video, forever Per-platform aspect ratios and metadata handled automatically Direct posting to YouTube, TikTok, and Instagram Reels A pipeline you own, not a tool you rent Marginal cost per finished video lands around £2 in API spend Who it's for Solo founders and creators with one face and ten distribution channels. Agencies producing for multiple brands without hiring more editors. B2B teams turning technical knowledge into shorts. SaaS and ecom brands whose content cadence is bottlenecked on editor capacity, not ideas. What it replaces A £4k/month video editor, a £15k agency retainer, or the calendar slot you don't have. Cascade delivers the same finished output, on schedule, every day. Production reality End-to-end pipeline, live and shipping. The hard part isn't any single API call. It's the orchestration: failure handling at every stage, idempotent retries, graceful degradation when one provider rate-limits, and consistent brand voice across thousands of outputs. Cascade ships finished videos rather than a half-baked pipeline.
1
50