FRAN CANETE
03 / Lab · Product case studies

AI product systems, built end to end.

02 case studies · Independent product work · Updated Jul 2026

Independent case studies built to demonstrate applied AI product engineering: model workflows, structured extraction, embeddings, human review, reliability controls, and the full-stack product systems that make those features useful in practice.

01

Plaudera.

plaudera.com → · SaaS · Live

AI-enabled customer feedback platform for collecting product ideas, detecting duplicates, scoring demand confidence, and managing roadmap decisions. Built around embeddings, similarity search, async background jobs, and human review workflows so AI can assist prioritisation without taking opaque or irreversible decisions.

Product outcome

Turns fragmented feedback into reviewable duplicate candidates and stronger demand signals without automatically merging user submissions.

AI workflow 05 steps
  1. 01 Feedback submitted
  2. 02 Embedding generated
  3. 03 pgvector similarity search
  4. 04 Candidate duplicates scored
  5. 05 Human merge or dismiss
AI engineering Implementation
  • Embeddings turn feedback into vector representations so semantically similar ideas can be retrieved even when the wording differs.
  • Gemini and similarity scoring support duplicate detection and confidence signals built from votes, contributor diversity, frequency, and impact.
  • Inngest moves background work outside the request cycle, while PostgreSQL and pgvector keep product data and vector search in one system.
Reliability and guardrails Product judgement
  • Potential duplicates enter a review workflow; the model never makes an irreversible merge decision.
  • Merge and dismiss actions remain explicit and auditable so product teams can correct uncertain matches.
  • Rate limits, CORS and CSRF controls, contributor sessions, and bot protection secure the public and embedded inputs feeding the workflow.
AI stack5 items
Google GeminiGoogle EmbeddingsVercel AI SDKpgvectorInngest
Platform stack15 items
Next.js 16React 19TypeScriptTailwind CSS 4shadcn/uiDrizzle ORMPostgreSQLBetter Auth +7
What I learned
  • Prioritisation needs more than vote count. Confidence scoring has to account for diversity, impact, frequency, and concentration so the product does not optimise for the loudest minority.
  • AI duplicate detection becomes useful only when paired with human review. Embeddings can find candidates, but merge/dismiss flows and audit trails make the feature trustworthy.
  • Embeddable workflows turn product ideas into infrastructure work quickly: CORS, CSRF, contributor sessions, rate limits, page rules, and bot protection all matter.
02

Duebase.

duebase.com → · SaaS · Live

AI-enabled financial due diligence SaaS that turns UK Companies House filings into structured financial signals, risk assessments, and health scores.

Product outcome

Turns raw company filings into structured financial metrics, risk signals, and health scores that are easier to inspect and compare.

AI workflow 06 steps
  1. 01 Company selected
  2. 02 Filing retrieved
  3. 03 Gemini structured extraction
  4. 04 Schema validation and retry
  5. 05 Risk signals generated
  6. 06 Results shown in dashboard
AI engineering Implementation
  • Gemini 2.5 Flash returns schema-constrained JSON instead of free-form prose, turning financial statements into product-ready data.
  • Inngest orchestrates long-running document analysis with retries, status updates, and recovery paths outside the request cycle.
  • Per-job token tracking and cost estimation make model usage visible, while the Companies House integration supplies authoritative source data.
Reliability and guardrails Product judgement
  • Schema validation and retry handling prevent malformed model output from silently becoming trusted product state.
  • Processing statuses make asynchronous work and failures visible instead of presenting uncertain results as instant success.
  • Subscription-based usage limits and middleware checks keep AI consumption bounded and enforceable.
AI stack3 items
Google Gemini 2.5 FlashInngestZod
Platform stack17 items
Next.js 14 (App Router)TypeScriptMaterial-UI (MUI) v7React Query (TanStack Query v5)React Hook FormNext.js API RoutesSequelize ORMPostgreSQL +9
What I learned
  • Structured outputs make LLM features more dependable, but the value comes from schema design, validation, retries, and graceful failure handling rather than the model alone.
  • Payment reconciliation is product infrastructure. Provider status, webhook timing, customer links, and access state need explicit recovery paths before real users arrive.
  • Trial systems live or die by lifecycle logic. Usage limits, reset timing, upgrade paths, and production traffic expose bugs that happy-path demos miss.