14 achievements — 8 technical, 6 milestone
Full-stack cloud + on-prem infrastructure built from scratch in one sprint.
→ READ MORESelf-service API key management, spend tracking, and audit logs — live on day two.
→ READ MOREPII never reaches the model. Every prompt is scrubbed before inference.
→ READ MOREFull Italian version of the platform — because our roots are in Turin.
→ READ MOREQuota system, spend caps, and key lifecycle management — usage that pays for itself.
→ READ MORE12-cell matrix harness measures throughput across size, concurrency, and history dimensions.
→ READ MORE6 security findings identified and remediated — from credential management to XSS.
→ READ MOREProforma invoices generated and emailed automatically on every top-up.
→ READ MOREA second deep security sweep found and remediated an IDOR, an SSRF, and a stored HTML injection — all rated high severity.
→ READ MOREUsage, spend, and audit data can now be exported as styled Excel workbooks or PDFs — filtered by date range, API key, or organization.
→ READ MORESpend alerts, invite events, and key lifecycle changes now surface as bilingual in-app notifications alongside email delivery.
→ READ MOREUsers can set a display name, preferred language, and enrol in MFA — without leaving the portal.
→ READ MORETeams can now collaborate under shared organizations with four access tiers — from read-only audit members to full administrators.
→ READ MORERebuilt the on-prem inference stack on native Ollama — request reliability rose 65.8% → 90.0% and serial throughput stabilized at ~44 tok/s across all prompt sizes.
→ READ MORE