Knowledge platforms that agents can cite, not scrape
Enterprise AI knowledge platforms need retrieval, provenance, and access control so agents cite governed sources instead of scraping the intranet into unofficial policy.
Read the articleBetter Technologies,
Better Results
Notes on the technology decisions behind the systems we build.
Approval gates for AI agents that touch money or citizens
When AI agents can move money or change citizen records, drafting is not enough. Approval gates, spend limits, and action whitelists for controlled autonomy. Bluelupin practitioner notes.
DPDP implementation for India-based platforms: what to build before May 2027
What India-based platforms should build for DPDP (consent, purpose, retention, DSRs, vendors, breach) and how to prove it before May 2027. A Bluelupin engineering checklist, not legal advice.
LLM benchmarks: what each bench actually measures
Capability evals and systems benches answer different questions. A plain map of LLM benchmarks for eng leads choosing what to measure before they pick a model or agent stack.
Decision model vs LLM: when agents should classify, route, and gate
When should an agent use a decision model vs an LLM? A practitioner look at TypeSafe Jev use cases for tool approval, routing, and typed Choice/Score outputs.