Everything we have measured, written down.
Reports, docs, comparisons and engineering notes. Nothing here is behind a form or an email wall.
The benchmark report
The published benchmark results as a single downloadable document. For the reading guide (what each number means and where qbrin does not lead), start with the engineering note below.
- Report
Benchmark scorecard
Head-to-head results with the sample size and the caveat on every row.
Open the scorecard - Report
Security benchmark
A measured SOC comparison: qbrin against RAG, an MCP agent and a naive LLM analyst, on live security data.
Read the benchmark - Docs
API reference
The REST API: authenticate, ingest, ask, and get a cited answer or a clear abstain.
Open the docs - Docs
Action authorization API
The pre-execution endpoint that answers ALLOW, HOLD or ESCALATE for a proposed agent action.
See the endpoint - Comparison
qbrin vs Glean
An architecture-level comparison, including where Glean is stronger.
Read the comparison - Comparison
Glean alternatives
qbrin, Microsoft 365 Copilot, Coveo, Elastic and Guru: pricing models and who each fits.
See the options - Engineering note
How qbrin works: evidence before answers
A visual guide from connected sources to a cited answer or a deliberate abstention.
Read the note - Engineering note
Evidence vs verification vs authorization in AI
Why source retrieval, claim support and permission to act are three separate gates.
Read the note - Engineering note
qbrin benchmark results: an honest guide
The published numbers, the sample sizes, and the cases where qbrin does not lead.
Read the note - Engineering note
When an absence becomes a finding
The quietest failure in AI systems: a failed read that gets reported as a confident negative.
Read the note - Engineering note
The most dangerous prompt injection is stopped by retrieval, not detection
Credential-scoped boundaries at the retrieval plane.
Read the note - Engineering note
A safety gate that blocks 100% of attacks and 100% of real work
Why substring grounding checks look perfect on the scoreboard and reject valid commands.
Read the note - Engineering note
A 400-token cap on our verifier was silently dropping correct answers
How a fixed limit turned parser errors into silent refusals.
Read the note - Engineering note
AI abstention: why knowing when to stop matters
The business case and measurement discipline behind saying “not enough evidence”.
Read the note
See it answer your hardest question.
Bring one real question your team keeps re-asking. We'll connect a source, read-only, and show you the answer, sourced, in seconds, in a 20-minute walkthrough. Nothing changes in your tools.
- One source connected, read-only
- Your real question answered, with sources
- Nothing changes in your tools