Amirus/ Work/ Axiom AI

Axiom — enterprise retrieval,
not just another chat wrapper.

A retrieval-augmented writing tool for engineering teams. We built the retrieval, eval harness, and production pipeline. The demo below reconstructs that pipeline with sample questions and pre-baked answers — pick one and watch the flow.

ClientAxiom AI, Inc.
SectorApplied AI · B2B
Engagement11 months
Team4 eng · 1 applied-ML
StackPython · pgvector · bge-large · Ray
Shipped2025 Q3
§ Interactive demo · RAG pipeline

Ask a question. Watch the retrieval, watch the answer.

or pick:
§ RETRIEVED · TOP 4 similarity
docs/citations.md#disambig 0.91
Axiom disambiguates citations using a three-stage ranker: lexical overlap, entity-type filter, then cross-encoder rerank.
rfcs/RFC-023.md#rerank 0.88
The rerank uses a distilled bge-large model at 76ms p95. If confidence is below 0.55, we prompt the author for clarification.
runbooks/citations.md 0.74
On-call: if the disambiguator is failing, fall back to "lexical only" by flipping the AXIOM_DISAMBIG_MODE=lex flag.
tests/disambig.json 0.69
Gold set of 1,240 ambiguous citation queries. Current pass rate: 93.6%.
§ GENERATED · STREAMING model: bge-large-v3
RETRIEVED
0chunks
P95 LATENCY
0ms
TOKENS
0
COST
$0
§ What we shipped

An eval harness, a retrieval pipeline, and a production runbook.

93.6%
Gold-set recall@10
86ms
Retrieval P95
1,240
Eval queries
$0.003
Cost / query

Building your own RAG? We've done this before.

Start a project →
◆ Tweaks
Accent
Logo variant