CASE STUDIES·REPRODUCIBLE WALKTHROUGHS

REAL QUESTIONS.
RUNNABLE ANSWERS.

XERJ audited its own Rust engine and found a real unauthenticated process-abort DoS — reached for 10,533 tokens instead of the 1.8M it takes to read the source once. WordPress core — ~619k lines — was security-audited for ~26,000 tokens. Those two are measured on real code; the other two are functional proofs on small synthetic corpora — they show the shape works, not how fast. Every number traces to a walkthrough in the repo.

01
XERJ AUDITS
ITS OWN
RUST.

XERJ indexed its own engine — 197 files, ~201k lines — as a queryable AST and call graph, then found an unauthenticated POST /_sql stack-overflow that aborts the process. A call-graph recursion-cycle query grep cannot express. Yellow is the tokens to reach the finding; blue is what it costs to read the source once.

10,533 TOKENS INSTEAD OF 1.8M · BUG FIXED
SECURITY ENGINEERS · AI-AGENT BUILDERS · RUST TEAMS
FULL CASE STUDY →
MEASURED · tiktoken cl100k_base · TOKENS TO THE /_sql FINDING
XERJ-ASSISTED READ EVERY FILE
Tokens to the finding 10,533 1,805,277 171×

TOKEN ACCOUNTING, NOT A LATENCY BENCHMARK · SOURCES IN docs/case-studies/xerj-self-audit →

02
WORDPRESS
SECURITY
AUDIT.

WordPress core is ~619k lines — ~26× a 200k-token context window. An agent indexed it as a queryable code graph and read only what queries surfaced. Yellow is the whole audit's token bill; blue is what it costs just to load the code once.

~26K TOKENS INSTEAD OF ~5.2M
SECURITY ENGINEERS · AI-AGENT BUILDERS · PLATFORM TEAMS
FULL CASE STUDY →
MEASURED · WORDPRESS CORE · 1,492 FILES / ~619K LINES
XERJ-ASSISTED AUDIT READ EVERY FILE
Tokens, entire audit ~26,000 ~5,200,000 ~199×

TOKEN ACCOUNTING, NOT A LATENCY BENCHMARK · SOURCES IN docs/case-studies/wordpress-security-audit →

03
SEMANTIC
ANALYTICS IN
ONE REQUEST.

"Of calls about wifi issues, how many are 2.4GHz vs 5GHz, and what are the key issues?" — asked by calltree.ai. Half retrieval, half analytics: normally two stores and an ETL. One XERJ POST /_search returns the slice, the breakdown, the metrics, and the evidence.

1 REQUEST · 1 STORE — WAS 2 + ETL
AI-OVER-SUPPORT TEAMS · DATA PLATFORM ENGINEERS
FULL CASE STUDY →
GENERATED CORPUS · NOT A BENCHMARK · 130 SYNTHETIC CONVERSATIONS
XERJ SPLIT STACK
Requests per question 1 2
Stores to operate 1 2
ONE RESPONSE CARRIES
01SEMANTIC SLICEk=80 nearest conversations
02BREAKDOWNterms buckets: band, key issues
03METRICScsat p50 · handle-time avg, per bucket
04EVIDENCE3 example hits → LLM narrative

SPLIT STACK = OLAP + VECTOR STORE + ETL, OR TWO ROUND TRIPS IN ONE ENGINE · AGGS-BEARING kNN RUNS THE EXACT SCAN, NO SPEED CLAIM · BUCKETS COUNT THE RETRIEVED SLICE · k=80 IS THE REQUEST PARAMETER, NOT A MATCH COUNT · SOURCES IN docs/case-studies/calltree-analytics →

04
POSTGRES CDC +
HYBRID SEARCH.

daily.dev's founder asked: can XERJ replicate automatically from Postgres? A logical-replication slot streams every INSERT, UPDATE, and DELETE into XERJ — no reindex jobs — and one hybrid query fuses BM25 + vector rankings server-side, replacing the tsvector + pgvector two-query app merge.

3/3 MUTATION TYPES REPLICATED · 0 CHANGES LOST
POSTGRES TEAMS · SEARCH ENGINEERS · PLATFORM TEAMS
FULL CASE STUDY →
FUNCTIONAL PROOF·SYNTHETIC 8-ROW CORPUS·NOT A BENCHMARK
XERJ POSTGRES TSVECTOR + PGVECTOR
Queries per hybrid search 1 fused query 2 queries + app-side merge
App-side score merges 0 · RRF fuses server-side 1 · across two score scales

ARCHITECTURAL COUNT FROM THE RECORDED RUN · SOURCES IN docs/case-studies/daily-dev-postgres-cdc →

05
SAME MODEL.
FEWER
TOKENS.

On code the model has not memorised, handing the same Claude Code a XERJ-retrieved reference makes it correct where memory fails — 21/21 vs 1/21 — at 1.5–2.7× fewer output tokens than native Claude Code grepping the source, across five languages. Red is answering from memory; yellow is XERJ-assisted. On memorised code, retrieval is honest overhead — and we say so.

21/21 vs 1/21 SOLVED · 6.5× CHEAPER THAN MEMORY
AI-AGENT BUILDERS · PLATFORM & DX TEAMS · SYNTHETIC CORPUS
FULL CASE STUDY →
MEASURED · 16 RUNS × 4 LANGUAGES · REAL OUTPUT TOKENS FROM claude -p
XERJ-ASSISTED BARE (MEMORY)
Output tokens to solve 9,982 260,916 26×
Tasks solved 16 / 16 11 / 16

SAME AGENT, ONE HIDDEN-TEST VERDICT · SYNTHETIC UNFAMILIAR-API CORPUS · SOURCES IN docs/case-studies/reference-coding →

READY?·REQUEST ACCESS

RUN ONE ON
YOUR DATA.

Every walkthrough reproduces from the repo. Want it run against your codebase, your conversations, or your Postgres? Leave a work email and we'll set it up with you.

We only use this email to send you the binary. Ever. ✓ THANKS. CHECK YOUR INBOX WITHIN 24 HOURS.