Google Cloud Partner SSO/SAML Encrypted Data Residency 13-Layer Engine
← Back to Home
DOCUMENTATION

goJarvisX Docs

Everything you need to modernize SQL, ETL workflows, code, schemas, lineage, and data — with enterprise-grade quality.

0 Conversion Pairs
0 Quality Layers
0 Modules
01

Getting Started

From sign-in to results in 5 steps.

1
Sign in with Google SSO — no password needed.
2
Accept Terms — confirm via email link (one-time).
3
Choose a module — JarvisQuery, JarvisFlow, JarvisCode, JarvisSchema, JarvisGraph, JarvisData, or JarvisRisk.
📤
4
Upload artifacts — CSV or ZIP (batch) or paste directly (Try Now). Optionally include DDLs.
5
Get results by email — download converted artifacts, quality report, and risk assessment from My Submissions.
Tip: Keep one logical unit per artifact (one query, one script). Split monolithic files before uploading for best accuracy.
02

Modules

Seven specialized modules under one platform. Click any card to expand.

🔎
JarvisQuery
SQL dialect conversion across 11+ engines
+
Input.sql / .zip / .csv
OutputConverted SQL + quality report
EnginesTeradata, Oracle, MySQL, PostgreSQL, SQL Server, Redshift, Snowflake, BigQuery, Hive, Spark, DuckDB
💻
JarvisCode
Script translation (Python, Java, Scala, BTEQ, Shell)
+
Input.py / .java / .scala / .sh / .zip
OutputConverted code files
Weight3x credits per artifact
🔄
JarvisFlow
ETL/workflow modernization (Informatica, Talend, SSIS → Airflow, dbt)
+
Input.xml / .json / .yaml / .zip
OutputTarget workflow definitions (Airflow DAGs, dbt models, Dagster pipelines)
Weight2x credits per artifact
📊
JarvisSchema
Batch DDL rewrite with type mapping
+
Input.sql / .ddl / .zip
OutputTarget-native DDL with constraint preservation
📈
JarvisGraph
Column-level lineage from SQL (AST + AI hybrid)
+
Input.sql / .zip
OutputInteractive lineage graph (HTML) + CSV export
Enginesqlglot AST parsing + Claude AI for complex expressions
JarvisRisk
Pre-conversion migration risk assessment
+
Input.sql / .zip (legacy artifacts)
OutputRisk report (HTML / CSV / PDF)
Engine50+ regex rules + AI enrichment
📊
JarvisData
AI sample data generation from DDL schemas
+
Input.sql / .ddl / .zip
OutputCSV / JSON test data
BillingRow-weighted: 1K=2x, 10K=5x, 100K=15x per table
03

13-Layer Quality Engine

Every conversion passes through all 13 layers — not just raw AI output.

0sqlglot Deterministic Transpilation60-70% of SQL at 100% accuracy. Zero AI cost. 16 dialects.
1Pre-LLM Deterministic Rewrites20 regex rules: NVL to COALESCE, SEL to SELECT, BTEQ cleanup.
2Complexity-Adaptive PromptingSimple/moderate/complex classification adjusts prompt depth.
3Feature Detection + Micro-Cards30+ features: QUALIFY, MERGE, PIVOT, cursors, dynamic SQL.
491 Pair-Specific Conversion CardsDeep dialect-level function mappings per source-to-target pair.
5RAG Retrieval (HyDE + RRF Reranking)FAISS vector search + few-shot examples injected per conversion.
6LLM Conversion (Advanced AI Agent)temp=0.0, deterministic, anti-comment rules, adaptive max_tokens.
7Post-LLM Deterministic RewritesSame 20 rules on OUTPUT — catches what LLM missed.
8Syntax Validation (sqlglot)Parses output in 16 target dialects.
9Category-Specific ValidationSQL / Code / Workflow / DDL validators with domain rules.
10Auto-Repair (LLM Fix)If validation fails: re-prompt with error list. AI single-pass fix.
11Semantic ScoringAI quality scoring: intent vs output (sampled, non-blocking).
12Confidence Scoring + Review Flags13 hard-feature detectors. HIGH / MEDIUM / LOW per artifact.
Competitors use 1 layer (raw LLM). JarvisX uses all 13 — engineered accuracy, not just AI output.
04

Supported Conversion Pairs

91 pair-specific cards with deep function-level mappings.

61 SQL pairs across 11+ engines
Teradata, Oracle, MySQL, PostgreSQL, SQL Server, Redshift, Snowflake, BigQuery, Hive, Spark, DuckDB, Druid
Before (Teradata)
SEL TOP 10 employee_name,
  NVL(dept, 'Unknown') AS department
FROM employees
QUALIFY ROW_NUMBER() OVER(
  PARTITION BY dept ORDER BY hire_dt
) = 1;
After (BigQuery)
SELECT employee_name,
  COALESCE(dept, 'Unknown') AS department
FROM (
  SELECT *, ROW_NUMBER() OVER(
    PARTITION BY dept ORDER BY hire_dt
  ) AS _rn FROM employees
) WHERE _rn = 1
LIMIT 10;
30 ETL/workflow pairs
Informatica, Talend, SSIS, DataStage, Control-M → Airflow, dbt, Databricks, Dagster, Prefect, Step Functions
Before (Informatica XML)
<MAPPING NAME="m_load_customers">
  <SOURCE NAME="SRC_CUSTOMERS" />
  <TARGET NAME="TGT_DW_CUSTOMERS" />
  <TRANSFORMATION TYPE="filter"
    CONDITION="status='ACTIVE'" />
</MAPPING>
After (Airflow DAG)
@dag(schedule='@daily',
     start_date=datetime(2026,1,1))
def load_customers():
    @task
    def extract():
        return read_source('SRC_CUSTOMERS')
    @task
    def filter_active(data):
        return [r for r in data
                if r['status']=='ACTIVE']
Code language pairs
Python, Java, Scala, BTEQ, Shell, JavaScript, TypeScript, C#, Ruby, Go, PHP
Before (BTEQ)
.LOGON tdserver/dbc,dbc;
SELECT COUNT(*) FROM sales
WHERE sale_date = DATE;
.IF ACTIVITYCOUNT = 0 THEN .GOTO NODATA
.EXPORT FILE=result.csv
SELECT * FROM sales
WHERE sale_date = DATE;
.LOGOFF
After (Python)
from google.cloud import bigquery
client = bigquery.Client()
count = client.query(
  "SELECT COUNT(*) FROM sales "
  "WHERE sale_date = CURRENT_DATE()"
).result().to_dataframe().iloc[0,0]
if count == 0:
    raise SystemExit("No data found")
df = client.query(
  "SELECT * FROM sales "
  "WHERE sale_date = CURRENT_DATE()"
).result().to_dataframe()
df.to_csv("result.csv", index=False)
05

Batch Lifecycle

From upload to email delivery — fully event-driven.

1
Upload ZIP/CSV with up to 10,000 artifacts per batch.
2
Evaluate Input validation, artifact count, source-type verification.
3
Reserve Credits Atomic transactional deduction from your plan quota.
4
Queue & Process Event-driven pipeline with AI Batch Engine + 13-layer quality engine.
5
Post-Process Download results, apply validation, quality scoring, confidence flags.
6
Deliver Email notification with download link. Results in My Submissions.
Failed jobs don't consume credits. Stuck jobs are auto-recovered by the sweeper (max 3 retries).
06

Plans & Billing

Artifact-based billing with per-plan Try Now limits.

Free
$0
50 artifacts/mo
5 Try Now total
Evaluation
Starter
$79/mo
250 artifacts/mo
50 Try Now/mo
Small teams
Scale
$499/mo
10,000 artifacts/mo
500 Try Now/mo
Enterprise migrations
Enterprise
$1,999/mo
50,000 artifacts/mo
1,000 Try Now/mo
Multi-team programs

View full plans with INR pricing →

Artifact weights: Query = 1x, Workflow = 2x, Code = 3x. Mixed batches pro-rate accordingly.
06a

Projects & Collaboration

Beyond one-off batches, JarvisX organizes work into Projects — persistent workspaces that group multiple batches, capture a running activity timeline, accumulate a blended quality score, and produce a stakeholder- ready Migration Pack on demand.

📚
Projects
Create a Project with a source → target pair once; attach any number of batches to it over time. Every linked batch rolls up into the project-level dashboard.
👥
Team access (Growth+)
Invite teammates with owner, editor, or viewer roles. Role-gated UI: viewers can't submit, editors can't destroy, owners hold the keys.
Per-batch sign-off
Each linked batch carries a review state (pendingreviewingapproved / changes-requested) so you can track who's signed off on what — before, during, and after conversion.
📦
Migration Pack export
One click assembles a ZIP containing a cover letter, visual summary, per-batch outputs, JarvisGraph lineage, JarvisRisk reports, and a manifest. Branded for Enterprise customers.
📄
Activity timeline
Every meaningful event (batch attached, role changed, pack exported) appears on the project's timeline with actor, timestamp, and payload. Great for stakeholder updates.
📃
Clone & archive
Clone a Project to fork its config for a similar migration; archive when complete. Archived Projects are read-only but fully retained.
06b

API & Programmatic Access

JarvisX exposes a JSON API under /api/v1/* for programmatic access. Generate a bearer token from your Account → API tokens page and include it on every call.

# Token format: jvx_<env>_<32-hex>  — shown once at creation, SHA-256 hashed at rest
curl -H "Authorization: Bearer jvx_prod_abc123..." \
     https://gojarvisx.ai/api/v1/whoami

# List your workspaces
curl -H "Authorization: Bearer ..." \
     https://gojarvisx.ai/api/v1/workspaces

# Attach an existing batch to a workspace (no re-run, no re-charge)
curl -X POST -H "Authorization: Bearer ..." \
     -H "Content-Type: application/json" \
     -d '{"job_id":"batch_abc123"}' \
     https://gojarvisx.ai/api/v1/workspaces/wks-xyz/attach-batch
Token lifecycle
Max 5 active per user. 90-day default expiry. Immediate revocation via self-serve UI. Revoked tokens return 401 on next request — no cache delay.
Scopes
Tokens carry scopes (read, write) to limit blast radius. A read-only token can query workspaces but can't mutate them.
Audit trail
Every API call is logged to audit_events with the token ID as actor. Tamper-evident audit for SOC 2 needs.
06c

Enterprise Features

Built for teams that need audit trails, uptime commitments, and identity-provider integration. See our Trust Center for the full security posture, or the Security Review for procurement-grade Q&A.

🔍
SOC 2-aligned audit log
Every privileged action (auth, access changes, data, billing, admin, export, review) is recorded with actor, subject, IP, user-agent, and structured payload. Admin CSV export for auditor handoff.
🛠
Public status page
Real-time component health + admin-curated incident history at /status. JSON endpoint /status/api for external uptime monitors.
🛡
SAML 2.0 SSO
Per-tenant federation with Microsoft Entra, Okta, Ping, ADFS. Admin pastes IdP metadata; your users sign in with their corporate identity. MFA / conditional access inherited from your IdP.
👉
Magic-link email auth
Self-serve sign-in for anyone with an email — 6-digit code emailed, 30-minute TTL, SHA-256 hashed at rest. No passwords, no breach risk.
🎨
Custom branding
Migration Packs can ship with your logo, company name, and tagline on the cover letter and summary pages — so the deliverable looks like it came from your team, not ours.
💲
Cost guardrails
Daily LLM spend cap, preflight cost estimation, kill-switch on budget breach. Large batches are quoted before commit; no surprise invoices.
07

Security & Privacy

Summary below; full posture with live/roadmap status at the Trust Center →

🔒
Authentication
Three paths: Google OAuth 2.0 (OIDC), SAML 2.0 (Entra / Okta / Ping / ADFS — Enterprise), and magic-link email codes. Sessions are server-side with 30-min idle timeout. No passwords stored on our side, ever.
👥
Access control
Workspace-level RBAC (owner / editor / viewer) enforced at route + service layer. Admin actions require explicit elevation, all audit-logged.
Data storage
GCS + Firestore in us-central1. AES-256 at rest by default; CMEK available for Enterprise. TLS 1.2+ in transit. Least-privilege IAM throughout.
🔑
Secrets management
All credentials in Google Secret Manager. API tokens and magic-link codes SHA-256-hashed at rest. Zero keys in source.
🤖
AI data handling
Your artifacts are processed by Claude / OpenAI to produce the conversion you asked for — nothing more. Neither we nor our LLM providers train on your data (per their enterprise API agreements).
📋
Compliance roadmap
SOC 2 Type II attestation targeted 2027. Controls are SOC 2-aligned today. Full posture + sub-processor list + DPA availability on the Trust Center.
08

Frequently Asked Questions

Upload .sql, .py, .java, .scala, .sh, .xml, .json, .yaml, .ddl, .csv, or .zip files. ZIP archives can contain up to 10,000 artifacts per batch.
Every artifact receives a blended quality score: 70% deterministic (syntax validation, rule checks) + 30% semantic (AI-based intent-vs-output scoring). Results include HIGH / MEDIUM / LOW confidence flags.
Failed artifacts go through Auto-Repair (Layer 10) which re-prompts the AI with the error list. If it still fails, you get a detailed error report. Failed jobs do not consume credits.
Each artifact type has a weight: Query = 1x, Workflow = 2x, Code = 3x. JarvisData scales by row count (1K=2x, 10K=5x, 100K=15x per table). Credits are reserved atomically before processing and refunded on failure.
Yes. All data is stored in Google Cloud Storage with least-privilege IAM. Artifacts are processed by Claude (Anthropic) and we do not train on your data. Sessions use server-side storage with short TTLs.
Yes. The Free plan includes 50 artifacts per month and 5 Try Now conversions (paste-and-convert instantly). No credit card required.
09

Support

Purchase / Upgrade
💬
Need Help?
Raise a support request →
Include batch ID and error details for fastest resolution.
Back to top

Please login to proceed

You must sign in before using this feature.