The Build Pipeline

Every analysis is
autonomously built.
And it shows.

Every analysis in our library is built by a pipeline of specialized agents — they research the method, write it as validated R, run it on the data, and independently verify the result before it ships. The numbers come from deterministic R, not a model improvising code: the same analysis runs the same way for every customer, every time. The same standard holds at every depth — but the pipeline scales with it, from an instant Snapshot to an assurance-grade Capstone that builds your analysis several times over and checks the results agree.

Custom
Built for your question, on your data
5
Stages, fully autonomous
100%
Reproducible — same answer, every run

Five stages. One daemon.

This is the rigorous R build — the path behind the Stats, Atlas, and Capstone tiers. Each module goes through five specialized stages, each handled by an agent with a single job, orchestrated by a daemon that runs continuously and builds in parallel. The fast Python tiers (Snapshot, Survey) run a shorter version of this same flow; an assurance-grade Capstone runs a longer one. See how the depths compare below ↓

Question + Dataset SPEC Research + Design ~5.5 min BUILD Write R code ~5.3 min RENDER Run R in Docker ~6 sec VERIFY 10 quality checks ~3.2 min if fail → fixer (~3 min) → retry DEPLOY ~1.8 min Daemon orchestrator (continuous polling)
1

Research the question

SPEC · 5.5 min avg

Reads the question, looks at the dataset shape, picks the right statistical method, and designs the report card by card. The output is a structured spec.

2

Write the R code

BUILD · 5.3 min avg

Implements the spec as deterministic R code with literate documentation, edge-case handling, and statistical safeguards. Same code runs every future report.

3

Run the analysis

RENDER · 6 sec avg

Executes the R script in a sandboxed Docker container against the test data. Produces metrics, datasets, charts, and the structured report payload.

4

10 quality checks

VERIFY · 3.2 min avg

Inspects every output: file completeness, metric validity, chart rendering, statistical soundness, code style. Reads each chart screenshot visually.

5

Push to production

DEPLOY · 1.8 min avg

Builds a Docker image, registers the module in the API, runs a smoke test, activates it. The library grows. Available to every customer instantly.

The same standard. The depth you choose.

The five-stage flow above is the heart of it — but the pipeline scales with the tier you pick. A Snapshot answers in seconds with a single query; the R tiers write and verify reproducible code; an assurance-grade Capstone builds your analysis independently several times and only ships what agrees. Same verification standard at every depth.

The engine is the dividing line. The Python tiers are built for speed — a fast descriptive read: a chart, an overview. The R tiers unlock the full statistical method catalog — real hypothesis tests, regression and survival models, diagnostics — because R's open-source library ecosystem is built for exactly that. R simply runs more kinds of analysis, so its pipeline is longer: more to build, and more to verify. You can see that below — each tier's pipeline grows with what it can do.

Snapshot · Python

Instant

≈ 30–90 sec · ~$0 to run

One focused question, answered fast. A single query and one chart with a plain-English readout — no R, no waiting.

  • Read your question
  • Pick the query & chart
  • Verify the narrative fits the data
  • Live for every customer
Survey · Stats · Atlas · R

Verified R

≈ 16 min · reproducible code you own

The full build. Reproducible R, executed in a sandbox, put through ten quality checks, and self-healed before it ever ships.

  • Research the method
  • Write reproducible R
  • Run it in a sandbox
  • 10 quality checks
  • Self-heal on any failure
  • Deploy
Capstone · R

Assurance-grade

deepest tier · built for trust

Everything in the R tiers, plus an extra layer of assurance: the analysis is built several times independently and only what agrees moves forward.

  • Research the method
  • Build the analysis several times — independently
  • Check the results agree
  • Write & run reproducible R
  • 10 quality checks + self-heal
  • Independent methodology review
  • Deploy

Pick the depth your question deserves — the answer comes back independently verified either way. Compare all five tiers →

The numbers behind the pipeline

These are real, live numbers — pulled from our pipeline database. Every module, every build, every quality check is logged.

11
Modules built last 48 hours
Autonomously, no manual fixes
~16 min
Average build time
From question to deployed module
10
Quality checks per build
Files, metrics, charts, code, visuals
100%
Reproducible — same answer, every run
Deterministic R, fixed seeds, isolated containers

All numbers from devgen.agent_execution and devgen.module_pipeline, last 7 days. Verifiable on request.

Where the time goes

Average wall time for each stage across recent builds. The longest stage is the builder writing R code; the shortest is rendering the analysis itself.

SPEC
Research + design
5.5 min
BUILD
Write R code
5.3 min
RENDER
6 sec
VERIFY
10 quality checks
3.2 min
FIXER
Self-heal (when needed)
3.0 min
DEPLOY
Build + activate
1.8 min
Typical happy-path total: ~16 min

Add ~3 minutes when the fixer needs to recover. Add another ~3 if it needs a second cycle. Maximum recorded build with two fixer cycles: 36 minutes.

Self-healing builds

When the verifier finds a problem, the fixer diagnoses, patches, and retries automatically — and anything that doesn't clear verification never ships. You only ever see analyses that passed the checks.

1

Verifier flags the issue

The verifier reads every chart screenshot and runs 10 structural checks. It writes a detailed report with the exact failure and a recommended fix.

2

Fixer patches the code

A repair-specialist agent reads the verification report, identifies the file to edit, and applies a minimal, targeted change. No refactoring, no scope creep.

3

Re-render and re-verify

The patched module re-runs end-to-end. If the verifier passes, the build moves to deployment. If it fails again, the fixer cycles up to 3 times.

4

Backoff on persistent failures

If a module fails 3 times, the daemon abandons it with exponential backoff (5, 10, 20 min) and surfaces the failure — but keeps processing other modules.

Why this matters

Most analytics platforms ask you to either trust generated code that changes every run, or wait days for a human data scientist to write the analysis. This pipeline does neither.

Capability Manual analyst LLM code generation MCP Analytics pipeline
Time from question to deployed analysis 2-5 days Minutes (per chat session) ~16 minutes
Same answer on re-run If documented Different code each run Deterministic R code
Source code in the report Separate file Lost in chat session Code appendix in every report
Quality checks before deploy Whatever the analyst remembers No verification step 10 automated checks per build
Self-heals when something breaks Manual debugging Re-prompt the LLM Fixer cycles automatically
Builds new modules continuously Bottleneck One-off only Daemon picks up new submissions

Run analyses from the library

Every module in our library was built by this pipeline. Upload a CSV and the system picks the right one for your data — analysis runs in seconds, the report has the source code attached.

Run a free analysis →