The Build Pipeline

Every analysis is
autonomously built.
And it shows.

Each module in our library was built by a pipeline of specialized agents — research, code, render, verify, deploy. No human typed it. No LLM hallucinated it. The same code runs the same way for every customer, every time.

~16 min
Average build time
11
Modules built last 48h
100%
Self-healing recovery rate

Five stages. One daemon.

Each module goes through five specialized stages, each handled by an agent with a single job. The whole flow is orchestrated by a daemon that runs continuously and processes new builds in parallel.

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 numbers behind the library

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%
Self-healing recovery rate
5/5 builds with issues recovered

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 doesn't escalate to a human — it diagnoses, patches, and retries. Of the 5 builds where the verifier found issues, all 5 recovered automatically. 100% recovery rate.

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 →