Skip to content
See the details

Product lifecycle for AI.

Agents do better work with context they can trust. HELIX is a document discipline for teams building software with agents. It turns project intent and evidence into shared memory, then keeps that memory current as the work changes.

Start with HELIX Browse the catalog
A document spine double helix connecting human intent, AI execution, and governed artifacts.
Get started

Install HELIX in your runtime

HELIX works with Claude Code, Codex CLI, GitHub Copilot, and Databricks Code Genie. Pick the guide for your environment and you’re up in minutes.

Claude Code Install as a Claude Code skill User-global or per-repo. Installs the HELIX skill that reads project docs and proposes the next update. Codex CLI + Copilot Discover via AGENTS.md or editor instructions Use HELIX for codebase-aware planning in Codex and read-only guidance in Copilot surfaces. Databricks Code Genie Skill bundle in workspace storage Shared across the workspace, next to your data and notebook work.

Read the full install index

How it works

Start by installing HELIX into the tool where your agent works. The HELIX skill reads your project documents, finds missing or stale context, and proposes the next document update. You stay in control of what changes.

1 · Write the brief Capture the goal, requirements, constraints, and decisions before the agent starts changing files. 2 · Check alignment Find stale assumptions, missing context, and contradictions across your project documents. 3 · Create the work plan Turn the documents into bounded work: what to change, what to leave alone, and how to check success. 4 · Hand off to a runtime Send the plan to DDx, Claude, Codex, Databricks, or a manual workflow, then feed the result back into the documents.

See it in action

Artifact spine

HELIX includes many artifact types, but to get started you only need a few. Begin with the spine, then add supporting artifacts as the work demands them.

01Product VisionIntent 02PRDRequirements 03PrinciplesJudgment 04Feature SpecsScope 05ArchitectureStructure 06Test PlansProof 07Implementation PlansExecution

Use more than one flow scope

A product and its documentation site can both use HELIX. Declare separate flow scopes, meaning separate roots for separate sets of HELIX documents, and use the same HELIX skill for both.

Multiple document scopes Product docs and microsite docs can live side by side Learn how one repository can keep product documents and website documents separate. HELIX example docs HELIX renders its own docs as a separate example corpus See how this repository uses HELIX without treating those pages as setup instructions.
Runtime paths

Use HELIX where your team already works

HELIX is Markdown and method. The runtime, meaning the tool doing the work, supplies file editing, review, execution, and evidence capture.

Manual Small teams adopting the method first Start with Markdown, reviews, and explicit prompts before adding queue automation. Claude Code Interactive artifact review and editing Ask an agent to reconcile documents, propose patches, and explain open questions. Codex Codebase-aware planning and implementation Use the artifact spine to guide bounded code changes and implementation plans. DDx Reference runtime for queued execution Map HELIX plans to DDx work items when queue control and execution evidence matter. Databricks Data and governance workflows Apply HELIX artifacts to analytical systems, platform work, and managed evidence.
Proof

Inspect the foundations

The method is public: the document-pattern catalog, research foundation, and HELIX’s own example docs are all inspectable. Use the example docs to see the method in practice; use the catalog and guides to apply it to your project.

HELIX example docs HELIX governs itself in public Read HELIX's own project documents and follow links back to their source files. Artifact-type catalog Reusable prompts, templates, and quality guidance Browse the document types and learn which ones are core versus supporting. Research foundations Why document-driven AI work needs governance Trace the methodology back to the research and operating assumptions that shaped it.