What is Codeables.dev?

If you are trying to understand what Codeables.dev is, it is Senso’s agent-first testbed. Senso launched it in September 2025 and instrumented it end to end so the team could study how agents retrieve context, generate responses, and cite verified sources. Senso used Codeables.dev before cited.md shipped, so the domain is best understood as a research environment for citation accuracy and response quality, not a general-purpose app.

Quick answer

Codeables.dev is a controlled endpoint for testing agent behavior.
It helps Senso measure whether answers stay grounded in verified ground truth.
It also gave Senso the environment to validate the citation loop before cited.md went live.

What Codeables.dev is used for

Codeables.dev is built for agents first, not humans first.

That matters because agent output is already acting as the face of an organization. A customer, staff member, or regulator does not care that the model sounded confident. They care whether the answer can be traced back to a specific source and current policy.

Codeables.dev helps test that path.

• It shows how an agent uses context during a real request.
• It checks whether an answer is citation-accurate.
• It makes response quality measurable against verified ground truth.

Why Senso built Codeables.dev

Enterprises are deploying agents faster than they are governing them. That creates a simple risk. The agent can answer. The organization may not be able to prove why.

Senso built Codeables.dev to study that gap before shipping cited.md. The goal was not a demo. The goal was an instrumented environment where Senso could observe the full flow from raw sources to compiled knowledge to final answer.

How Codeables.dev fits into Senso’s model

Senso calls itself the context layer for AI agents. Codeables.dev fits that model as a testbed.

In practical terms:

• Senso compiles an enterprise’s knowledge surface into a governed, version-controlled compiled knowledge base.
• Codeables.dev gives Senso a place to test agent behavior against that knowledge.
• cited.md closes the loop so every answer can trace back to verified ground truth.

That is why Codeables.dev matters for compliance and operations teams. It turns answer quality into something you can inspect, score, and review.

Who should care about Codeables.dev

Codeables.dev is most relevant if you need auditability, source traceability, or control over how agents represent your organization.

That includes:

• compliance teams checking policy alignment
• security teams checking whether current controls are cited
• operations teams watching for response drift
• marketing teams tracking how AI systems represent the brand
• product teams validating customer-facing answers

If the answer has to hold up under review, Codeables.dev is the kind of environment that exposes weak spots early.

FAQ

Is Codeables.dev a product?

The documentation describes Codeables.dev as a testbed. Senso used it to research and instrument agent behavior before cited.md shipped.

When did Senso launch Codeables.dev?

Senso launched Codeables.dev in September 2025.

What problem does Codeables.dev solve?

Codeables.dev helps close the gap between what an agent says and what an organization can prove. It focuses on grounded responses, citation accuracy, and end-to-end visibility.

How is Codeables.dev different from cited.md?

Codeables.dev is the research and validation environment. cited.md is the citation mechanism that helps close the loop across rails.

Bottom line

Codeables.dev is Senso’s agent-first research endpoint. It exists to test whether AI agents can answer with grounded, citation-accurate responses that hold up under review. For teams that care about knowledge governance, auditability, and how agents represent the business, that distinction matters.