The spec is executable
Testable statements and scenarios, so the build has a definition of done from the first minute.
For the person who will be asked how it actually works. Outline, the factory behind it, and the platform they both run on.
One spec is the source of truth throughout. Outline, the factory and the application all query the same data and knowledge platforms through MCP.
A fast model runs the conversation, so it keeps up with speech. A frontier model reads the transcript as it grows and feeds back the gaps and contradictions. Better at spotting the hole, too slow to talk.
| Source | How Outline uses it |
|---|---|
| Your data platform | Every entity, field or rule you name is checked against the live data. |
| Your knowledge base | Documents, prior interviews and expert corrections. |
| Screen mock-ups | Drawn as you talk, in your brand, confirmed by you. |
A specification folder any team can read and any agent can build from: testable requirements, acceptance scenarios, flows with their exceptions. You own it.
EARS statements, Gherkin scenarios, Cockburn-style flows, a Volere-style requirement shell, ISO/IEC/IEEE 29148 as the coverage model, serialised as a Spec Kit / Kiro shaped Markdown folder.
Agents plan from the spec, build against the platform, and run its acceptance scenarios as tests. What fails goes back round. An inmydata engineer reviews what passes.
Testable statements and scenarios, so the build has a definition of done from the first minute.
Data, auth, access control and knowledge retrieval come from the platform, not the application.
Parts that pass review are reused. Early applications take days; later ones take less.
Spoken, checked against your data.
Approved by you. The source of truth.
Agents build and test. An engineer reviews.
Screens and agents on live data, in our cloud or yours.
Every build runs through gates we record, and the software shows its working. Read how we build.
Connects to the systems you already run, including the legacy ones most AI tooling cannot reach. A semantic layer a model can understand, sub-second queries, row-level security on every one. One MCP interface serves the interview, the build and the application.
| Capability | What it means in practice |
|---|---|
| Real-time connectors | Change data capture, no batch loads. |
| Semantic layer | "Overdue orders" means what your finance team means. |
| Sub-second queries | Many questions per decision. |
| Row-level security | Applied once, inherited by every application and agent. |
| Runs where you need it | Our cloud, your cloud, or a Windows or Linux server on your premises. |
Most of how a business runs is in people, not systems. The knowledge platform captures it through AI-led interviews and the documents you already have, and keeps it retrieved, not just stored. Outline builds from it. The application runs on it.
| Capability | What it means in practice |
|---|---|
| Expert interviews | By voice, over as many sessions as it takes. |
| Document ingestion | Policies, procedures, wikis and email threads. |
| Hybrid retrieval | The passage that answers, not the one that matches. |
| A base that learns | Contradictions consolidated, gaps asked about, expert corrections win. |
The business, the platform and the models all change under an application. Each is a routine event with a known path, not an incident.
| What changes | What happens |
|---|---|
| The business | Describe it to Outline. Spec updated, delta built, full suite run. |
| The platform | Patches roll out across every tenant, each application’s tests first. |
| The models | Tested against each application’s scenarios before it is switched. |
| Your schema | The semantic layer absorbs most of it. The rest is regenerated from the spec. |
| Your knowledge | Corrections and new documents flow in continuously, without a release. |
We are opening the data platform and the knowledge platform: run them yourself, read the code, leave with everything intact. We charge for the factory and for keeping your software right.
| Point | Detail |
|---|---|
| Access control | Row- and column-level security, inherited by everything on the platform. |
| Your data | Yours outright. Deleted shortly after termination. DPA in the standard terms. |
| Audit | Every query and agent action is logged. Logs on request. |
| Certifications | None yet. SOC 2 compliance is a design goal. Listed when held, not before. |
| Models | Your choice of provider where allowed, billed to your own key. |
Bring your architect. Half an hour on your data, your security model and what the factory can’t do yet.