The Datamap provides automated data mapping, discovery, and classification of sensitive dataflows across all your repositories. It gives privacy teams a live, code-level view of where sensitive data is collected, processed, and shared — including flows into AI and third-party integrations that questionnaire-based approaches typically miss — covering both safe and risky data sinks.
When an AI integration is enabled, a chat panel on the left side of the Datamap lets you query your organization-wide datamap in plain English. Instead of building filters by hand, ask where sensitive data goes and HoundDog.ai searches your dataflows, answers in chat, and opens the matching, pre-filtered Datamap view next to the conversation.
Without AI, the Datamap is still available, built from the scanner’s deterministic findings. You can apply the same advanced filters to search for dataflows; there is no chat panel and no AI review.
Asking Questions in Plain English
Section titled “Asking Questions in Plain English”Typical questions come from different teams:
- An AppSec engineer asks where auth tokens are leaking in plaintext into application logs.
- A privacy engineer asks which third-party integrations receive PII.
- An AI governance team asks which AI integrations exist and what sensitive data reaches them.
Type a question in the prompt box, or start from one of the suggestions shown on an empty chat, such as:
- Which repositories handle medical data?
- Show me the most severe open risky dataflows right now.
- Which third parties receive PII?
- Which AI services receive sensitive data in our code?
- What data elements are present in my code?
A model selector below the prompt box shows which provider and model answer the question. The chat is read-only: it searches and opens views, but never changes your data.
For example, asking “Which third parties receive PII?” makes HoundDog.ai search the datamap and reply with the matching third-party integrations, the sensitive data elements involved, their sensitivity, the repositories, and whether each flow is risky. It then opens the filtered Data Sinks view so you can inspect the same results in the Datamap’s flowchart and table.
Asking “Which AI services receive sensitive data in our code?” works the same way for AI integrations, and also calls out AI integrations that are detected in code but receive no sensitive data.
Previous conversations are kept so you can return to them from the history button at the top of the chat, and the layout buttons let you resize or collapse the conversation and Datamap panes.
How It Works
Section titled “How It Works”The scanner stays deterministic: it discovers the sensitive data flows in your code, and the datamap is built from those results. The chat adds a natural-language interface on top of that evidence: its answers are grounded in the dataflows already in your datamap, not in new detections.
On the Cloud Platform, the chat runs on the HoundDog.ai-managed model out of the box. Cloud and self-hosted organizations can also connect their own AI provider and API key, in which case each question, along with the datamap data needed to answer it, is sent directly to that provider under the DPA and terms your organization holds with it. See AI Integration for the data AI features send.
Enabling the Chat
Section titled “Enabling the Chat”- Make sure an AI integration is Active under Settings → AI. On the Cloud Platform, the HoundDog.ai-managed integration is active by default. To use your own provider instead — Anthropic, AWS Bedrock, Google Gemini, Microsoft Azure OpenAI, or OpenAI — add it and mark it Active. See Provider Integrations.
- Turn on the Enable AI Assistant toggle on the same page.
Once enabled, the chat panel appears on the left side of the Datamap. On a Self-Hosted Platform there is no managed model, so adding your own provider integration is required.
- Name the data you care about — a data element such as Auth Token or a sensitivity level — and the destination, such as logs, third parties, or AI integrations.
- Use the opened Datamap view to verify an answer, and triage the underlying findings on the Dataflows page.
- Answers come only from scanned repositories. If a repository is missing from the results, make sure it has completed an authenticated scan and appears under Repositories.
The Datamap offers two flowchart views and four table views:
| View | Description |
|---|---|
| Flowchart: Left to Right | Data elements on the left flowing into data sinks on the right. |
| Flowchart: Top Down | The same flow rendered vertically — the default on tall viewports. |
| Table: Data Elements | All detected data elements, with the repositories and sinks they touch. |
| Table: Data Sinks | All detected data sinks, with the data elements they receive. |
| Table: Repositories | Repositories with their dataflow counts by severity, detected data elements, and data sinks. |
| Table: Dataflows | The underlying dataflows in tabular form. |
Filters for Repository (and branch), Data Element, Data Element Sensitivity, Data Element Tag, Data Sink, Data Sink Tag, and Dataflow Severity apply across views. A Dataflow Status filter is available on the Table: Dataflows view. Each view answers a different kind of question:
- By repository — select several repositories (say, backend, frontend, and an authentication service) to get a comprehensive view of every dataflow across them.
- By data element — “show me every repository where Social Security Number is processed” and every sink it may be exposed to.
- By data sink — “show me all sensitive data sent to OpenAI across the organization.”
The flowchart views place data elements on one side and data sinks on the other, with dataflow counts on every edge and risky sinks highlighted. By default, the middle column represents all of your organization’s repositories; select specific repositories in the filters to narrow it to just those.
Drilling Down
Section titled “Drilling Down”You can drill down into the detected data elements, by the sensitivity of the data elements or by the severity of the dataflows going into the detected data sinks — either by applying filters yourself or by asking in the chat. For example, the screenshot below asks for the most severe open risky dataflows: the chat summarizes them by repository, data sink, and data element, and opens the Table: Dataflows view filtered to the top severity and Open status, with each flow’s status, AI review status, data elements, data sink, and code location.
