# Waydev Brain: Private 15B AI Engineering Intelligence Source: https://waydev.co/waydev-brain/ Last updated: 2026-10-29 Publisher: Waydev Waydev Brain · Powered by Waydev 15B # Ask your engineering data anything.Nothing leaves your network. Waydev Brain helps engineering leaders ask questions across delivery performance, AI adoption and engineering investment. With a privately deployed Waydev 15B configuration, inference runs in your controlled environment rather than through an external model API. Deployment architecture and data flows are reviewed with your security team. [Request an enterprise demo](https://waydev.co/demo/) Read the technical overview 15B SDLC model Public cloud - Git repositories - Issue trackers - CI/CD pipelines - AI coding tools - Delivery risk - AI-assisted work - Spend and outcomes Model 15B parameters, SDLC-trained Deployment Air-gapped option Data residency Inside your perimeter Agents Specialized for engineering work Waydev 15B deployment: 9 in 10 answers right in Waydev internal tests · 53% fewer incorrect answers than the base model · One 16 GB GPU minimum · No per-token model API fees. Review the benchmark methodology. ## Waydev 15B: engineering intelligence, tested against engineering questions **Waydev-reported evaluation:** approximately 9 in 10 answers correct, with 53% fewer incorrect answers than the same base open-source model before domain training. The release benchmark has 104 frozen cases, repeated three times per case; numeric answers are checked against reference queries. These are Waydev’s internal test results, not an independent third-party benchmark. How Waydev tests each release · Hardware requirements · [Request an enterprise demo](https://waydev.co/demo/) ## Why we built Waydev Brain Engineering leaders should be able to ask “Why did cycle time go up last sprint?” and get a trustworthy answer from their own engineering data. Sending sensitive repository metadata, tickets, developer activity or internal delivery metrics to an outside AI API is not acceptable for every organization. - **Security:** Some organizations prohibit sending source-code metadata and developer activity to external model providers. - **Privacy and employee representation:** Works Councils and EU privacy obligations can constrain how identifiable developer information is used. - **Regulated deployment:** Banks and other regulated organizations may require AI inference to stay inside infrastructure they control. - **Accuracy:** General-purpose models may confuse metric definitions and database schemas. Waydev 15B is tuned for Waydev’s data model and analytical tasks. ## What Brain does for each team Team Problem today With Waydev Brain Engineering leaders Need an analyst or custom report Ask questions in natural language and receive data-backed metrics, charts or widgets. Security and IT External AI services may be blocked Run Waydev 15B locally on your GPU without external model-provider calls in the air-gapped configuration. Works Councils and HR Individual performance information needs protection Works Council mode supports team-level responses and anonymization controls. Finance Variable third-party model usage fees Local model inference with infrastructure costs instead of per-token model API fees. Platform teams Generic AI guesses metric and schema definitions Waydev-domain training covers metric definitions, data models and supported tools. ## What Waydev Brain can do - **Ask your data:** ask about pull requests, commits, issues, deployments, teams and AI usage through [Waydev Agent documentation](https://docs.waydev.co/v5.0/docs/waydev-agent). The Agent supports natural-language analysis and engineering evidence. - **Understand metrics:** DORA, cycle time, review workload, allocation and AI adoption, with definitions and context. See the [DORA, SPACE and DX guide](https://waydev.co/engineering-metrics-frameworks/). - **Explain and predict:** investigate changes in trends and estimate where metrics may be heading, distinguishing forecasts from observed facts. - **Widgets and SQL:** use the Waydev Agent’s conversational widget creation and SQL workflow to build analyses from natural-language descriptions. The [Dashboards guide](https://docs.waydev.co/v5.0/docs/dashboards) documents seven widget types: metric cards, radial bars, metrics tables, charts, metric focus, heatmaps and composite time metrics. Widgets support metric selection, live preview and scoped filters. See also [Prompt Dashboards](https://waydev.co/features/prompt-dashboards/). - **PR review and coding assistance:** review diffs and answer supported coding questions. **Engineering data foundations:** see the [Waydev SDLC documentation](https://docs.waydev.co/v5.0/docs/waydev-sdlc) for the engineering data context and the [Agent guide](https://docs.waydev.co/v5.0/docs/waydev-agent) for asking questions of it. Dashboard access can be public within a workspace or private with explicit per-user view and edit permissions, as described in the [dashboard access documentation](https://docs.waydev.co/v5.0/docs/dashboards). Related capabilities: [Signals](https://waydev.co/features/signals/), [Goals](https://waydev.co/features/goals/), and [AI coding ROI research](https://waydev.co/ai-coding-roi-research/). Product direction · Exploring ## From engineering data to continuous engineering context Every pull request, issue and deployment tells part of the story. The reasoning behind decisions, constraints and trade-offs often lives in conversations or AI coding sessions that are harder to find later. Our vision for Waydev Brain is to connect the *what changed* with the *why it changed* across engineering teams and tools. ### What persistent engineering context could unlock - **Decision history:** link delivery changes to relevant issues, reviews and documented decisions so new team members can understand the reasoning behind them. - **Context across agents and teams:** explore ways to make approved engineering knowledge reusable between human and AI-assisted workflows instead of rediscovering it in each session. - **Evidence for engineering leaders:** connect historical context with cycle time, quality, AI adoption and investment metrics to explain trends and trade-offs. - **Enterprise controls:** design for permission-aware retrieval, retention policies and private deployment requirements. **Example:** If a billing change causes a regression, imagine asking Brain which prior changes affected the calculation, what related issues and tests revealed, and how the change affected delivery metrics—all with links to the underlying evidence. **Forward-looking concept:** This section describes a product direction, not a currently available feature. Waydev Brain is not represented here as recording AI agent sessions, syncing prompts into Git or providing repository-backed persistent memory today. [Discuss your enterprise use case with Waydev](https://waydev.co/demo/) ## Built on over a decade of engineering analytics Waydev 15B is specialized using questions from engineering analytics, Waydev metric definitions, the Waydev data model and privacy requirements. According to Waydev’s technical training process, each model iteration uses approximately **1,500 checked conversations**. Training examples with numerical results are validated against reference queries; examples that fail the checks are excluded. ## Proven before each release **Waydev-reported results:** approximately 90% correct answers and 53% fewer wrong answers than the unmodified base model on its internal engineering-question benchmark. Waydev’s release gate uses **104 frozen test cases** run **three times per case**. Each release must outperform the current version without any tested skill area dropping by more than 10 points. Numerical outputs are verified against reference queries rather than by visual judgment. Waydev 15B is currently described as version 3. These figures describe Waydev’s internal evaluation under its stated test conditions. They are not a guarantee of accuracy for every customer dataset, language or workflow. ## Private by design - **Local inference:** a roughly 9 GB model file runs on an NVIDIA GPU on-premises or in your private cloud. An appropriately configured air-gapped installation does not need internet access for inference. - **No outside AI model calls:** when the local Waydev 15B provider is selected, requests need not be sent to OpenAI, Anthropic or other external model APIs. - **Existing access controls:** data retrieval is designed to use Waydev permission checks. For example, the [dashboard documentation](https://docs.waydev.co/v5.0/docs/dashboards) specifies private/public visibility and per-user Can View and Can Edit permissions. Validate model and tool-level access enforcement in the enterprise deployment review. - **Auditable requests:** logs identify the model, skill and requesting user. - **No automatic customer-data training:** an on-premise installation does not send customer prompts or engineering data to Waydev for model training. Architecture and data-egress requirements should be validated against the specific customer’s network and integration setup. See [Waydev Security](https://waydev.co/security/). ## Built for EU privacy requirements and Works Councils Requirement Waydev Brain support Third-country data transfer control Local inference keeps model requests on customer-controlled infrastructure when configured for air-gapped operation. No individual rankings Works Council mode is intended to keep responses at team level and refuse developer ranking requests. Data minimization Anonymization can hide colleague names so reporting emphasizes team patterns. Transparency and accountability Model, skill and user are recorded for each AI request. Works Council mode is configured at account level and may be documented in an employee-representation agreement. These features support governance but do not replace a GDPR, employment-law or EU AI Act assessment. ## A private model for your company For enterprise deployments, Waydev can tailor a private Waydev 15B model to your engineering terminology, metric definitions, technology stack, processes, documentation and privacy rules. A custom model is evaluated against Waydev’s benchmark plus customer-specific tests. - **Workshop:** agree on leadership questions, metrics and privacy constraints. - **Verified training data:** generate examples from the approved environment and aggregate or anonymize them first. - **Your benchmark:** add customer acceptance questions to the release gate. - **Private delivery:** deliver a dedicated model artifact for your environment, with updates governed by the agreed release process. ## What you need to run Waydev 15B Deployment GPU memory Context window Parallel requests Minimum 16 GB, NVIDIA L4 class 64,000 tokens 4 Recommended 48 GB, NVIDIA L40S class 128,000 tokens 6 Linux, CUDA 12+ and 30 GB available disk space. Internet access is not required for local inference. Actual throughput and context availability depend on the configuration and workload. ## Frequently asked questions ### What is Waydev 15B designed to do? Waydev 15B is specialized for engineering analytics questions, metric definitions and software delivery data. It is not intended to replace a general-purpose model for every task. Depending on your organization’s policies and configuration, other model providers may also be available in Settings. ### Does our data train the model? No. In an on-premises deployment, customer prompts and engineering data are not sent back to Waydev for model training. ### Can it run without a GPU? Not at a practical production inference speed. A supported NVIDIA GPU with 16 GB VRAM is the stated minimum. ### Which languages are supported? English is standard. Other languages can be considered as part of a custom build. ### What does Waydev Brain cost? Enterprise pricing is private and depends on deployment, scale and customization. There are no third-party per-token API fees when running local Waydev 15B, but infrastructure, support and licensing costs still apply. ## Run Waydev Brain on your own data, inside your own network. See what your engineering leaders can ask, how answers are grounded and how the model runs in your environment. [Request an enterprise demo →](https://waydev.co/demo/)