AI Code Insights
AI Code Insights measures what AI coding agents produce inside an engineering organization, tracking AI-generated code by commit, PR, team, agent and repo from IDE to production. It attributes authorship by monitoring supported coding agents' edits and links them to commits, pull requests and deployments, reporting adoption, delivery velocity, code-quality signals and session-level agent performance. It includes the Agent Experience report, which scores requirements clarity, steering and task scope from the agent's perspective.
Find alternatives to AI Code Insights
What it does
- Evaluation and observability
- Data analysis
Features 8
- Local-first, line-level metricsIdentifies AI versus human code locally without source code leaving the machine.
- Cross-tool AI code viewSingle view of AI code across Claude Code, Cursor, Copilot and more, by team, repo, tool and period.
- AI code outcome linkageConnects AI code to outcomes such as cycle time, revert rate, throughput and review burden.
- Agent Experience ScoreAgent Experience Score helps teams identify patterns in how developers collaborate with AI, not just how often they use it.
- AI Code Overview reportThe AI Code Overview report shows SDLC lifecycle metrics bucketed by the percentage of AI in each pull request.
- AI dollar impact reportThe AI dollar impact report translates AI tool investment into an estimated net dollar figure.
- DaemonA lightweight, self-hosted daemon runs on developer machines across macOS, Windows and Linux to power AI Code Insights.
- Self-hosted processorThe self-hosted processor keeps AI Code Insights session transcripts inside the customer's network.
Sources
- Pricing
-
Modular, developer-license-based, quote-only; no figures published.
- Description
-
Official documentation · 5 Sep 2026
'AI coding agents are writing code across your organization every day. AI Code Insights shows you what they produce, how they work, and where they get stuck.' Marketing H1: 'Track AI code from IDE to production'.
- What it does
-
Official documentation · 5 Sep 2026
Tracks code authorship attribution across supported coding agents; measures adoption, delivery velocity, code quality signals and session-level agent performance. Six reports including Agent Experience. 'Transcript retention and analysis are optional and off by default.'
- Constraints
-
Derived from the security facts on this page, from the same source.
- Security
-
Platform-wide DX security page; dx-cli and dx-mcp-server left out (not stated). GDPR compliance and DPF certification stated but no DPA page, so gdpr-dpa not recorded. 'Directory sync' not recorded as SCIM. Training/ZDR/residency not stated.
- Sold within
-
Official documentation · 5 Sep 2026
Listed in the DX Products nav under the AI Measurement grouping, within the single DX developer intelligence platform.
- Intended for
-
"The most innovative engineering organizations run on DX"; named case studies CTO Adyen, CTO Vanguard, Sr. Director Booking.com; tracks individual "Developer Self-service"
Also from DX
-
DX AI Application
DX AI is a conversational interface for exploring an organization's engineering data held in DX, described by the vendor as 'the copilot for engineering leaders.' It answers natural-language questions with generated charts, summarizes qualitative snapshot data into themes and sentiment, and diagnoses the drivers behind metric changes. Its data can also be streamed into external LLM clients via the DX MCP server.
-
Fabric Developer tool
Fabric is DX's context layer for AI agents, marketed as 'the context engine for AI-native engineering.' It turns an organization's software catalog into structured, live context that agents can query, and adds scorecards and self-service automation so agents can create services, provision infrastructure and resolve failing standards checks. Context is exposed to any MCP-compatible agent via the DX MCP server.
-
DX MCP Server API service
The DX MCP server exposes a customer's DX data to MCP-compatible AI clients such as Claude, Cursor and Devin Desktop. It is deliberately read-only, offering tools to list and retrieve software catalog entities, scorecards and initiatives, and teams, plus execution of SQL queries against the DX Data Cloud PostgreSQL database. It is available as a DX-hosted remote endpoint at ai.getdx.com/mcp or run locally from DX's open-source dx-mcp-server repository.
-
DX CLI Developer tool
Command-line interface to a DX instance, built so coding agents can drive it: it ships an agent skill telling an agent when and how to call the CLI, and covers the same catalog, scorecard and self-service operations a human uses the dashboard for.
-
TrueThroughput Application
Uses AI to weight pull requests by complexity to measure engineering output.
Something wrong here? Send a correction — quote this product id: dx-ai-code-insights.