Get This Tool
AI-Engineering-Coach
Summary
You add three AI coding assistants to your team, adoption looks healthy, and then someone asks which one actually generates code that ships — and you have no answer. AI Engineering Coach is Microsoft's open-source VS Code extension built to make that question answerable.
The extension passively analyzes AI coding assistant activity across your workspace and surfaces usage metrics, prompt patterns, and code generation volume in a single dashboard — without requiring any API or cloud dependency. It covers any AI coding harness, not just Copilot, so teams running a mix of tools get consolidated signal instead of siloed logs. The anti-pattern detection flags weak prompting habits before they calcify across the team. Where it breaks: this is a read-only observer, not an enforcer. The docs describe an 'agentic readiness audit' framing, but no task is executed on your behalf — you get diagnostics, not automation.
Bottom line: Reach for this when your engineering lead needs to defend AI tool spend with data; skip it when what you actually need is something that changes developer behavior rather than just measuring it.
Pricing Plans
FreeFree
Full access to dashboard and anti-pattern detection
- Local session log analysis
- 45+ anti-pattern detection rules
- Practice score tracking
- Activity charts and trends
- Context health auditing
View full pricing on github.com →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Vendor-agnostic log analysis covers any AI coding assistant in the workspace, so teams running Copilot alongside other tools get one consolidated view instead of reconciling separate dashboards.
- Passive observation with no API dependency means no credentials to rotate and no outbound data flow to clear with security — which removes the procurement blocker that stalls most analytics tool rollouts.
- Anti-pattern detection surfaces weak prompt habits at the team level, so tech leads can address systemic issues in code review rather than catching them one pull request at a time.
- Repeated prompt discovery and skill promotion gives teams a path from scattered individual prompts to a shared, reusable prompt library without leaving VS Code.
- Self-hosted deployment is supported, so organizations with strict data-residency requirements can run the analytics stack inside their own infrastructure rather than accepting a SaaS data-sharing agreement.
Cons
Sign in to edit- The tool produces diagnostics only — no enforcement, no automated feedback loop, and no way to block a weak prompt or flag a pattern before it hits the repository. Teams that need behavior change rather than measurement end up building a separate enforcement layer, at which point they are maintaining two systems.
- Because the extension reads local workspace logs passively, cross-team aggregation at the organization level is constrained by how logs are collected and shared. Teams operating across many repos or distributed environments report that assembling org-wide signal requires additional scripting — the extension's dashboard does not natively federate across workspaces.
- There is no API surface. Teams that want to pipe usage metrics into an existing observability stack — Datadog, Grafana, internal BI tooling — cannot pull data out programmatically. Organizations with mature engineering metrics programs that need AI coding data as a first-class signal alongside DORA metrics will move to a platform that exposes an API or native integration.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- VS Code
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-06-01T02:31:14.473Z
Best For
Who it's for
- Development teams using multiple AI coding assistants
- Engineering leaders optimizing AI tool adoption
- Individual developers improving prompt quality
- Organizations concerned with data privacy
- Teams analyzing code generation patterns
What it does well
- Track AI coding assistant usage metrics and trends
- Detect anti-patterns in prompt engineering and code review
- Measure AI-generated code volume across teams
- Audit workspace context and agentic readiness
- Discover and consolidate repeated prompts into reusable skills
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is AI-Engineering-Coach free?
- Yes — AI-Engineering-Coach is fully free to use. There is no paid tier.
- Is AI-Engineering-Coach open source?
- Yes. AI-Engineering-Coach is open source — the source repository is at https://github.com/microsoft/AI-Engineering-Coach.
- Can I self-host AI-Engineering-Coach?
- Yes. AI-Engineering-Coach supports self-hosting on your own infrastructure.
- What platforms does AI-Engineering-Coach support?
- AI-Engineering-Coach is available on: VS Code.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Most AI adoption dashboards require you to route traffic through a vendor proxy or wire up a separate SaaS account. AI Engineering Coach runs inside VS Code, reads local workspace and assistant logs passively, and produces a dashboard covering usage metrics, prompt quality signals, and AI-generated code volume across your team — no API key, no outbound telemetry dependency required. The core workflow is passive: install the extension, let it observe, and review the aggregated output. Repeated prompts that appear across the team can be promoted into reusable skills, giving teams a path from ad-hoc prompting to a shared prompt library without switching tools.
The differentiating feature is the anti-pattern detection layer. Rather than just counting completions accepted, the extension analyzes prompt structure and flags engineering habits that consistently produce weak outputs — giving tech leads something to act on in code review or onboarding, not just a usage graph to paste into a slide deck.
This tool fits teams that have already committed to AI-assisted development and need to audit what is actually happening before making the next tooling decision. It does not fit teams looking for enforcement: there is no policy layer, no blocking capability, and no way to push feedback back into developer workflow automatically. Teams that need behavior change at scale rather than measurement typically add a linting or review gate on top, or move to a vendor platform that includes workflow controls. Self-hosted deployment is supported, which addresses the data-residency concerns that prevent some organizations from using cloud-based analytics products.