Skip to main content
Practical Guides

How Should Copilot “Chat-First” Metrics Be Read? A Durable 28-Day Engagement Guide

The dashboard now covers nine experiences, but Chat and VS Code Agents do not change adoption phases, and one user can count in multiple features

ENHE AI5 min7 views

GitHub updated the Copilot impact dashboard on 2026-11-06 by adding Copilot Chat and the VS Code Agents window to feature engagement and renaming the “Passive users” cohort to “Chat-first users.” The engagement rule remains use on at least two days in a twenty-eight-day period. One person can be counted under more than one feature, and Chat or the Agents window does not change adoption phases; the API still reports Chat-first users as No Cohort. This durable guide explains how to keep the denominator, window, feature overlap, access scope, and before-and-after compatibility visible, then pair engagement with task quality and human review instead of presenting usage as business value.

More topic tags (7)
AI NewsAuto PublishingGEOCopilot Impact DashboardCopilot Chat-first指标28天参与度VS Code Agents usage
How Should Copilot “Chat-First” Metrics Be Read? A Durable 28-Day Engagement Guide

Key takeaways

The dashboard now covers nine Copilot experiences and renames “Passive users” to “Chat-first users.”
Engagement means use on at least two days in twenty-eight days, and one user can appear in multiple feature counts.
Chat and the VS Code Agents window do not change adoption phases, and usage is not quality or business value.

By ENHE AI · 2026-11-09 · AI-assisted drafting and editorial checks.

Direct answer: Chat-first does not mean low-value user

The new name describes a usage pattern: the person uses Copilot but has not used a qualifying adoption-phase feature on at least two days in the twenty-eight-day window. It is not a performance grade and does not show that the person completed no valuable work.

GitHub says Chat and the VS Code Agents window enter feature engagement but do not change adoption phases; the API still reports Chat-first as No Cohort. Reports need to preserve that boundary.

Nine experiences, the window, and the denominator

After adding Chat and the VS Code Agents window, the dashboard covers nine features. Engagement requires use of a feature on at least two days in the twenty-eight-day period. A report should state the organization, eligible population, observed population, window dates, and generation time.

The numerator may be engaged users for a feature. The denominator depends on the question: assigned seats, active developers, or observable users under the metrics policy. Ratios with different denominators are not directly comparable.

A chart discussion represents interpretation of 28-day metrics. Contextual stock photo, not customer usage data or proof of impact. Image: Unsplash.
A chart discussion represents interpretation of 28-day metrics. Contextual stock photo, not customer usage data or proof of impact. Image: Unsplash.

Why feature counts must not be added

GitHub explicitly says one user may count under more than one feature. A person using Chat, code completion, and the Agents window in the same period appears in three feature counts. Adding all nine feature counts double-counts people.

Present feature engagement separately. When unique people are needed, use deduplicated user-level data or an explicit unique-user measure from the product. If deduplication is unavailable, mark it unknown rather than estimating.

How to compare periods

Reports before the update lack Chat and VS Code Agents and use a different cohort name. For trends, preserve a seven-feature comparable view alongside the new nine-feature view, or compare only shared features. Do not attribute all increase after scope expansion to adoption growth.

Record the data version, export date, window, seat changes, organizational changes, and policy settings for every review. Mark definition changes on charts instead of backfilling an apparently continuous line.

Move from engagement to task value

Engagement answers which surfaces were used. It does not answer whether code became more correct, cycle time improved, or cost was reasonable. Choose one task family and separately track acceptance, human correction, delivery time, AI credits, and failure.

A review can show Chat engagement, Agents-window engagement, and movement among comparable features, then add quality and cost for one concrete task. Without task outcomes, report adoption signals only and do not claim business-value improvement.

FAQ

Can Chat-first or feature counts be added together?

Not directly. One user can appear in multiple feature counts, so unique people require a deduplicated measure.

Do adoption phases rise automatically because of Chat use?

No. The update adds Chat and VS Code Agents to feature engagement, but they do not count toward adoption phases.

Related tools and reading

These pages support the same task, workflow, or decision boundary.

Conclusion

Place the denominator, twenty-eight-day window, feature overlap, access, and version change beside the report. Present engagement separately from task quality, human correction, cycle time, and cost. A metric can guide questions; it cannot prove value alone.

What this means for everyday users

Reports before the update lack Chat and VS Code Agents and use a different cohort name. For trends, preserve a seven-feature comparable view alongside the new nine-feature view, or compare only shared features. Do not attribute all increase after scope expansion to adoption growth.

Related reading

GitHub Copilot Usage API Names Custom Skills, Agents, and MCP Servers: How to Read the Report

GitHub updated the Copilot usage metrics API on October 22, 2026, so customer-defined skills, agents, MCP servers, slash commands, and plugins can appear by configured name instead of being grouped entirely under other or custom. Each totals_by_* list now includes as many as 25 entries per record, up from five. This article helps administrators turn the change into a reliable adoption report. It covers required Copilot CLI and SDK versions, a naming review before reports are shared, one-day and 28-day comparisons, and a reconciliation check against known pilots. It also explains why historical days, path-like names, outdated clients, and blocked telemetry can still undercount activity. The metrics are useful for trends and enablement, not exact billing.

GitHub Copilot Impact Dashboard Adds Industry Comparisons: How to Read the Median and Top Decile

GitHub added an Industry comparison section to the Copilot impact dashboard on October 22, 2026. Eligible enterprises and standalone organizations can opt in to compare agent-first or multi-agent adoption and pull-request merge-rate leverage with aggregated participating peers. When enough peers participate, scores are placed against a 28-day median and, as the group grows, a top-decile reference. This article explains how to decide whether to opt in and how to avoid overreading the result. It covers company-size and industry groups, fallback to broader peer groups when samples are small, regional separation for data-residency customers, daily refreshes, and 30-day deletion of aggregated benchmarks. The comparison is context for planning, not a complete industry census or employee ranking.

GitHub Copilot Metrics Add OpenCode and Other Clients: Requests Are Not Prompts

GitHub added totals_by_client to the Copilot usage metrics API on October 23, 2026. Enterprise and organization reports can now show model traffic from OpenCode, Claude Code, Codex, Zed, Copilot CLI, GitHub apps, cloud agents, code review, VS Code, JetBrains, and other clients. This article helps administrators build reliable one-day and 28-day reports without confusing model calls with user prompts. It explains request, session, token, model, and selection-mode fields; separates client traffic from agent-app jobs; and adds checks for unknown identifiers, empty arrays, permissions, and coverage. The result is a governance trend report, not an exact invoice or individual productivity score.

What Still Works After Turning Off Generative AI in Canva? A Three-Layer Controls Guide

Canva launched two AI controls for Free and Pro users on November 19, 2026. One hides generative AI features, while the other reduces AI-generated assets in library search and recommendations. They control different surfaces. Assistive editing tools such as Background Remover and Magic Grab remain available when generative features are off. This durable guide separates three layers: generating new content, editing existing content, and discovering library assets. For each layer, record the setting path, expected change, effect on existing designs, labeling behavior, and rollback. The method helps creators adjust Canva to their preferred workflow without assuming that every AI-related tool, existing design, or metadata rule is removed by a single switch.

How Do You Delegate an Outcome to an AI Agent? An Autopilot Acceptance Contract

Microsoft presents Autopilot as a personal teammate with identity, memory, a workspace, and a remote computer that can continue cloud work without the user laptop remaining open. The product framing emphasizes delegating outcomes rather than scripting every action. This durable guide turns that idea into an acceptance contract for any long-running agent: state the objective and exclusions, bound data, accounts, spending, and external communication, define evidence and human approval at each milestone, set escalation, budget, and stop conditions, and accept work from inspectable artifacts rather than the agent’s own status claim. It is a reusable governance pattern, not proof that the Microsoft preview was enabled or tested.

How Should You Maintain ChatGPT Business Hub? Use Four Registers for Profile, Products, Insights, and Agents

OpenAI introduced Business Hub and Business Agents in beta on November 10, 2026. Businesses can claim and update their information, provide product feeds, and view aggregated mentions, clicks, and discovery topics when privacy thresholds are met. Eligible United States ecommerce and online-service businesses can also offer clearly labeled Business Agents. This durable guide turns setup into four maintenance registers: business profile, product feed, aggregated insights, and agent answers. Each register names the source, owner, refresh frequency, exception signal, and human review. The routine prevents a one-time claim from becoming stale and avoids interpreting aggregated trends as individual conversations. It is based on public documentation and did not claim a real business account.