# PostHog AI Product Analyst That Ships Fixes Give a Replicas cloud coding agent access to PostHog and your repository. It can investigate product behavior, trace the relevant code, make a change, run checks, and return a reviewable pull request or technical report. - Canonical: https://tryreplicas.com/use-cases/posthog-ai-product-engineer - Start a workspace: https://tryreplicas.com/auth?mode=signup - PostHog setup: https://docs.tryreplicas.com/features/plugins ## What is a PostHog AI product analyst? A PostHog AI product analyst is a cloud coding agent that uses product analytics as engineering context. It can inspect PostHog projects, events, insights, dashboards, feature flags, and recordings, then connect that evidence to the repository where the product behavior is implemented. Replicas remains a coding agent throughout the workflow. The goal is not another dashboard summary. The goal is a verified code change, a pull request, or a technical investigation that tells an engineer exactly what to do next. ## From product signal to reviewable software work Product analytics explains what users did. The codebase explains why the product behaved that way. A coding agent can work across both sides of that boundary. - **Start with a product question:** Ask why a funnel step dropped, where users get stuck, whether an experiment changed behavior, or which feature path needs investigation. - **Inspect PostHog evidence:** The agent queries the connected PostHog account for the relevant events, insights, dashboards, flags, or recordings available to it. - **Trace behavior into code:** Replicas searches the repository for the routes, components, handlers, analytics events, and feature-flag logic behind the signal. - **Change and verify:** When the evidence supports a fix, the agent edits the code, runs the relevant checks, and returns a pull request. Otherwise it returns a technical report with its evidence and next steps. ## What can a PostHog coding agent work on? The best tasks begin with a specific product signal and end with an engineering output that a human can review. - **Conversion drops:** Investigate a funnel step that fell and identify the responsible product flow and code path. - **Rage clicks and dead ends:** Trace repeated clicks or abandoned sessions to a confusing or broken interface. - **Experiment cleanup:** Compare results, inspect the feature-flag implementation, and prepare the winning cleanup change. - **Instrumentation gaps:** Audit missing or inconsistent analytics events and fix the instrumentation in the repository. - **Post-deploy regressions:** Explain an unexpected behavior change after a deployment and prepare a targeted fix. - **Inconclusive evidence:** Return a technical report instead of a change when the evidence does not justify touching code yet. ## A dashboard summary is not the finish line Replicas keeps the work in an inspectable cloud workspace. Reviewers can see the evidence the agent used, the files it changed, the commands it ran, and the result it recommends. - A pull request with the product signal, root cause, code change, and verification results. - A technical investigation linking PostHog evidence to specific routes, components, or handlers. - A corrected analytics event or feature-flag implementation with tests. - A reproduction and a clear blocker when the product signal is not sufficient for a safe fix. ## Keep product analysis inside the coding workflow PostHog access gives the agent more context, not unlimited authority. The connected account determines what data the agent can access, and code changes remain visible for human review. - Use a PostHog personal API key with only the access the workflow needs. - Give the agent a clear product question, time range, and success condition. - Run changes in a configured Replicas environment before opening a pull request. - Review analytics interpretations and code changes before merging or deploying. - Return an investigation instead of inventing causality when the evidence is ambiguous. ## FAQ ### Can Replicas analyze PostHog data? Yes. With the PostHog plugin installed, Replicas agents can access projects, events, insights, dashboards, feature flags, and recordings according to the connected account permissions. ### Can a PostHog insight become a pull request? Yes, when the agent can connect the signal to a specific code path and verify a safe change. If the evidence is incomplete, the better output is a technical investigation or a request for more context. ### Does this make Replicas a general-purpose analytics agent? No. Replicas is a cloud coding agent platform. PostHog supplies product context so the coding agent can investigate, change, test, and return better software work. ### Does Replicas automatically change production from PostHog? No. The agent works in a Replicas cloud workspace and returns reviewable code or findings. Teams decide what to merge and deploy. ## Related docs - [How to use PostHog with Replicas](https://tryreplicas.com/blog/how-to-use-posthog-with-replicas): Follow the recommended setup, task format, and review process for PostHog investigations. - [Automated bug fixes](https://tryreplicas.com/use-cases/automated-bug-fixes): Learn how Replicas investigates failures and returns fixes or debugging handoffs. - [Plugins docs](https://docs.tryreplicas.com/features/plugins): Connect PostHog and control which account a Replicas workspace can use.