Goals

Q2 2026 objectives

Goal 1: Agent-first AI Observability

Description: Make AI Observability usable directly from agents and developer workflows, not just through the product UI.

What we will ship:

• MCP tools and skills - expose core AI Observability workflows through MCP tools and reusable skills
• PostHog AI integration - bring AI Observability capabilities directly into PostHog AI workflows

Goal 2: Eval experience and reliability

Description: Make evaluations easier to run and give teams clearer visibility into where their AI systems fail.

What we will ship:

• Trace-level evaluations - run evaluations directly against traces
• Session-level evaluations - extend evaluations to broader user and agent sessions where it makes sense
• Improve observability of failures - show errors more transparently

Goal 3: Prompt management improvements

Description: Make prompts easier to organize, scope, and connect to experimentation.

What we will ship:

• Prompts and experiments integration - tighter connections between prompt workflows and experimentation
• Prompt tags - tag prompts and fetch them by tag for better organization
• Private project API keys - switch prompt management from personal API keys to scoped, private project API keys so prompts aren't tied to an individual user's account

Goal 4: Reliability and performance

Description: Continue improving the speed, resilience, and overall quality of AI Observability, with a particular focus on trace-heavy workflows.

What we will ship:

• Trace and platform improvements - ongoing improvements to the speed, resilience, and overall quality of core AI Observability workflows

Goal 5: Trace and session UI

Description: Revamp the single trace and session experience for modern agentic use cases.

What we will ship:

• Single trace UI refresh - modernize the trace experience for agent-first workflows
• Session UI improvements - bring the same quality bar to session-level investigation
• Custom message parsers - define parsers for different agent and LLM message structures

Goal 6: Cluster migration

Description: Finish migrating to the new ai_events cluster architecture.

What we will ship:

• ai_events cluster migration - migrate to new architecture, which is optimized for point lookups of traces

Handbook

Who we're building for

Product Engineers and Full Stack Developers who are building:

• AI-native products (agents, assistants, copilots, specialized hardware)
• AI-adjacent products (LLMs integrated into existing products)

AI Observability is a good fit if:

• They need to monitor traces, spans, token costs, latency, and analyze usage of AI features
• They're using trace summaries to debug and evals to make product decisions
• They care about questions like: “how does interacting with LLM features correlate with retention, usage, or revenue?”
• They're already PostHog users (or should be) using product analytics and session replay to combine qualitative context with quantitative data
• They want to start getting value right away, without needing extensive setup and configuration

Who else might want to use AI Observability at their org:

• Application Ops / SRE to monitor production AI systems for errors, prompt injection, jailbreaks, or other security issues
• Product Managers to understand user sentiment, usage and make decisions about their AI roadmap
• Customer Success / Support Teams to improve documentation or investigate user issues

Who we're NOT building for (right now)

AI Researchers and Machine Learning (ML) Engineers doing:

• Deep foundation model work
• Complex benchmarking and evaluation
• Advanced experimentation requiring specialized tooling

These folks are running CI/CD pipelines and building full QA automation frameworks with performance benchmarks. If they try us and churn, that's fine. We haven't built the tools they need (yet).