Skip to content

Commit c997cad

Browse files
Add user personas to LLM analytics team page (#13592)
1 parent 373dcc6 commit c997cad

File tree

1 file changed

+27
-1
lines changed

1 file changed

+27
-1
lines changed

contents/teams/llm-analytics/index.mdx

Lines changed: 27 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,4 +4,30 @@ sidebar: Handbook
44
showTitle: true
55
hideAnchor: false
66
template: team
7-
---
7+
---
8+
9+
### Who we're building for
10+
**Product Engineers** and **Full Stack Developers** who are building:
11+
- AI-native products (agents, assistants, copilots, specialized hardware)
12+
- AI-adjacent products (LLMs integrated into existing products)
13+
14+
**LLM analytics is a good fit if:**
15+
- They need to monitor traces, spans, token costs, latency, and analyze usage of AI features
16+
- They're using trace summaries to debug and evals to make product decisions
17+
- They care about questions like: “how does interacting with LLM features correlate with retention, usage, or revenue?”
18+
- They're already PostHog users (or should be) using [product analytics](/product-analytics) and [session replay](/session-replay) to combine qualitative context with quantitative data
19+
- They want to start getting value right away, without needing extensive setup and configuration
20+
21+
**Who else might want to use LLM analytics at their org:**
22+
- **Application Ops / SRE** to monitor production AI systems for errors, prompt injection, jailbreaks, or other security issues
23+
- **Product Managers** to understand user sentiment, usage and make decisions about their AI roadmap
24+
- **Customer Success / Support Teams** to improve documentation or investigate user issues
25+
26+
### Who we're NOT building for (right now)
27+
**AI Researchers** and **Machine Learning (ML) Engineers** doing:
28+
- Deep foundation model work
29+
- Complex benchmarking and evaluation
30+
- Advanced experimentation requiring specialized tooling
31+
32+
These folks are running CI/CD pipelines and building full QA automation frameworks with performance benchmarks.
33+
If they try us and churn, that's fine. We haven't built the tools they need (yet).

0 commit comments

Comments
 (0)