Letting users file feedback that agents fix (eric zakariasson)
Tweet describing a loop: in-app feedback lands in PostHog with replay and errors, and a Cursor cloud agent picks it up.
Posted by eric zakariasson (@ericzakariasson)
i’ve been building some smaller apps over the last weeks for myself, friends and family and discovered a pretty nice pattern in the process
you see, after building, i’m not particularly interested in fixing bugs or triaging feature requests. i just want to get the job done
so i’ve set up a system that lets me and other users fix bugs and build features without me having to actually open cursor
the flow:
- someone files feedback in the app
- it lands in posthog with the submitted text, session replay, events, and errors
- a cursor cloud agent picks it up with that context, plus live read-only posthog mcp
- it loops until the fix is verified, then opens a github pr with tests
- i get a ping and review it on my phone
we give our cloud agents access to all the necessary user context, and they’ll figure it out
with this in place, we can start setting up more abstractions in between. if we’re getting a high volume, we might want to triage first with another cloud agent or some automation. the feedback can create a github or linear issue, which we later pick up with a cron-backed cloud agent that decides which are duplicates. there are so many ways to configure this, you just gotta try it out and see what works for you
but there’s so much more here that is untapped. with session replays and event logs, you can have a cloud agent look at each session replay to extract ux pitfalls and improvement areas. you can have another agent looking at event logs to see weird patterns. another one for errors or similar
try it out and see what you can do!
Similar in the index
- Fanout Sequenced courses on AI research, system design and ML math for developers.
- Gisting: compressing LLM agent context (Shopify) Shopify Engineering on compressing agent context to raise throughput and cut cost.
- Learn Inference An interactive guide to serving generative models in production.
- Tokenminning: saving tokens (PostHog) PostHog on cutting AI token spend: trim AGENTS.md, audit MCP, use caching.