What does it take to build AI that can hold a real conversation?
This is a dev post classified by AGK Intelligence as Testing & observability (a free resource), kept by the Dev Radar because it carries real work, not commentary.
What does it take to build AI that can hold a real conversation? Seth Wright of @My_CTM shares his learnings on testing voice AI when no two calls match, and why a phone number can come out as billions on the latest episode of Ship Happens: https://youtu.be/u1L4m5D9NCU
Posted by Docker (558.3k followers) 1 h ago · 3 likes · 1.4k views · view the original post on X. Kept by the Dev Radar as Testing & observability.
More dev work like this
- feels like there's a new major outage every day now, and it's getting worse as agents… — @boristane
- Model testing? No. Data orchestration testing → 6.4x fewer input tokens. Answered 2.6x… — @clay
- Gate CI on p95 latency with one Postman CLI command: — @getpostman
- If you’re asking “how do we actually use Seer?” We’ll just show you 🤝 — @sentry
- Chai was told to price Workers IO at par with the competitor. He priced it lower. — @solofounders
- Yesterday we announced Argent e2e — @blazejkustra_
- Test and verification technique effectiveness with Astra: — @danluu
- "We are basically taking the problem of verifying software and converting it into a… — @solofounders
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 19:56 UTC. Full method.