AI in the wild — real examples from real practitioners

Tendril

Here’s what’s actually happening on X.

Real posts · verified first

Real posts from people who actually shipped this. Verified entries first, with attribution.

0 confirmed links3 cited from news112 representative

Showing 1 of 115 postsEvery entry links back to X

Jordan Ast@jordaast

AE; Gong power user

Representative

Gong call review with LLMs1.1 years agoRubric-based call review

Representative of AE threads on pulling Gong transcripts into Claude with a rubric — scoring discovery depth, objection handling, and next-step clarity in minutes.

“My manager's 1:1 went from 'watch these 3 calls' to 'read this rubric score and tell me which you disagree with.'”

How to replicate

1.Write a 5-criterion rubric: discovery, qualification, objection handling, next step, tone.
2.Export the Gong transcript; paste it into Claude with the rubric.

Prompt template

You are a sales coach. Score this sales call against the rubric below. For each criterion, return a 1–5 score and quote the exact line from the transcript that justifies the score. Do not paraphrase — quote. Rubric:
1. Discovery depth: <definition>
2. Qualification: <definition>
3. Objection handling: <definition>
4. Next step clarity: <definition>
5. Tone/pace: <definition>
Transcript: <paste>

Pitfall

Trusting the score without the quote. Always require evidence — models will invent a score to be helpful, but requiring a quote forces them to be real.

What you'll learn

•How to turn qualitative review into quantitative signal
•Why requiring quotes neutralizes hallucination in review tasks
•How to spot systemic weaknesses across a team from aggregated scores
•When a human reviewer still has to watch the whole call

Glossaryhallucination prompt system prompt

#gong#call-review#coaching

About this page(tap to expand)

Curated examples of practitioners using AI in the wild — builders, sellers, ops leads, teachers, artists. Every entry links to the original post. When we can’t verify a specific URL, we flag the entry as representative rather than inventing one.

Tendril keeps this list conservative on purpose. Entries marked representativedescribe patterns we’ve seen practitioners discuss publicly on X but whose exact URLs we haven’t individually verified. We’d rather flag an example as representative than fabricate a precise post-ID. If you see a wrong attribution or a broken link, tell us and we’ll fix it within the day.