Make the requirement clear
When AI writes code, who defines what good means?
Shihipar stresses understanding the problem and communicating requirements to coding agents.
Thariq Shihipar
Return to the original context.
Source, interpretation and uncertainty
What does this actually establish?
| Source status | Publisher chapter at 00:15:37 · Not an independently verified outcome |
|---|---|
| Speaker context | Anthropic employee · discussing Claude Code |
| What remains open | Clear instructions help evaluation; they do not guarantee a correct implementation. |
AGI editorial interpretation
Two ways this could unfold
As implementation gets easier, clear goals may become more valuable. Weak testing can still hide a misunderstood requirement.
Where do I stand for now?
Turn a view into a small experiment
What is my next step?
A simple plan you can test and revise. Your notes stay in this tab until you save them.
Embed the free action planner
Video and context stay on this source page.
<iframe src="https://agiscorecard.com/future-guide/requirements-still-matter?embed=1" title="AGI action planner" width="100%" height="950" loading="lazy"></iframe>When you want to keep the work
Your next step deserves a place to return to.
Reading, video access, local saves and exports are free. Use the same plan on another device with AGI’s existing cloud workspace and version history.
No paid interview collection or automated personal-report subscription is offered here.
AGI cloud membership
9 USDT / 30 days
Plus the order-matching decimal and network fees. 50 workspaces, 10 versions per workspace, 64 KB per workspace and 5 MB in total. No auto-renewal or extra AI allowance.