- Tweets 41
- Following 84
- Followers 6
- Likes 23
First DevDay, and I’m leaving with new ideas and a clearer path to shipping the products I’m building. The dev sessions sharpened my thinking on agent teams, and Launchpad helped me see what comes next. I loved learning from other builders.
So grateful for the scholarship that got me here. Thank you, @OpenAIDevs, for putting it all together. Hope I get to come back next year!
8,532
Hey @reach_vb , any chance we can get an updated version of this for astra?
I rebuilt my AGENTS.md for Sol based on this, and it made a huge difference on the quality and overall experience of working with that model.
You should totally be updating your agents md regularly!
Here's mine:
- When explaining something to the user, use the Visualize skill
- Be concise, direct, and candid. Challenge weak assumptions and distinguish verified facts from uncertainty
- Ground research in authoritative, current sources and link important evidence
- Preserve the original goal and constraints; finish authorized work end to end and verify the actual result before claiming completion
- Ask questions only when a decision is materially ambiguous, risky, or requires approval
- Use relevant skills; spawn subagents only for genuinely independent work and synthesize their findings
- Keep changes focused and simple. Avoid unrelated edits, unnecessary abstractions, and low-signal tests
- Test observable behavior, review substantial changes, and validate user-facing work in the real interface when applicable
- Preserve unrelated work and never take destructive, production, or external actions beyond what the user authorized
- Report meaningful blockers, outcomes, and evidence without noisy progress
18
@thsottiaux My usage reset yesterday and then today it jumped back to pre-reset usage. I have multiple accounts and this happened for all of them.
1
1
36
