Michael Luo

product at @openai, ex-@stripe, ex-@ycombinator, Free e-sign

[Michael Luo @AzianMike]

We shipped a bunch of stuff in Agents API in October!
And make sure you read to the end for some beta features 👀

The full list:
- auto review: automatically review and approve or deny supported agent actions, similar to Codex’s “review for me”
- automations: you or the agent can schedule future work, including recurring tasks. things like "check on x every hour" automatically work
- update tools mid-session: change the tools available to an agent while a session is running
- Artifact SDK: hosted sandboxes will now be better at spreadsheets, presentations and Word documents
- (experimental) time awareness: experimental setting that gives the agent an understanding of time, so things like "do x in <10 mins" work well
- sandbox prewarming: you can prewarm sandboxes before you need them (speeds things up by doing expensive work like installing packages)
- async compaction: on by default, compacts context in the background so it doesn’t block the agent
- cross-session prompt caching: system prompts are automatically cached across sessions
- GPT-6 Astra Ultrafast: use ultrafast mode in the Agents API for faster output
- sandbox snapshots: hosted environments can be restored after going idle, with their files intact
- 12hr prompt caching: makes things faster for cases where your users talk to the agent less frequently
- environment keys: create environment keys programmatically
- turn-level history: inspect a specific turn and its subagent activity
- vault metadata filtering: filter vaults by metadata when listing them

- beta features we're working on: contact us to try them out
- memory: agents will be able to remember stuff and search old messages across sessions
- decisions api: give agents access to the decisions api, for faster performance on tasks that benefit from filtering, classification etc
- budget control: give the agent a max dollar budget to work within
- env pooling; we create a pool of vanilla containers, making performance faster for hosted sandboxes
- v2 architecture: faster and more reliable across the board

[Michael Luo @AzianMike]

We must build more donut centers

[Polymarket @Polymarket]

BREAKING: Krispy Kreme officially outperforms NVIDIA over the past year.

[Daniel Steigman @trekedge]

PSA: To use daybreak, sign in with your hardware key, not a random passkey. Otherwise, you will get cyber refusals due to improper authentication.

[Michael Luo @AzianMike]

@daniel_nguyenx @marclou @tdinh_me Sure, tell him to email me [email protected]!

[Michael Luo @AzianMike]

And you should use GPT-Live via our API to get the best voice experience in your own app!

[Olivia Moore @omooretweets]

I was an early enthusiast, but my AI voice usage across products has gone up probably 5x in the last two months

As agents gain more human capabilities, talking to them like a human feels a lot more efficient

Now is a good time to make your product voice-enabled 👀

[Michael Luo @AzianMike]

Huge! Welcome to the team!

[cat @_catwu]

Some news: I’m joining OpenAI to lead product management for Core Products!

I have a lot of respect for OpenAI for showing the world that scaling works, for bringing AI to over a billion people, and for believing great products are core to the mission.

I’m excited to work with @thsottiaux, an incredible PM team, and everyone across OpenAI. Together, we’ll build agents that have your back and your team’s, and keep you in control, so you get more time for the people and work you love.

Lots to learn, and lots to build. Please keep your feedback coming!

[Michael Luo @AzianMike]

@dani_avila7 Hi! I'm helping work on this - let me know if you have any feedback or things we can improve on this!

[Michael Luo @AzianMike]

@ajambrosino Can you improve the mozzarella stick appetizers? Maybe make the cheese pull longer?

[Michael Luo @AzianMike]

Bring the same Codex auto approval for actions into Agents API!

Keeps your workflows safe while also streamlining the approval process.

[Kevin Whinnery @kevinwhinnery]

Super handy option shipped in the @OpenAIDevs Agents API last week - automatic review. Brings the Codex "approve for me" behavior to agents in the API, cutting down on chatty API approval steps. The network restrictions on your sandbox still work though!

[Michael Luo @AzianMike]

ChatGPT Sites is so easy and convenient to use to build software UI. I'm building my own personal finance calculator for my situation specifically and it's so much nicer of an interface than an Excel spreadsheet.

[Michael Luo @AzianMike]

@stevendcoffey Omg yes to updating tools midsession!

[Michael Luo @AzianMike]

Building your own agent is only getting easier by the week

[Steve ☕️ @stevendcoffey]

🗣️ The Agents API team has a shipping problem – we literally cannot stop. Here’s what we cooked up for you beautiful people this week:

💂 Auto Review: Just like in codex, auto-review will evaluate commands for potential bad behavior before executing.

🗜️ Async Compaction: Speed up your sessions by allowing compaction to happen in the background.

🕐 Time awareness: An experimental feature that allows the model to have a sense of time passing. This means the model will better act on queries like, ”timebox CI fixes to 10 minutes.”

🔨 Tool Updates: You can now update a session’s tools at any time.

💰 Better prompt-cache awareness: System prompts are now automatically cached across all sessions, saving you money and time

[Steve ☕️ @stevendcoffey]

🗣️ The Agents API team has a shipping problem – we literally cannot stop. Here’s what we cooked up for you beautiful people this week:

💂 Auto Review: Just like in codex, auto-review will evaluate commands for potential bad behavior before executing.

🗜️ Async Compaction: Speed up your sessions by allowing compaction to happen in the background.

🕐 Time awareness: An experimental feature that allows the model to have a sense of time passing. This means the model will better act on queries like, ”timebox CI fixes to 10 minutes.”

🔨 Tool Updates: You can now update a session’s tools at any time.

💰 Better prompt-cache awareness: System prompts are now automatically cached across all sessions, saving you money and time

[Michael Luo @AzianMike]

@levelsio Sounds and looks like Walmart, including all the goods probably being made in China

[Michael Luo @AzianMike]

@decentrek It sounds like 7702 just helped them move faster but the “root” cause is something related to a private key/permissions being compromised right?

It feels like 7702 is purely a neutral tool for better UX (so net positive). But let me know if I’m understanding wrong

[Michael Luo @AzianMike]

@samsheffer 2 packs! And I got this beauty

[Michael Luo @AzianMike]

Thanks to Sam’s advice i also got some cards!

[Sam Sheffer @samsheffer]

やっとできました！少なくとも30軒のコンビニエンスストアを回った後、日本でポケモンカード30枚を獲得しました！

[Michael Luo @AzianMike]

Claim your API credits. Then build with the Agents API

[OpenAI Developers @OpenAIDevs]

Starting today, eligible ChatGPT Pro and Business subscribers can claim up to $500 per month in API credits to build apps and agents.

[Michael Luo @AzianMike]

@samsheffer Sad, I just checked a local 7-11 and didn’t see it :( was it in this toy section area?