Grok Bot decisions
Right Resource, Right Moment
- Problem
- Saving a resource is easy. Getting it back at the right moment is harder.
- Decisions
- Show one high-confidence card. Silence stays unknown; explicit feedback can block a card. An annoying card pauses for 14 days.
- Measure
- Right-moment ratings, precision and false-interrupt rate.
Context Guard
- Problem
- An agent can act on memory you cannot see or correct.
- Decisions
- Show each fact and let the person confirm, correct or delete it.
- Measure
- Confirmed facts, corrections and deletions.
Product notes
Making agent work steerable before the change lands
A proposal for adding an instruction to a specific step of an agent task and seeing whether the agent can still include it.
Making agent work steerable before the change lands
A proposal for adding an instruction to a specific step of an agent task and seeing whether the agent can still include it.
The change was small
I asked an agent to put a holding page on my portfolio. While it was working, I wanted to add LinkedIn alongside my X profile. The change was small. Knowing whether the instruction would reach the right part of the work was harder.
I could send another message, but I could not easily see whether the agent was still preparing the page, had already updated the links, or was about to deploy. I wanted to steer the work without stopping it and without triggering a second deployment.
Attach the instruction to the work
I would start with a short, visible map of the current turn. A new instruction could refer to one of its steps. I could ask to include LinkedIn in the profile-links step and see an acknowledgment beside the affected work.
When I send an instruction, I want to know whether the agent can still include it in the deployed result. An acknowledgment should tell me that, beyond confirming receipt.
The first MVP could be text: the steps, the current position and the acknowledgment beside the affected step. A visual component can follow once the underlying state is reliable.
Proposed interaction
A flow to test. In this example, a new instruction targets the profile-links step.
- Read current state
- Prepare page
- Update profile links
- Review
- Deploy
- Received
- The system has captured the instruction.
- Included
- The instruction is attached to work that can still incorporate it.
- Needs another pass
- The relevant step is already complete, so this change needs another pass.
Where a change needs another pass
I would define when a change needs another pass. Updating a local file and deploying a public page are different events. The interface should show whether there is still time to include the change, without making me understand the agent’s internal machinery.
I would keep this as a proposal until the steps and acknowledgments reliably match the work. A reassuring but inaccurate status would leave me with the same uncertainty.
What I would test
I would give people a small change while an agent task is in flight. I would check whether they can tell if it was included, whether they repeat themselves less, and how often the task needs another deployment. I would also check whether maintaining the map slows the work down.
I would also check whether the map and acknowledgments stay accurate when an instruction arrives after its step has finished.
The unit of value is finishing
Paper IRL explores whether turning saved X bookmarks into finite, private editions helps readers return to material they already chose.
The unit of value is finishing
Paper IRL explores whether turning saved X bookmarks into finite, private editions helps readers return to material they already chose.
An edition that can be finished
People save posts because they want to return to them. The collection grows, but reading competes with the same feeds and interruptions that created the collection. Paper IRL starts with an edition that can be finished.
The reader has already chosen the material by saving it. I want to turn it into a private physical edition they can sit down and finish.
What that changes
The saved material carries the reader’s intent, so the early product does not need to invent a ranking score. Source links and context help preserve what was saved. The edition needs to be readable and finite.
I would judge the early experience by whether a reader can sit down with an edition and finish it. I would add more material or more ways to browse only if they help with that. I still need to test whether this changes reading behavior.
Printing and delivery would remove another chore. I can promise them only after the order path works; producing a print-ready file is one step.
Prototype evidence and the next test
The prototype records describe HTML and PDF files with access scoped to the owner, an explicit sample mode and output that preserves the source material. Whether readers finish more material, and whether paid fulfillment works, remain untested.
A useful next experiment would compare what people finish from a small edition with what they revisit in their ordinary save queue. I would also ask whether the edition earns a recurring place in their week.
Ideas and demos on video
Why I started Creatorbase
who doesn't like a good origin story? shared @JoinCreatorbase's from back in 2022 along with why are we building it what problems does it solve and for whom @BasedIndia @callusfbi @buildonbase @base @somewhatsahil https://t.co/yC7UxYqpqA
- Product strategy
- Creator economy
Why I started Creatorbase
who doesn't like a good origin story? shared @JoinCreatorbase's from back in 2022 along with why are we building it what problems does it solve and for whom @BasedIndia @callusfbi @buildonbase @base @somewhatsahil https://t.co/yC7UxYqpqA
Chop: content distribution and creator pay
introducing chop an onchain clipping platform within Creatorbase brands can get their own content amplified via 1000s of creators or clippers or choppers, you get the drift creators get paid per view more people or agents (we don't judge) - can now participate in the onchain creator economy win win for both the brands and the creators will be sharing a more in depth "why tf are we doing this" video separately this is a product demo video shipping fast is a muscle that we are developing and i am happy to move with this pace we are now platform for you to get fresh ugc content created for your brand AND also get your core content library amplied dont let your brand content die at the hands of the social media algos so if you are a brand, please reach out to me here or in the dms or just sign up with the link in the comments same for all you creators, sign up to the early access list using the link chop chop!
- Creator incentives
- Distribution
Chop: content distribution and creator pay
introducing chop an onchain clipping platform within Creatorbase brands can get their own content amplified via 1000s of creators or clippers or choppers, you get the drift creators get paid per view more people or agents (we don't judge) - can now participate in the onchain creator economy win win for both the brands and the creators will be sharing a more in depth "why tf are we doing this" video separately this is a product demo video shipping fast is a muscle that we are developing and i am happy to move with this pace we are now platform for you to get fresh ugc content created for your brand AND also get your core content library amplied dont let your brand content die at the hands of the social media algos so if you are a brand, please reach out to me here or in the dms or just sign up with the link in the comments same for all you creators, sign up to the early access list using the link chop chop!
Pull it up Jamie
A physical device that sits on top of a podcaster’s desk and they tap it to research whatever assertion, data they just spoke about - using audio The conversation goes on meanwhile It does the job in the background and then beeps when done Then the conversation evolves naturally as per the new / confirmed data As someone who knows about a domain, it’s frustrating when the tangent goes off despite of good faith participants OpenAI / perplexity / anthropic should build and sponsor it
- Voice interfaces
- Product ideas
Pull it up Jamie
A physical device that sits on top of a podcaster’s desk and they tap it to research whatever assertion, data they just spoke about - using audio The conversation goes on meanwhile It does the job in the background and then beeps when done Then the conversation evolves naturally as per the new / confirmed data As someone who knows about a domain, it’s frustrating when the tangent goes off despite of good faith participants OpenAI / perplexity / anthropic should build and sponsor it
Onchain raffle agent
built this Onchain Raffle Agent that lets anyone create and run raffles in <60 seconds built on @CoinbaseDev 's Agentkit on @Replit and using @Alchemy APIs would love to hear your thoughts and feedback on it https://t.co/7jWIlL1Y3s
- Agent workflows
- Onchain products
Onchain raffle agent
built this Onchain Raffle Agent that lets anyone create and run raffles in <60 seconds built on @CoinbaseDev 's Agentkit on @Replit and using @Alchemy APIs would love to hear your thoughts and feedback on it https://t.co/7jWIlL1Y3s
An agent for creator rewards
building onchain is more exciting and feasible than ever, thanks to @CoinbaseDev we have built an autonomous, onchain agent that rewards content creation around the onchain ecosystem in a fair, verifiable(remember the OG motto) and efficient manner. here is the demo from @ETHIndiaco
- Creator economy
- Agent workflows
An agent for creator rewards
building onchain is more exciting and feasible than ever, thanks to @CoinbaseDev we have built an autonomous, onchain agent that rewards content creation around the onchain ecosystem in a fair, verifiable(remember the OG motto) and efficient manner. here is the demo from @ETHIndiaco