Developer Support Bot Trained On Decentraland Documents
Proposal Details
Grant size
Tier
Beneficiary
Description
The core of technical Web3 projects depends on a healthy ecosystem of developers using the protocols. Developers learn how to use the various projects through inspecting developer docs and Github repositories. As expected, documentation doesn’t cover everything and a team of people are needed to provide “front line” support to those building/using the protocol. Enter Developer Relations, a team tasked with being the first human interface with protocols who provide 2 critical roles for the project: building developer communities & tracking product-market fit. The issue that often arises is a lack of human capital to be able to deal with the number of requests & questions that populate a DevRel team's day. We propose to provide a solution that will enable the Decentraland DevRel team to be able to focus on what they do best: solving unique customer problems and building trust in the protocol. By providing a bot that can answer previously asked questions, it will enable DevRel to become more effective and in turn provide higher quality support to end users.
Voting Rationale
0.025
Developer Support Bot Trained On Decentraland Documents This proposal is now in status: REJECTED. Voting Results: * Yes 2% 123,215 VP (47 votes) * No 78% 3,854,998 VP (88 votes) * Abstain 20% 1,033,634 VP (33 votes)
Hello, this is a great idea, but I see @HPrivakos building bots for the DCL DAO Discord which seems to be included in his salary. If this is needed, we should lean on those already doing it and pay them.
Hi, thanks for your initiative. Very interesting topic ! :boom: Please reach DAO Community in [Discord](https://discord.gg/ZM5v4gRpq9) and tell more about this proposal.
Love this. I think we need just a bit more information/discussion on Milestone 2, and attempting to reach an end-state which can allow the community to build on the said model. I think I can get behind this if the hosting of the bot is passed over to the community + a framework/documentation for ingesting new data is provided (so that we can keep updating the model as needed/repeat the past processes done). Keep in mind that DCL's documentation is always changing and growing (at a very rapid rate), so we can't have the bot stagnate. Additionally, being able to constantly have an up-to-date ingested reference (even if we're just using it for a top_p - esque self reflection reference), will be extremely helpful in being able to plug in self-iterating agents to the bot. IE: imagine an Auto-GPT that has the latest unity-renderer documentation, and is tasked with attempting to contribute new components to the DCL SDK (with a self-criticism model built around the proposed Support bot).
4 Comments