Tencent WorkBuddy is an AI agent built for everyday office work. Make a request. Guide your AI expert team. Bring in a second opinion. Get sharpened, ready-to-use results.
@ismaelyws Thank you, Hans! Means a lot on launch day
Report
The disagreement-survival question Omri raised is the one that bit me hardest building this stuff. What worked for me wasn't a smarter merge prompt, it was giving each expert a flag field the synthesizer literally can't drop, so a minority-of-one objection still renders in the final output. The moment I let the combine step weigh objections by confidence, the useful contrarian take got averaged into mush. Do your experts write to a shared structured object, or hand back prose the synthesizer re-reads and re-summarizes?
@dipankar_sarkar The way it works in WorkBuddy is closer to your flag-field instinct. You can ask for it directly in your brief: preserve dissenting opinions, show unresolved objections, keep each expert's take visible. The clearer the expectation, the better the team calibrates.
I like the idea of bringing in another expert opinion at any point. In real work, the problem is often not generating content, but knowing whether the direction is actually the right one.
@orman_canida Exactly! That's the core idea behind our expert system.
Instead of asking users to become AI experts, we believe AI should bring the right expertise and workflow to every task, so people can focus more on their work instead of figuring out how to get the best results~
@cruise_chen Thanks so much! That’s exactly what we’re trying to do—help users get professional results without needing to become AI experts~
Report
the "bring in a second opinion" framing is a nice touch. most AI-work tools stop at one answer, and leaning into an expert-panel idea instead is more how real teams actually decide things. curious how you keep the experts from just agreeing with each other. congrats on the launch.
That's something we care about a lot. Our experts are designed with different workflows, curated domain knowledge, and specialized skills, so each one can contribute its own perspective to a task.
We're continuously improving them, and we'd love to hear your feedback if you give WorkBuddy a try~
@ll_wen Thanks Daniel, really appreciate the support!
Report
Love the idea of experts cross checking each other instead of just one model guessing alone, that debate before delivery feels like the real innovation here.
@ilko_kacharov Exactly this. That "debate before delivery" framing is actually how we think about it internally too.
Report
Interesting idea! I'm pretty set with using Claude Code for everything, and I think most people by now use what they are used to. How will you convince users to switch and try WorkBuddy instead of what they are used to?
Also cool logo, here's a free static QR code that goes to your website that I made for you to use if you want:
@mjohnson42 Ha, thanks for the QR code, that's a genuinely kind thing to do. And I'm not going to try to pull you off something that already works for you, that's usually a losing pitch anyway. The people we're really built for aren't devs living in the terminal, it's the folks next to them doing business work: reports, decks, research, analysis. Different job than writing code. So it's less "switch your daily driver" and more "when you've got a work deliverable to produce and don't want to babysit it step by step, this is worth a look." If that day comes, I'd love to hear what you think.
Report
The "finished files in your folders, not trapped in chat" line is the strongest part for me. That last mile is where a lot of AI tools still feel unfinished.
Curious how much control users have over the final deliverable format. Can someone define a preferred structure or template once and have future expert teams follow it?
@sergbmw Thanks, that line is basically the whole reason we built this, so glad it landed. On control: you steer the format in your brief, so you can ask for a PDF, a 9-slide deck, a specific section structure, whatever you need, and the experts build to that.
And for the "define it once and reuse it" part, that's exactly what our Skill system is for. You can save a preferred structure or template as a Skill, describe it once in plain language (literally something like "I want the report in this format, save it as a Skill"), and future runs just follow it. So you're not re-specifying the format every time. You can still tweak it on the fly for a one-off, or let the saved template drive it by default. The goal is that the last mile lands in your format, not a generic one.
Report
@sherina_chen That control model is much clearer now. Having the structure live in the brief feels like the right place for it, because it keeps the output tied to intent rather than adding another settings layer. Curious whether teams can save reusable briefs/templates for recurring deliverables.
Replies
Hello Inbox
Congrats on the launch @sherina_chen
Miora
@ismaelyws Thank you, Hans! Means a lot on launch day
The disagreement-survival question Omri raised is the one that bit me hardest building this stuff. What worked for me wasn't a smarter merge prompt, it was giving each expert a flag field the synthesizer literally can't drop, so a minority-of-one objection still renders in the final output. The moment I let the combine step weigh objections by confidence, the useful contrarian take got averaged into mush. Do your experts write to a shared structured object, or hand back prose the synthesizer re-reads and re-summarizes?
Miora
@dipankar_sarkar The way it works in WorkBuddy is closer to your flag-field instinct. You can ask for it directly in your brief: preserve dissenting opinions, show unresolved objections, keep each expert's take visible. The clearer the expectation, the better the team calibrates.
Niceeee
Miora
@madalina_barbu Thanks for the support~!
I like the idea of bringing in another expert opinion at any point. In real work, the problem is often not generating content, but knowing whether the direction is actually the right one.
Miora
@orman_canida Exactly! That's the core idea behind our expert system.
Instead of asking users to become AI experts, we believe AI should bring the right expertise and workflow to every task, so people can focus more on their work instead of figuring out how to get the best results~
Agnes AI
I like that this is built around everyday office work instead of abstract agent demos. The positioning feels grounded.
Miora
@cruise_chen Thanks so much! That’s exactly what we’re trying to do—help users get professional results without needing to become AI experts~
the "bring in a second opinion" framing is a nice touch. most AI-work tools stop at one answer, and leaning into an expert-panel idea instead is more how real teams actually decide things. curious how you keep the experts from just agreeing with each other. congrats on the launch.
Miora
@alex_watson2110 Thanks so much for the thoughtful comment!
That's something we care about a lot. Our experts are designed with different workflows, curated domain knowledge, and specialized skills, so each one can contribute its own perspective to a task.
We're continuously improving them, and we'd love to hear your feedback if you give WorkBuddy a try~
BiRead
Congrats WorkBuddy team.
Miora
@ll_wen Thanks Daniel, really appreciate the support!
Love the idea of experts cross checking each other instead of just one model guessing alone, that debate before delivery feels like the real innovation here.
Miora
@ilko_kacharov Exactly this. That "debate before delivery" framing is actually how we think about it internally too.
Interesting idea! I'm pretty set with using Claude Code for everything, and I think most people by now use what they are used to. How will you convince users to switch and try WorkBuddy instead of what they are used to?
Also cool logo, here's a free static QR code that goes to your website that I made for you to use if you want:
Miora
@mjohnson42 Ha, thanks for the QR code, that's a genuinely kind thing to do. And I'm not going to try to pull you off something that already works for you, that's usually a losing pitch anyway. The people we're really built for aren't devs living in the terminal, it's the folks next to them doing business work: reports, decks, research, analysis. Different job than writing code. So it's less "switch your daily driver" and more "when you've got a work deliverable to produce and don't want to babysit it step by step, this is worth a look." If that day comes, I'd love to hear what you think.
The "finished files in your folders, not trapped in chat" line is the strongest part for me. That last mile is where a lot of AI tools still feel unfinished.
Curious how much control users have over the final deliverable format. Can someone define a preferred structure or template once and have future expert teams follow it?
Miora
@sergbmw Thanks, that line is basically the whole reason we built this, so glad it landed. On control: you steer the format in your brief, so you can ask for a PDF, a 9-slide deck, a specific section structure, whatever you need, and the experts build to that.
And for the "define it once and reuse it" part, that's exactly what our Skill system is for. You can save a preferred structure or template as a Skill, describe it once in plain language (literally something like "I want the report in this format, save it as a Skill"), and future runs just follow it. So you're not re-specifying the format every time. You can still tweak it on the fly for a one-off, or let the saved template drive it by default. The goal is that the last mile lands in your format, not a generic one.
@sherina_chen That control model is much clearer now. Having the structure live in the brief feels like the right place for it, because it keeps the output tied to intent rather than adding another settings layer. Curious whether teams can save reusable briefs/templates for recurring deliverables.