Augmend

RPA is dead. Long live RPA(gent) Everyone is talking about agents. I think of them as simply AI + tools + a for loop but wanted to get my notes down to share. Calling out a need for more human/agent collaboration tools starting with WatchMe augmend.com/blog/agents

TreeSeg on the orange site front page!

In this blog post we take a closer look at how, here at @augmendtech, we segment video sessions into chapters using our in-house developed chapter segmentation algorithm, TreeSeg. Read the post here: augmend.com/blogiverse/TreeS…

New paper (preprint) alert! From organizing recorded videos and meetings into chapters to breaking down large inputs in order to fit them into a context window, temporal topic segmentation of large transcripts is very important. We have a new approach that we're calling TreeSeg

Can a website really have too much neon glow? I'm told by designers that I proved the answer to be yes; new homepage dropped in celebration of the new @augmendtech API that les anyone leverage multimodal video understanding in their apps or agents

More early thoughts for those interested

"A computer for every AI Agent and any task" Not quite as catchy as the PC revolution, but possibly more important. The future according to @augmendtech TLDR Agents need their own VMs/PCs. We should share screens with eachother, just like we were working with a human

If you want to engage in Q&A directly with the video we let you do that too with a tool I’ve been working on, here’s a 3blue1brown video with a built in chat and an automatically written scannable doc to go back over more info. Easier to consume imho augmend.com/replay/jmdTiAowA…

here is a @TomFrankly video on building an expense tracker, turns it into a step by step doc and can answer questions like below augmend.com/replay/jnUiKIowA…

Here is a 3blue1brown video, you can see we get a doc together and can answer questions in the chat, you can even copy/paste directly from the processed video. It's not quite the right format since our templates right now are aimed at step by step instructions instead of more explainer-type, but that's easy enough to add as a new template type augmend.com/replay/jmdTiAowA…

always happy to hear more from you all on agents. you should add chapters and some notes to let folks jump around in the video more though. Here are some auto-generated, feel free to copy/paste them into that video: [00:00:00] Interview with Langchain's CEO Harrison Chase [00:01:12] Agent Roles in Application Decision-Making [00:04:39] Control vs. Autonomy in LLM Agent Development [00:06:55] From AI Co-Pilots to Autonomous Agents [00:10:36] Custom Cognitive Architectures in LLMs [00:16:58] Coding Agents for GitHub Issue Resolution [00:18:46] Cognitive Architecture's Impact on Product Quality [00:20:21] Autonomous Agents in UX/UI and Industry Automation [00:23:51] AI in Bridging the Creative Gap [00:26:12] Language Model Reasoning Evolution [00:28:10] Task Planning and Execution Challenges in AI [00:30:47] UX Influence on Language Learning Model Architecture [00:32:31] Agent-Human Collaboration via Editable Actions [00:35:09] Building with Large Language Models [00:39:26] Langchain: Orchestrating Cyclical Applications [00:41:14] Testing Non-Deterministic Language Model Applications [00:43:44] Software Testing: Language Model Evaluations [00:45:37] AI Leadership and Influential Figures [00:48:03] Practical Engagement with GPT-5 Development You might also like that we can process that video and make it so anyone can "chat with" and get answers quickly, try it here and check out the generated markdown doc from that video too: augmend.com/replay/jktetjXQA…

Give me a youtube or loom or just a link to a video and I'll turn it into a doc + intelligent Q&A link right now. Drop one below and let's try it out together