
What happened
FlashLabs updated Hermes Agent, its AI agent inside the FlashRev B2B sales platform, adding multiple sessions, file management, and scheduled tasks with five patterns.
Why it matters
The changes target day-to-day reliability, letting sales staff keep separate research and outreach sessions and automate recurring prep work instead of repeating the same instructions each time.
WHO IT HITSSales teams using FlashRev can split research, material creation, and outreach drafting into separate sessions, and can register recurring weekly prep work as scheduled tasks so they no longer re-enter the same instructions.
Summaries like this, every morning.
Hermes Agent was built to autonomously run complex multi-step workflows — web research, work spanning multiple tools, and tasks in remote environments — with an emphasis on execution, automation, and traceability. The new release shifts attention from what the agent can do to whether it can be used steadily in daily work. Centralizing key settings and AI model configuration on the FlashRev side is presented as a way to reduce connection and execution problems triggered by settings changes.
The session and file features are aimed at organization: conversations can be split by purpose such as research, material creation, and drafting, renamed, and searched, then sorted under Chat, Automation, and All tabs. Files Hermes generates can be previewed, uploaded, and downloaded, and deliverables can be managed across sessions.
FlashLabs frames the update as part of evolving FlashRev into a platform that completes every sales workflow with AI. The company says it will keep expanding the platform's AI agent features.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Artificial Analysis's evaluation found OpenAI's GPT-6.2 Astra and Sol give shorter, more direct answers than p…

Between 1:48 and 5:21 PT on November 21, requests to OpenAI's API and ChatGPT failed at rates peaking at 75%…

OrcaRouter started providing an API for Qwen4 Max, Alibaba's latest flagship model, so developers can call it…

A developer's task.md grew to 1,630 lines, about 45% records of finished work, and Claude reported 63 unfinish…

A Zenn author published a master index of every article in their series — Rokid Glasses smart glasses (15 post…

Ziva.sh tested GPT-6 Luna on 10 beginner Godot prompts, with 'Godot 4' specified, no version, and web search;…
