Sellio Launches Omnichannel AI Support Inbox

// 1h agoPRODUCT LAUNCH

Sellio Launches Omnichannel AI Support Inbox

Sellio brings website chat, WhatsApp, Instagram, Telegram, and email into one shared inbox with tickets, analytics, and AI agents trained on a team’s docs. Its embeddable widget lets AI handle first replies while humans take over when needed.

// ANALYSIS

Sellio’s strongest angle is combining affordable omnichannel support with controlled AI automation for small teams.

–One inbox unifies customer conversations, ownership, handoffs, tickets, and analytics.
–AI agents are grounded in company knowledge and escalate uncertain questions to humans.
–AI auto-replies currently focus on website chat, while other channels remain human-operated.
–A free tier and workspace-based pricing could appeal to teams priced out of per-seat support platforms.
–The widget’s one-script setup and API make deployment relatively accessible for lean engineering teams.

// TAGS

sellioagentchatbotautomationhosted-service

DISCOVERED

1h ago

2026-10-04

PUBLISHED

7h ago

2026-10-04

RELEVANCE

5/ 10

AUTHOR

Khalid Nouri

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH21m ago

Finetuning with Sampling Makes SFT Rival RL

Harvard researchers introduce an MCMC-based projection-sampling method that reshapes expert off-policy traces toward a model’s own distribution before supervised fine-tuning. Across chemistry, math, and medical QA tasks, the approach reportedly improves generalization and reduces forgetting versus strong RL and self-distillation baselines.

RESEARCH21m ago

Sharpening Tax Exposes RL’s Coverage Trade-Off

This research finds that RL post-training can improve pass@1 while narrowing an LLM’s solution coverage under repeated sampling. It introduces Sharpening Tax to measure that loss and PTGS, which adapts training temperature to prompt difficulty.

OPEN SOURCE53m ago

Crawlers Debuts Open Crawler Sandbox

Crawlers is an open-source, MIT-licensed browser sandbox for configuring autonomous crawler swarms, running them through a deterministic synthetic web, and inspecting or forking each simulation locally.