Chat.sh Launches AI-Native Help Center

// 2h agoPRODUCT LAUNCH

Chat.sh Launches AI-Native Help Center

Chat.sh is a help-center platform that uses AI to answer questions with cited source pages, while hosting documentation on a company’s own domain or folder. It also exposes articles as Markdown for ChatGPT, Claude, and other agents.

// ANALYSIS

Chat.sh targets a real support pain point, but its strongest differentiator is treating documentation as infrastructure for both humans and AI agents.

–Semantic search generates answers instead of returning keyword-matched article lists
–Custom-domain and folder hosting preserve branding, URLs, and analytics ownership
–Markdown exports and llms.txt make help content easier for AI assistants to consume
–A free tier and one-time $399 domain plan challenge subscription-heavy help-center tools
–The upcoming messenger and inbox could turn the documentation layer into a broader support platform

// TAGS

chat-shsearchragchatbothosted-servicedevtoolpricing

DISCOVERED

2h ago

2026-10-01

PUBLISHED

8h ago

2026-10-01

RELEVANCE

7/ 10

AUTHOR

Damon Chen

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH43m ago

Context Language Models Let Agents Rewrite Context

Context Language Models let agents directly edit file-backed context, deciding what to retain, compact, or offload during long-running tasks. The paper reports stronger benchmark results with lower compute, plus Suffix Cache Reuse for more efficient serving. Paper: https://arxiv.org/abs/2609.37725; Code: https://github.com/facebookresearch/context-language-models

INFRA57m ago

Serval Makes SeatGeek’s AI Rollout Scalable

Serval’s SeatGeek case study shows how a company-wide ChatGPT rollout generated 300 IT requests on day one, with 60% of employees filing tickets by day three. Serval later automated 406 Claude license requests with zero human touches.

TUTORIAL1h ago

Self-Improving Agents Teaches Adaptive Harnesses

Micheal Lanham’s Manning MEAP shows developers how to improve production agents without fine-tuning by optimizing prompts, memory, reasoning scaffolds, tools, and code around a frozen model. It includes hands-on HelixAgent projects, evaluation loops, and production controls.