# agentic AI insights

Rangoon Insights reporting and guides tagged agentic AI.

Canonical: https://rangoon.ai/insights/tags/agentic-ai/

## Topics
- [Agent systems](https://rangoon.ai/insights/topics/agents/): Agent runtimes, handoffs, tools, and the boundaries that make them reviewable.
- [Governance](https://rangoon.ai/insights/topics/governance/): Policy, identity, authorization, approvals, and evidence for consequential work.
- [Infrastructure](https://rangoon.ai/insights/topics/infrastructure/): Model serving, sandboxes, tool services, and deployment boundaries.
- [Models](https://rangoon.ai/insights/topics/models/): Inference choices, local serving, compatibility, and operational tradeoffs.

## Stories
- [DeepSeek separated stable V3.2 tool use from the temporary V3.2-Speciale endpoint](https://rangoon.ai/insights/archive-deepseek-v3-2-speciale-december-2025/)
  DeepSeek launched stable V3.2 and the API-only V3.2-Speciale on December 1, 2025, separating tool-enabled modes from a temporary reasoning variant.
- [Kimi K2-0905 made context, tool parsing, and serving configuration one release surface](https://rangoon.ai/insights/archive-moonshot-kimi-k2-0905-september-2025/)
  Moonshot AI announced Kimi K2-0905 on September 5, 2025, citing a 256K context window, enhanced frontend and tool-calling work, and broader agent-scaffold integration.
- [GLM-4.5 put hybrid reasoning modes and open weights in one release record](https://rangoon.ai/insights/archive-zai-glm-4-5-july-2025/)
  Z.AI introduced GLM-4.5 and GLM-4.5-Air on July 28, 2025, describing hybrid reasoning modes, agentic capabilities, and open-weight distribution.
- [Perplexity launched Comet first for Max subscribers, joining web browsing with an in-browser assistant](https://rangoon.ai/insights/archive-perplexity-comet-july-2025/)
  Perplexity launched Comet on July 9, 2025, initially offering its AI browser to Max subscribers while planning invite-only waitlist access over the summer.
- [NVIDIA Llama Nemotron Super made model-family labels insufficient for agents](https://rangoon.ai/insights/archive-nvidia-llama-nemotron-super-2025/)
  NVIDIA announced Llama Nemotron reasoning models on March 18, 2025, including Super. A family benchmark needs the exact size, quantization, tools, prompts, and agent harness.


## More information

- [Documentation index](https://rangoon.ai/llms.txt)
- [AI access and policies](https://rangoon.ai/ai/)
- [Source repository](https://github.com/hypler-dev/rangoon)