Tesana builds 2.5D RPG via single prompt

// 2h agoPRODUCT LAUNCH

Tesana builds 2.5D RPG via single prompt

Tesana’s "prompt-to-world" engine generates a fully playable 2.5D orthographic RPG—complete with towns, NPCs, and turn-based combat—from a single natural language description. The platform automates the entire development pipeline, translating "vibe coding" into structured game logic and 3D environments.

// ANALYSIS

Tesana is shifting the generative AI paradigm from isolated asset creation to autonomous game loop synthesis.

–Uses the proprietary Muranyi-3 model to translate complex prompts into structured game code and interactive 3D scenes
–Eliminates traditional development hurdles by automating traversal, quest logic, and Pokémon-style combat systems
–Marks a significant leap in "vibe coding," allowing non-technical creators to build functional prototypes in minutes
–While early outputs lack the polish of commercial titles, the integrated asset pipeline suggests a disruptive future for indie game development

// TAGS

tesanaai-coding3d-genagentgame-devno-codedevtoolframework

DISCOVERED

2h ago

2026-05-21

PUBLISHED

2h ago

2026-05-21

RELEVANCE

8/ 10

AUTHOR

TesanaAI

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS36m ago

Anthropic's ethical pause cuts Claude misalignment

Anthropic says it tested a tool Claude could call mid-task to get a brief reminder of its ethical commitments, and the model used it at key moments before consequential actions. In internal alignment evaluations, weaving that pause into the decision loop reduced misaligned behavior, though Anthropic says it still needs to separate the effect of the reminder itself from the effect of pausing to reflect.

BENCHMARK59m ago

Composer 2.5 tops CursorBench, Gemini 3.5 Flash slips

Composer 2.5 scored 63.2% on the newest CursorBench evaluation, matching flagship performance at 20x less cost. The benchmark results highlight its immense value for AI-assisted coding tasks, while Google's Gemini 3.5 Flash disappointed by falling to tenth place.

UPDATE1h ago

Anthropic adds self-hosted sandboxes, MCP tunnels to Managed Agents

Anthropic has updated Claude Managed Agents with self-hosted sandboxes in public beta and MCP tunnels in research preview. This hybrid architecture lets enterprises run tools and private MCP servers securely inside their own networks while Anthropic handles the orchestration loop.